Self-contained audio and annotation gallery · built 2026-10-03 10:34 UTC

Hear what the Whisper multitask models predict

Thirty clips: twelve generated predictions from three listening studies, twelve seeded Emolia/Emilia samples in six languages, and six curated P3 test clips with inserted vocal bursts. The same audio is annotated by completed Whisper Tiny and Whisper Base checkpoints. Each player contains Base64 audio, so this is one self-contained file.

Model weights, inference and training code · Scaling Ladder dataset

Training-reference z-scores. z = (raw model prediction − training teacher median) / training teacher standard deviation. The first 100 targets use all 100,858 S9 Ladder t0+t1 clips. The additional 92 use a seeded 100,000-example P3 training subset. z shows how unusual a score is for that dimension; it is not a probability, preference or human rating. Interest and Concentration no longer dominate just because of high raw baselines. These display statistics do not change checkpoint inference.

What is shown

All 192 scalar outputs per model, grouped into emotions, VoiceNet, genuineness, blend, Empathic Insight Plus, AudioBox, DNSMOS, burst count and VoiceCLAP attributes. R_quality was trained from Ladder but has no P3 test labels. Character rate (CPS) is computed from source metadata when available; it is not a learned head. Raw VoiceCLAP 768D and BUD-E 3072D embeddings were stored as training sidecars but are not outputs of these checkpoints.

Speaker vectors

Each checkpoint predicts Orange timbre (128D) and identity (250D). A cosine of 1 means identical direction to the Orange teacher vector; values closer to 1 indicate stronger reconstruction. The full vectors are expandable below each clip.

Burst times

The frame head predicts a value every 20 ms. Bars and the start/end list use a fixed 0.5 threshold with no smoothing. The separate count head is a regression estimate and may differ from the number of contiguous bars.

Dataset scope

Generated examples are from the three supplied HTML studies. Natural examples are two seeded Emolia clips per language from six shards; they may occur in training. The six P3 clips are from the source-disjoint test split but deliberately selected for distinctive teacher emotion scores and inserted bursts. This curated gallery is for interpretation, not a held-out performance estimate. Consult the separate test report in the model repository.

Showing all 30 clips

g01EnglishDPO acting study

HVSAC-001 · en · targets: Doubt, Sadness, Triumph

Generated TTS prediction · Rank 16 × 0.50 · C01 · 19.7 s

Grandma... I am beside your hospital bed, holding the sealed letter you gave me. I thought it would explain the secret... instead it feels like you trusted me with your whole past. I wish I could ask what to do, but I will carry this truth forward.

Tiny Base · values are model estimates, not ground truth

Strongest emotions relative to training

Thankfulness Gratitude

z +1.45 / +2.49raw 1.05 / 1.78

Relief

z +0.97 / +1.76raw 0.70 / 1.23

Sadness

z +1.73 / +1.55raw 1.31 / 1.17

Shame

z +1.65 / +1.24raw 0.85 / 0.65

Disappointment

z +1.46 / +1.29raw 1.02 / 0.90

Distress

z +1.42 / +1.26raw 1.16 / 1.03

Contemplation

z +1.00 / +1.32raw 0.68 / 0.87

The center of each bar is the S9 teacher median. Positive z is to the right; negative z is to the left. Ranking uses z, not raw teacher units.

Strongest VoiceNet dimensions relative to training

Authoritative style (S_AUTH)

z +1.69 / +2.13raw 2.85 / 3.31

Fullness (FULL)

z +2.05 / +1.98raw 3.60 / 3.54

Content appropriateness (EXPL)

z +1.88 / +1.93raw 0.69 / 0.71

Narrator style (S_NARR)

z +1.91 / +1.74raw 4.07 / 3.83

Esthetics (ESTH)

z +1.85 / +1.61raw 3.85 / 3.66

Chest resonance (R_CHST)

z +1.67 / +1.67raw 3.55 / 3.55

Mixed resonance (R_MIXD)

z +1.53 / +1.34raw 2.72 / 2.56

All 57 VoiceNet predictions, including raw units, are in the full table below. These seven are ranked by z; the top values may differ from the strongest raw dimensions.

Voice, speed and quality scores in context

Genuineness (0–6)z -1.06 / -1.10raw 0.62 / 0.55

Vocal-burst blend (0–10)z -1.00 / -1.31raw 3.95 / 3.08

Content enjoyment (CE)z +0.35 / +0.44raw 5.16 / 5.24

Production quality (PQ)z +0.34 / +0.12raw 7.34 / 7.15

Speech signal quality, calibratedz +0.11 / +0.23raw 3.54 / 3.60

Background quality, calibratedz +0.54 / +0.68raw 3.89 / 4.02

Overall quality, calibratedz +0.55 / +0.79raw 3.18 / 3.32

P.808 MOS estimatez +0.86 / +1.05raw 3.85 / 3.94

score content enjoymentz +0.72 / +1.10raw 4.72 / 4.84

score overall qualityz +0.08 / +0.63raw 2.69 / 2.97

Background Noisez -2.04 / -2.88raw 0.27 / 0.05

Tempo (TEMP)z +0.12 / +0.17raw 2.26 / 2.32

Arousal (AROU)z -0.24 / +0.04raw 2.08 / 2.40

Valence (VALN)z -0.30 / -0.49raw 1.99 / 1.78

Recording quality (RCQL)z +0.75 / +0.68raw 3.42 / 3.36

Background noise (BKGN)z +1.07 / +0.82raw 3.51 / 3.33

talking speedz +1.36 / +1.32raw 14.14 / 13.97

Characters per second (CPS): 12.59 raw · z +0.95

Characters in source transcript divided by audio seconds; not a Whisper output. Reference: 86,334 P3 training teacher values, median 9.03, SD 3.76. Cross-language character counts depend on writing system; compare with care.

Orange speaker embedding reconstruction

Cosine against Orange on this same clip (higher means closer to that teacher vector):

Embedding	Tiny	Base
Timbre · 128D	0.761	0.806
Identity · 250D	0.698	0.680

Vocal-burst regions

Tiny

Base

0 s19.7 s

Verified burst intervals are unavailable for this clip.

Tiny: 0 regions, count-head estimate 0.00; Base: 0 regions, count-head estimate 0.01.

Exact predicted start and end times

Model	Region	Start (s)	End (s)	Duration (s)

All 192 score slots · raw and z values

z = (prediction − training teacher median) / training teacher SD. Higher values are not universally better. R_quality has Ladder training labels but no P3 test labels, so no held-out P3 metric is available for it.

#	Target	Tiny raw	Tiny z	Base raw	Base z	Train median	Train SD
Emotion scores Forty clip-level Empathic Insight emotion teacher outputs. Each row evaluates one named emotion score.
0	Affectionemo_Affection	0.698	+1.21	0.575	+1.00	0.007	0.570
1	Amusementemo_Amusement	0.174	+0.20	-0.095	-0.11	-0.001	0.885
2	Angeremo_Anger	0.495	+0.80	0.588	+0.95	0.004	0.613
3	Astonishment Surpriseemo_Astonishment_Surprise	0.485	+0.84	0.314	+0.54	0.005	0.572
4	Aweemo_Awe	0.253	+0.59	0.039	+0.09	0.000	0.427
5	Bitternessemo_Bitterness	0.434	+1.01	0.192	+0.43	0.013	0.415
6	Concentrationemo_Concentration	0.810	+0.24	1.216	+0.78	0.634	0.741
7	Confusionemo_Confusion	0.450	+0.83	0.447	+0.83	0.001	0.540
8	Contemplationemo_Contemplation	0.683	+1.00	0.869	+1.32	0.082	0.598
9	Contemptemo_Contempt	0.167	+0.36	-0.019	-0.04	-0.000	0.464
10	Contentmentemo_Contentment	0.426	+0.83	0.378	+0.74	0.000	0.514
11	Disappointmentemo_Disappointment	1.024	+1.46	0.903	+1.29	0.000	0.700
12	Disgustemo_Disgust	0.346	+0.69	0.026	+0.04	0.007	0.489
13	Distressemo_Distress	1.165	+1.42	1.034	+1.26	0.000	0.821
14	Doubtemo_Doubt	0.252	+0.53	0.394	+0.83	0.006	0.466
15	Elationemo_Elation	0.131	+0.16	0.011	-0.00	0.012	0.728
16	Embarrassmentemo_Embarrassment	0.327	+0.66	0.374	+0.77	0.043	0.430
17	Emotional Numbnessemo_Emotional_Numbness	0.683	+0.74	0.592	+0.64	0.004	0.917
18	Fatigue Exhaustionemo_Fatigue_Exhaustion	0.174	+0.27	0.044	+0.03	0.028	0.539
19	Fearemo_Fear	0.625	+1.00	0.514	+0.82	0.015	0.610
20	Helplessnessemo_Helplessness	0.885	+1.28	0.824	+1.19	-0.004	0.696
21	Hope Enthusiasm Optimismemo_Hope_Enthusiasm_Optimism	0.429	+0.41	0.289	+0.23	0.117	0.760
22	Impatience and Irritabilityemo_Impatience_and_Irritability	0.437	+0.41	0.477	+0.47	0.149	0.705
23	Infatuationemo_Infatuation	0.445	+0.86	0.288	+0.57	-0.015	0.533
24	Interestemo_Interest	1.790	+0.22	1.658	+0.08	1.589	0.907
25	Intoxication Altered States of Consciousnessemo_Intoxication_Altered_States_of_Consciousness	-0.022	+0.01	-0.040	-0.03	-0.025	0.559
26	Jealousy and Envyemo_Jealousy_and_Envy	0.255	+0.44	0.088	+0.06	0.059	0.442
27	Longingemo_Longing	0.890	+1.27	0.623	+0.85	0.087	0.632
28	Malevolence Maliceemo_Malevolence_Malice	0.529	+0.89	0.335	+0.52	0.055	0.534
29	Painemo_Pain	0.673	+1.16	0.402	+0.70	-0.002	0.579
30	Pleasure Ecstasyemo_Pleasure_Ecstasy	0.301	+0.46	0.090	+0.12	0.017	0.614
31	Prideemo_Pride	0.211	+0.41	0.442	+0.87	0.002	0.509
32	Reliefemo_Relief	0.696	+0.97	1.231	+1.76	0.033	0.681
33	Sadnessemo_Sadness	1.313	+1.73	1.172	+1.55	0.000	0.759
34	Sexual Lustemo_Sexual_Lust	0.353	+0.65	0.049	+0.04	0.030	0.494
35	Shameemo_Shame	0.854	+1.65	0.647	+1.24	0.013	0.510
36	Sournessemo_Sourness	0.399	+0.92	0.050	+0.13	-0.005	0.439
37	Teasingemo_Teasing	0.333	+0.61	0.026	+0.05	0.000	0.545
38	Thankfulness Gratitudeemo_Thankfulness_Gratitude	1.053	+1.45	1.777	+2.49	0.041	0.697
39	Triumphemo_Triumph	0.110	+0.22	0.230	+0.46	-0.007	0.521
VoiceNet dimensions Fifty-seven VoiceNet voice, delivery, style, and recording dimensions. Codes are expanded in the target column.
40	Perceived voice age (AGEV)vn_AGEV_reg	3.164	+0.14	3.375	+0.32	2.984	1.238
41	Arousal (AROU)vn_AROU_reg	2.085	-0.24	2.403	+0.04	2.359	1.147
42	Arousal shift (ARSH)vn_ARSH_reg	2.369	-0.24	2.739	+0.18	2.580	0.867
43	Vocal attack (ATCK)vn_ATCK_reg	2.162	+0.00	2.219	+0.04	2.162	1.295
44	Background noise (BKGN)vn_BKGN_reg	3.515	+1.07	3.326	+0.82	2.703	0.761
45	Brightness (BRGT)vn_BRGT_reg	2.372	+0.47	2.331	+0.42	1.991	0.813
46	Speech chunking (CHNK)vn_CHNK_reg	2.568	+0.58	2.525	+0.55	1.847	1.239
47	Articulation clarity (CLRT)vn_CLRT_reg	2.529	+0.54	2.735	+0.76	2.018	0.945
48	Cognitive load (COGL)vn_COGL_reg	1.437	-0.62	1.260	-0.79	2.094	1.061
49	Dynamic arc (DARC)vn_DARC_reg	1.139	-0.35	1.142	-0.34	1.615	1.380
50	Disfluency (DFLU)vn_DFLU_reg	0.914	-1.33	0.951	-1.30	2.488	1.184
51	Emphasis (EMPH)vn_EMPH_reg	3.289	+0.45	3.129	+0.34	2.607	1.524
52	Esthetics (ESTH)vn_ESTH_reg	3.852	+1.85	3.663	+1.61	2.402	0.782
53	Content appropriateness (EXPL)vn_EXPL_reg	0.692	+1.88	0.710	+1.93	0.086	0.322
54	Focus (FOCS)vn_FOCS_reg	3.243	+0.82	3.117	+0.70	2.344	1.102
55	Fullness (FULL)vn_FULL_reg	3.601	+2.05	3.539	+1.98	1.778	0.889
56	Perceived gender (GEND)vn_GEND_reg	4.883	+0.52	5.076	+0.64	4.055	1.588
57	Harmonicity (HARM)vn_HARM_reg	2.219	-0.31	2.253	-0.27	2.480	0.836
58	Metallic character (METL)vn_METL_reg	1.235	-0.40	1.343	-0.29	1.621	0.958
59	Pitch range (RANG)vn_RANG_reg	2.178	-0.82	2.174	-0.82	2.914	0.897
60	Recording quality (RCQL)vn_RCQL_reg	3.416	+0.75	3.360	+0.68	2.754	0.888
61	Vocal register (REGS)vn_REGS_reg	0.790	-0.32	0.750	-0.35	1.198	1.268
62	Respiration (RESP)vn_RESP_reg	2.207	-0.45	1.856	-0.78	2.680	1.056
63	Roughness (ROUG)vn_ROUG_reg	2.160	+0.14	2.071	+0.04	2.033	0.887
64	Chest resonance (R_CHST)vn_R_CHST_reg	3.547	+1.67	3.547	+1.67	2.135	0.844
65	Head resonance (R_HEAD)vn_R_HEAD_reg	1.630	-0.63	1.703	-0.54	2.148	0.822
66	Mask resonance (R_MASK)vn_R_MASK_reg	1.139	-0.76	1.477	-0.43	1.908	1.005
67	Mixed resonance (R_MIXD)vn_R_MIXD_reg	2.723	+1.53	2.560	+1.34	1.436	0.841
68	Nasal resonance (R_NASL)vn_R_NASL_reg	2.503	-0.27	2.457	-0.32	2.791	1.047
69	Oral resonance (R_ORAL)vn_R_ORAL_reg	1.967	-0.29	2.064	-0.16	2.184	0.741
70	Throat resonance (R_THRT)vn_R_THRT_reg	1.991	-0.10	2.003	-0.08	2.070	0.803
71	Smoothness (SMTH)vn_SMTH_reg	3.044	+0.82	2.966	+0.75	2.143	1.093
72	Stance (STNC)vn_STNC_reg	3.025	+0.35	3.210	+0.51	2.633	1.137
73	Speech structure (STRU)vn_STRU_reg	2.869	+0.76	3.108	+1.01	2.137	0.958
74	ASMR style (S_ASMR)vn_S_ASMR_reg	1.796	+0.30	1.199	-0.12	1.370	1.411
75	Authoritative style (S_AUTH)vn_S_AUTH_reg	2.851	+1.69	3.305	+2.13	1.088	1.043
76	Cartoonish style (S_CART)vn_S_CART_reg	1.190	-0.26	1.011	-0.39	1.560	1.401
77	Casual style (S_CASU)vn_S_CASU_reg	2.569	-0.96	2.415	-1.08	3.793	1.278
78	Conversational style (S_CONV)vn_S_CONV_reg	2.516	-0.06	2.821	+0.17	2.594	1.318
79	Dramatic style (S_DRAM)vn_S_DRAM_reg	2.820	+0.09	2.798	+0.07	2.721	1.148
80	Formal style (S_FORM)vn_S_FORM_reg	2.569	+1.35	2.624	+1.40	1.195	1.021
81	Monologue style (S_MONO)vn_S_MONO_reg	3.824	+0.78	3.571	+0.58	2.824	1.284
82	Narrator style (S_NARR)vn_S_NARR_reg	4.065	+1.91	3.830	+1.74	1.307	1.446
83	Newsreader style (S_NEWS)vn_S_NEWS_reg	0.881	+0.83	1.043	+1.12	0.408	0.568
84	Playful style (S_PLAY)vn_S_PLAY_reg	1.024	-1.01	0.857	-1.14	2.352	1.315
85	Ranting or angry style (S_RANT)vn_S_RANT_reg	0.203	-0.78	0.819	-0.31	1.213	1.289
86	Storytelling style (S_STRY)vn_S_STRY_reg	4.236	+1.29	4.323	+1.35	2.480	1.366
87	Teacher or didactic style (S_TECH)vn_S_TECH_reg	1.147	+0.41	0.789	+0.12	0.646	1.227
88	Whispered talking style (S_WHIS)vn_S_WHIS_reg	3.878	+1.41	3.216	+1.00	1.597	1.618
89	Tempo (TEMP)vn_TEMP_reg	2.262	+0.12	2.319	+0.17	2.117	1.190
90	Tension (TENS)vn_TENS_reg	2.105	+0.64	2.287	+0.86	1.559	0.852
91	Valence (VALN)vn_VALN_reg	1.993	-0.30	1.782	-0.49	2.328	1.118
92	Valence shift (VALS)vn_VALS_reg	2.374	-0.13	2.309	-0.19	2.518	1.079
93	Velocity flux (VFLX)vn_VFLX_reg	1.057	-0.99	1.052	-1.00	2.256	1.208
94	Volatility (VOLT)vn_VOLT_reg	2.098	-0.55	1.877	-0.80	2.586	0.886
95	Vulnerability (VULN)vn_VULN_reg	2.051	-0.61	1.548	-1.12	2.648	0.984
96	Warmth (WARM)vn_WARM_reg	3.892	+1.44	3.602	+1.13	2.578	0.909
Genuineness, blend, and legacy quality Genuineness and vocal-burst blend are predicted. R_quality has Ladder training labels but no valid P3 test labels.
97	Genuineness (0–6)genuineness_0_6	0.616	-1.06	0.553	-1.10	2.332	1.621
98	Vocal-burst blend (0–10)blend_0_10	3.947	-1.00	3.077	-1.31	6.676	2.738
99	Legacy R_quality (no P3 test labels)R_quality	0.510	-1.73	0.412	-2.02	1.095	0.338
Empathic Insight Plus extra scores Nineteen additional clip-level teacher scores, including background noise and content enjoyment.
100	Ageeiv_extra:Age	3.218	-0.11	3.270	+0.07	3.250	0.293
101	Arousaleiv_extra:Arousal	1.560	+0.62	1.240	-0.11	1.289	0.435
102	Authenticityeiv_extra:Authenticity	2.963	+1.94	2.923	+1.68	2.667	0.153
103	Background Noiseeiv_extra:Background_Noise	0.268	-2.04	0.047	-2.88	0.808	0.264
104	Confident vs. Hesitanteiv_extra:Confident_vs._Hesitant	1.160	+0.40	1.217	+0.59	1.040	0.303
105	Gendereiv_extra:Gender	-0.744	-0.12	-1.145	-0.53	-0.621	0.999
106	High-Pitched vs. Low-Pitchedeiv_extra:High-Pitched_vs._Low-Pitched	1.991	+0.65	2.091	+1.05	1.827	0.250
107	Monotone vs. Expressiveeiv_extra:Monotone_vs._Expressive	2.059	+0.42	2.004	+0.31	1.859	0.470
108	Recording Qualityeiv_extra:Recording_Quality	2.577	+1.31	2.648	+1.52	2.144	0.332
109	Serious vs. Humorouseiv_extra:Serious_vs._Humorous	0.793	-0.40	0.728	-0.59	0.929	0.340
110	Soft vs. Harsheiv_extra:Soft_vs._Harsh	0.444	+0.51	0.410	+0.41	0.281	0.320
111	Submissive vs. Dominanteiv_extra:Submissive_vs._Dominant	0.793	+1.29	0.693	+0.98	0.376	0.324
112	Valenceeiv_extra:Valence	-0.291	-0.78	-0.215	-0.58	0.005	0.380
113	Vulnerable vs. Emotionally Detachedeiv_extra:Vulnerable_vs._Emotionally_Detached	1.708	-0.01	1.765	+0.12	1.715	0.437
114	Warm vs. Coldeiv_extra:Warm_vs._Cold	-0.043	-0.31	-0.021	-0.24	0.051	0.300
115	score background qualityeiv_extra:score_background_quality	3.410	+0.16	3.616	+0.45	3.301	0.693
116	score content enjoymenteiv_extra:score_content_enjoyment	4.724	+0.72	4.840	+1.10	4.507	0.303
117	score overall qualityeiv_extra:score_overall_quality	2.692	+0.08	2.971	+0.63	2.652	0.507
118	score speech qualityeiv_extra:score_speech_quality	1.801	-0.05	1.844	+0.25	1.808	0.146
Meta AudioBox Aesthetics Four AudioBox aesthetic teacher outputs. Expansions follow the official Meta model card.
119	Content enjoyment (CE)audiobox:CE	5.159	+0.35	5.242	+0.44	4.799	1.018
120	Content usefulness (CU)audiobox:CU	6.464	+0.81	6.401	+0.75	5.649	1.001
121	Production complexity (PC)audiobox:PC	1.883	-0.28	1.549	-0.48	2.331	1.617
122	Production quality (PQ)audiobox:PQ	7.339	+0.34	7.148	+0.12	7.044	0.879
Microsoft DNSMOS Seven DNSMOS teacher outputs: raw and calibrated SIG/BAK/OVRL estimates plus P.808 MOS.
123	Speech signal quality, rawdnsmos:SIG_raw	4.010	+0.16	4.116	+0.32	3.900	0.669
124	Background quality, rawdnsmos:BAK_raw	4.109	+0.80	4.232	+0.91	3.211	1.124
125	Overall quality, rawdnsmos:OVRL_raw	3.630	+0.67	3.840	+0.93	3.085	0.812
126	Speech signal quality, calibrateddnsmos:SIG	3.542	+0.11	3.605	+0.23	3.488	0.501
127	Background quality, calibrateddnsmos:BAK	3.887	+0.54	4.017	+0.68	3.389	0.928
128	Overall quality, calibrateddnsmos:OVRL	3.176	+0.55	3.319	+0.79	2.840	0.606
129	P.808 MOS estimatednsmos:P808_MOS	3.847	+0.86	3.942	+1.05	3.421	0.496
Vocal-burst count The regression target is log(1 + count). A separate table also reports count error after inverse transformation.
130	Vocal-burst count, log(1 + count)burst_count_log1p	-0.008	-0.01	0.013	+0.02	0.000	0.647
VoiceCLAP attributes Sixty-one individual VoiceCLAP attribute teacher scores. The raw 768D VoiceCLAP embedding is stored in sidecars but is not a model output.
131	Affectionvoiceclap_attribute:Affection	1.001	+0.10	1.175	+0.41	0.947	0.554
132	Agevoiceclap_attribute:Age	3.061	-0.31	3.309	+0.15	3.229	0.547
133	Amusementvoiceclap_attribute:Amusement	0.299	-0.16	0.360	-0.06	0.392	0.572
134	Angervoiceclap_attribute:Anger	1.228	+0.47	1.370	+0.75	0.992	0.506
135	Arousalvoiceclap_attribute:Arousal	1.536	+0.19	1.731	+0.50	1.420	0.622
136	Astonishment Surprisevoiceclap_attribute:Astonishment_Surprise	0.735	+0.47	0.870	+0.75	0.509	0.479
137	Authenticityvoiceclap_attribute:Authenticity	3.105	+2.00	3.148	+2.26	2.770	0.167
138	Awevoiceclap_attribute:Awe	0.751	+0.82	0.839	+1.16	0.539	0.259
139	Background Noisevoiceclap_attribute:Background_Noise	0.177	-1.48	0.234	-1.26	0.567	0.264
140	Bitternessvoiceclap_attribute:Bitterness	0.653	+0.25	0.737	+0.61	0.592	0.236
141	Concentrationvoiceclap_attribute:Concentration	1.204	-0.02	1.116	-0.18	1.214	0.531
142	Confident vs. Hesitantvoiceclap_attribute:Confident_vs._Hesitant	0.939	-0.28	1.034	-0.08	1.069	0.468
143	Confusionvoiceclap_attribute:Confusion	0.447	-0.59	0.481	-0.49	0.643	0.334
144	Contemplationvoiceclap_attribute:Contemplation	1.049	+0.66	0.877	+0.24	0.780	0.406
145	Contemptvoiceclap_attribute:Contempt	0.799	+0.27	0.870	+0.48	0.709	0.339
146	Contentmentvoiceclap_attribute:Contentment	0.709	+0.39	0.571	-0.06	0.588	0.307
147	Disappointmentvoiceclap_attribute:Disappointment	1.060	+1.03	1.131	+1.27	0.760	0.291
148	Disgustvoiceclap_attribute:Disgust	0.539	-0.41	0.679	+0.26	0.625	0.207
149	Distressvoiceclap_attribute:Distress	1.207	+0.80	1.391	+1.33	0.927	0.350
150	Doubtvoiceclap_attribute:Doubt	0.521	-0.07	0.602	+0.36	0.535	0.188
151	Elationvoiceclap_attribute:Elation	0.655	+0.29	0.694	+0.39	0.539	0.397
152	Embarrassmentvoiceclap_attribute:Embarrassment	0.275	-0.10	0.340	+0.11	0.307	0.314
153	Emotional Numbnessvoiceclap_attribute:Emotional_Numbness	0.839	+0.66	0.885	+0.83	0.664	0.266
154	Fatigue Exhaustionvoiceclap_attribute:Fatigue_Exhaustion	0.490	+0.11	0.420	-0.16	0.462	0.261
155	Fearvoiceclap_attribute:Fear	0.895	+1.31	0.950	+1.57	0.618	0.212
156	Gendervoiceclap_attribute:Gender	-0.767	-0.61	-0.940	-0.78	-0.151	1.005
157	Helplessnessvoiceclap_attribute:Helplessness	1.017	+1.34	1.040	+1.42	0.658	0.268
158	High-Pitched vs. Low-Pitchedvoiceclap_attribute:High-Pitched_vs._Low-Pitched	2.120	+0.75	2.132	+0.78	1.840	0.375
159	Hope Enthusiasm Optimismvoiceclap_attribute:Hope_Enthusiasm_Optimism	0.917	+0.54	1.005	+0.76	0.705	0.396
160	Impatience and Irritabilityvoiceclap_attribute:Impatience_and_Irritability	0.878	-0.32	1.165	+0.21	1.052	0.541
161	Infatuationvoiceclap_attribute:Infatuation	0.554	-0.16	0.768	+0.48	0.608	0.332
162	Interestvoiceclap_attribute:Interest	1.476	-0.28	1.402	-0.45	1.598	0.440
163	Intoxication Altered States of Consciousnessvoiceclap_attribute:Intoxication_Altered_States_of_Consciousness	-0.070	-1.24	0.093	-0.88	0.502	0.463
164	Jealousy & Envyvoiceclap_attribute:Jealousy_&_Envy	0.649	+0.52	0.920	+1.62	0.523	0.245
165	Longingvoiceclap_attribute:Longing	0.784	+1.12	0.808	+1.23	0.538	0.220
166	Malevolence Malicevoiceclap_attribute:Malevolence_Malice	0.918	+0.25	0.944	+0.32	0.833	0.346
167	Monotone vs. Expressivevoiceclap_attribute:Monotone_vs._Expressive	1.983	+0.35	1.906	+0.22	1.775	0.594
168	Painvoiceclap_attribute:Pain	0.528	+0.67	0.652	+1.24	0.381	0.218
169	Pleasure Ecstasyvoiceclap_attribute:Pleasure_Ecstasy	0.612	+0.36	0.680	+0.59	0.503	0.301
170	Pridevoiceclap_attribute:Pride	0.988	+0.59	1.346	+1.62	0.780	0.349
171	Recording Qualityvoiceclap_attribute:Recording_Quality	2.876	+1.72	2.776	+1.41	2.313	0.328
172	Reliefvoiceclap_attribute:Relief	1.313	+0.70	1.515	+1.18	1.025	0.415
173	Sadnessvoiceclap_attribute:Sadness	1.222	+1.50	1.266	+1.64	0.752	0.313
174	Serious vs. Humorousvoiceclap_attribute:Serious_vs._Humorous	0.572	-0.41	0.483	-0.56	0.803	0.568
175	Sexual Lustvoiceclap_attribute:Sexual_Lust	0.449	-0.44	0.420	-0.51	0.635	0.419
176	Shamevoiceclap_attribute:Shame	0.960	+1.53	1.103	+2.04	0.526	0.283
177	Soft vs. Harshvoiceclap_attribute:Soft_vs._Harsh	0.303	+0.40	0.054	-0.29	0.160	0.360
178	Sournessvoiceclap_attribute:Sourness	0.715	+0.03	0.798	+0.32	0.706	0.291
179	Submissive vs. Dominantvoiceclap_attribute:Submissive_vs._Dominant	0.922	+0.83	0.950	+0.91	0.623	0.359
180	Teasingvoiceclap_attribute:Teasing	0.597	+0.15	0.673	+0.35	0.540	0.379
181	Thankfulness Gratitudevoiceclap_attribute:Thankfulness_Gratitude	1.813	+0.81	1.844	+0.87	1.384	0.529
182	Triumphvoiceclap_attribute:Triumph	0.988	+0.76	1.076	+1.00	0.716	0.359
183	Valencevoiceclap_attribute:Valence	-0.113	-0.17	-0.415	-0.64	-0.007	0.635
184	Vulnerable vs. Emotionally Detachedvoiceclap_attribute:Vulnerable_vs._Emotionally_Detached	1.920	+0.51	2.009	+0.67	1.638	0.556
185	Warm vs. Coldvoiceclap_attribute:Warm_vs._Cold	0.112	+0.45	-0.030	+0.09	-0.066	0.400
186	durationvoiceclap_attribute:duration	11.444	+0.08	12.331	+0.22	10.914	6.354
187	score background qualityvoiceclap_attribute:score_background_quality	3.550	+0.61	3.700	+0.91	3.245	0.498
188	score content enjoymentvoiceclap_attribute:score_content_enjoyment	4.862	+1.40	4.915	+1.76	4.656	0.147
189	score overall qualityvoiceclap_attribute:score_overall_quality	2.870	+0.57	2.956	+0.78	2.635	0.412
190	score speech qualityvoiceclap_attribute:score_speech_quality	1.925	+0.50	1.893	+0.03	1.891	0.069
191	talking speedvoiceclap_attribute:talking_speed	14.143	+1.36	13.967	+1.32	9.028	3.756

All Orange embedding components

The cosine above is the meaningful vector-level comparison; component values have no standalone semantic label.

Timbre — all 128 vector components

Dimension	Tiny	Base	Orange teacher
0	0.0691	0.0211	-0.0450
1	-0.0576	-0.0845	-0.0794
2	-0.0744	-0.0543	-0.0784
3	0.0771	0.0616	0.1256
4	-0.0230	-0.0226	-0.0457
5	-0.0141	-0.0158	-0.0266
6	0.0885	0.0936	0.1438
7	-0.0702	-0.0737	-0.0731
8	0.0549	0.0525	0.0999
9	0.0372	0.0703	0.1221
10	0.0095	0.0346	0.0981
11	0.0048	0.0688	0.1649
12	-0.0607	-0.0462	0.0525
13	-0.0052	-0.0130	0.0238
14	-0.0771	-0.0450	0.0221
15	-0.0557	-0.0942	-0.0716
16	-0.0801	-0.1183	-0.0989
17	-0.0018	-0.0208	-0.0589
18	0.0641	0.0367	-0.0709
19	0.0219	-0.0531	-0.0641
20	0.0202	0.0046	-0.0800
21	0.0843	0.0435	0.1161
22	-0.1236	-0.0564	-0.0751
23	-0.0089	-0.0147	0.0688
24	-0.0630	-0.0881	-0.0645
25	-0.0855	-0.0809	-0.0702
26	-0.0454	0.0026	-0.0188
27	-0.0774	-0.0845	-0.0745
28	0.0805	0.0634	0.0980
29	-0.1351	-0.0869	-0.0856
30	0.1801	0.0634	-0.0078
31	0.3907	0.3912	0.2549
32	-0.0885	-0.0924	-0.0770
33	0.0359	0.0727	0.0933
34	-0.0790	-0.0459	-0.0717
35	-0.0109	0.0129	0.0792
36	-0.0694	-0.0851	-0.0859
37	0.1251	0.0241	-0.0134
38	0.0166	-0.0122	0.0524
39	-0.1152	-0.1044	-0.0806
40	-0.0372	-0.0184	0.0240
41	-0.0557	-0.0721	-0.1149
42	0.0185	-0.0291	-0.0729
43	-0.0568	-0.0767	-0.0822
44	-0.0021	-0.0513	-0.0767
45	-0.0437	-0.0447	-0.0516
46	-0.0572	-0.0930	-0.0558
47	-0.0364	-0.0543	-0.0808
48	0.0135	-0.0120	-0.0702
49	-0.1045	-0.0845	-0.0454
50	0.0942	0.1201	0.1969
51	-0.0138	-0.0727	0.0269
52	0.0326	0.0308	-0.0307
53	-0.0992	-0.0930	-0.0815
54	0.0530	0.0374	0.0224
55	0.0778	0.1527	0.0919
56	0.0973	0.0815	0.1689
57	0.0173	-0.0039	0.0100
58	-0.1061	-0.0845	-0.0850
59	0.2365	0.2173	0.2803
60	-0.1206	-0.1322	-0.0771
61	0.0186	-0.0752	0.0222
62	-0.1122	-0.1123	-0.0747
63	-0.0241	0.0267	-0.0759
64	0.0782	0.1425	0.0364
65	-0.0546	-0.0492	-0.0652
66	0.0319	-0.0037	-0.0136
67	-0.1007	-0.0408	-0.0183
68	0.0387	0.0685	0.0794
69	-0.0671	-0.0694	-0.0732
70	-0.1030	-0.0779	-0.0828
71	-0.0143	0.0177	0.0522
72	-0.0641	-0.0839	-0.0459
73	-0.1251	-0.0857	-0.0977
74	-0.0557	-0.0610	0.0223
75	-0.0131	0.0210	-0.0970
76	-0.0912	-0.0779	-0.0775
77	0.0538	0.1328	0.0425
78	-0.0086	-0.0417	-0.0461
79	-0.0740	-0.0900	-0.0693
80	0.1373	0.1956	0.1107
81	0.0610	0.0404	0.0525
82	0.0223	0.0918	0.0348
83	-0.1259	-0.0863	-0.0818
84	0.0488	0.1220	-0.0196
85	-0.0220	0.0625	0.0359
86	-0.0286	-0.0131	-0.0470
87	-0.0012	-0.0026	-0.0033
88	-0.0061	-0.0474	0.0259
89	0.1396	0.0936	0.1165
90	-0.1160	-0.1582	-0.0866
91	0.1900	0.1244	0.1757
92	-0.1496	-0.0924	-0.0201
93	-0.0717	-0.0589	-0.0781
94	0.0133	0.0264	-0.0480
95	-0.0935	-0.0906	-0.0858
96	0.1106	0.1872	0.0992
97	-0.0205	-0.0338	-0.0854
98	0.0477	0.0664	0.1279
99	-0.0618	-0.1075	-0.0793
100	-0.0303	-0.0318	-0.0848
101	0.0927	0.1195	0.1438
102	0.0740	0.1008	0.1376
103	-0.0599	-0.0115	-0.0844
104	-0.0004	-0.0029	-0.0781
105	-0.0942	-0.0954	-0.0770
106	-0.0256	0.0305	-0.0961
107	0.0204	0.0767	0.0771
108	0.0483	0.0501	-0.0866
109	-0.0801	-0.0857	-0.0784
110	0.1335	0.1382	0.2197
111	-0.0599	-0.0803	-0.0927
112	-0.1106	-0.1189	-0.0788
113	0.0488	0.0013	0.0237
114	-0.1267	-0.0978	-0.0861
115	-0.1068	-0.0930	-0.0757
116	-0.0683	-0.0869	-0.0685
117	0.2732	0.2137	0.1322
118	-0.0866	-0.0734	-0.0778
119	0.0422	0.0134	-0.0074
120	-0.0862	-0.1069	-0.0470
121	-0.1007	-0.1020	-0.0810
122	-0.0387	0.0501	0.0493
123	0.0209	-0.0094	-0.0509
124	0.0265	-0.0152	-0.0883
125	-0.0656	-0.0567	-0.0797
126	-0.0729	-0.1044	-0.0688
127	-0.1213	-0.0954	-0.0848

Identity — all 250 vector components

Dimension	Tiny	Base	Orange teacher
0	0.0074	0.0215	-0.0009
1	-0.1012	-0.1056	-0.0408
2	-0.0888	-0.0392	-0.0518
3	-0.1312	-0.1193	-0.0800
4	-0.0176	-0.0100	-0.0384
5	-0.0502	-0.0397	-0.0341
6	0.0215	0.0133	0.0061
7	0.0776	0.0226	-0.0117
8	-0.0202	0.0402	-0.0272
9	0.1859	0.1566	0.1617
10	0.1018	0.0873	0.0523
11	-0.0489	-0.0066	-0.0083
12	-0.0139	0.0141	-0.0158
13	-0.0410	-0.0410	-0.0372
14	-0.0472	-0.0251	-0.0509
15	0.0395	0.1219	0.0723
16	0.0615	0.0773	-0.0098
17	0.0540	0.0365	0.0939
18	-0.0601	-0.0449	-0.0429
19	-0.0199	0.0307	0.0381
20	-0.0366	-0.0183	-0.0200
21	-0.0379	-0.0631	-0.0391
22	-0.0143	-0.0507	-0.0168
23	-0.0731	-0.0036	-0.0408
24	-0.0166	0.0044	-0.0360
25	0.0008	-0.0025	-0.0455
26	-0.0328	-0.0673	-0.0465
27	-0.0070	-0.0071	-0.0343
28	-0.0871	-0.0694	-0.0457
29	0.0077	-0.0101	-0.0406
30	-0.0253	-0.0363	-0.0367
31	-0.0314	-0.0620	-0.0530
32	-0.0533	-0.0307	-0.0434
33	0.1196	0.0363	0.0891
34	-0.0320	0.0191	-0.0504
35	0.0116	0.0799	0.1178
36	-0.1668	-0.0678	-0.0446
37	-0.0032	-0.0357	-0.0292
38	-0.1422	-0.1598	-0.0585
39	-0.0584	-0.0164	-0.0231
40	-0.0275	-0.0597	0.0332
41	-0.0091	-0.0261	0.0111
42	0.0328	0.0639	0.0331
43	0.0150	0.0507	-0.0016
44	0.0152	0.0336	0.0193
45	-0.0639	-0.0272	-0.0484
46	-0.0151	-0.0256	-0.0149
47	0.0837	0.0547	0.1667
48	-0.0141	-0.0332	-0.0446
49	0.0036	-0.0289	0.0606
50	0.0248	0.0247	-0.0345
51	0.0916	0.0457	0.0936
52	-0.0149	-0.0363	-0.0416
53	-0.0090	0.0029	-0.0408
54	0.0769	0.0139	-0.0144
55	-0.0694	-0.0339	-0.0675
56	-0.0227	-0.0549	-0.0247
57	-0.0119	-0.0213	-0.0492
58	0.0615	0.0217	-0.0067
59	0.0571	0.0704	0.0519
60	-0.0649	-0.0699	-0.0442
61	0.0246	0.0307	0.0318
62	-0.0088	0.0334	0.1034
63	-0.0105	-0.0399	0.0972
64	-0.0074	0.0118	-0.0315
65	0.2160	0.1566	0.2203
66	-0.0895	-0.0562	-0.0507
67	0.0175	0.0251	0.1021
68	-0.0002	-0.0163	0.0495
69	-0.0132	-0.0188	-0.0324
70	-0.0502	-0.0502	0.0538
71	-0.0302	-0.0038	0.0491
72	-0.0412	-0.0736	-0.0467
73	0.0179	-0.0539	0.0465
74	-0.0502	-0.0725	-0.0455
75	0.1128	0.1309	0.1020
76	-0.0183	-0.0293	-0.0402
77	0.0403	0.0652	0.0429
78	-0.0120	-0.0214	0.0262
79	0.0796	0.1172	0.0973
80	-0.0256	0.0457	0.0467
81	0.0557	0.0678	0.1071
82	0.0367	0.0161	0.0224
83	-0.0537	-0.0544	-0.0374
84	-0.0584	-0.0141	-0.0635
85	-0.0496	-0.0618	-0.0450
86	-0.0043	-0.0017	-0.0402
87	-0.0759	-0.0179	-0.0291
88	-0.0800	-0.1004	-0.0445
89	-0.0208	-0.0452	-0.0407
90	0.0301	0.0339	0.0866
91	0.0362	0.0235	-0.0530
92	-0.0639	-0.0591	-0.0389
93	0.0182	-0.0668	-0.0511
94	-0.0752	-0.0788	-0.0325
95	-0.0284	0.0072	0.0563
96	-0.0865	-0.0878	-0.0403
97	-0.0206	-0.0415	-0.0530
98	0.0236	0.0499	-0.0476
99	0.0309	0.0486	0.0444
100	-0.0352	-0.1167	-0.0508
101	-0.0472	-0.1046	-0.0425
102	-0.0214	0.0112	-0.0503
103	-0.0419	-0.1056	-0.0744
104	-0.0248	-0.0628	0.0228
105	-0.0342	-0.0652	0.0642
106	0.0179	0.0008	0.0935
107	0.0313	0.0170	0.0992
108	-0.0489	-0.0394	-0.0335
109	0.0888	0.0746	0.0976
110	-0.0243	-0.0209	-0.0146
111	0.0465	0.1051	0.0807
112	-0.0112	-0.0193	0.0089
113	-0.0224	-0.0156	0.0119
114	0.0796	0.0384	0.0412
115	-0.0571	-0.0505	-0.0319
116	-0.0196	-0.0259	-0.0808
117	-0.0354	-0.0783	-0.0735
118	-0.0165	-0.0518	-0.0396
119	0.1080	0.2102	0.1157
120	-0.0106	-0.0352	-0.0468
121	0.0073	0.0694	0.1346
122	0.0578	0.0350	0.1277
123	0.0432	0.0063	0.0270
124	0.0320	0.0373	0.0742
125	0.0294	0.0193	-0.0240
126	0.0547	0.1735	-0.0544
127	-0.0042	0.0054	-0.0388
128	0.0663	-0.0045	0.0346
129	0.0205	0.0434	-0.0345
130	0.0179	-0.0117	0.0132
131	0.0277	-0.0101	-0.0394
132	-0.0943	-0.0654	-0.0477
133	-0.1169	-0.0825	-0.0445
134	0.0950	0.1240	0.1037
135	0.0909	0.0857	0.0804
136	-0.1107	-0.0809	-0.0482
137	0.0299	-0.0057	0.0721
138	0.0683	0.0520	0.0935
139	-0.0625	-0.0077	-0.0461
140	0.0028	0.0505	0.0249
141	-0.0779	-0.0576	-0.0446
142	-0.0543	-0.0644	-0.0389
143	0.0102	0.0314	0.0942
144	-0.0023	0.0185	0.1373
145	-0.0489	-0.0332	-0.0158
146	0.0728	0.0641	-0.0053
147	0.0868	0.0631	0.0853
148	-0.0789	-0.0594	-0.0497
149	0.0308	0.0180	0.0319
150	-0.0502	0.0505	0.0179
151	0.2037	0.1640	0.3110
152	-0.0930	-0.0873	-0.0499
153	0.0383	0.1135	0.0898
154	0.0482	0.0604	0.1166
155	0.0506	0.0410	0.1113
156	-0.0063	0.0068	-0.0255
157	0.0287	0.0327	0.0014
158	-0.0820	-0.0930	-0.0561
159	0.0591	0.0894	0.1351
160	0.0769	0.0581	0.0298
161	-0.0813	-0.0583	-0.0323
162	0.0326	0.0946	0.0723
163	-0.0086	-0.0309	0.0279
164	-0.0038	-0.0053	-0.0396
165	-0.0523	-0.0615	-0.0479
166	-0.1579	-0.1041	-0.0524
167	0.0632	0.0347	0.1149
168	0.0331	0.0562	0.0145
169	0.1285	0.0804	0.0505
170	0.0006	-0.0439	0.0297
171	-0.0820	-0.0704	-0.0396
172	0.1087	0.1535	0.1432
173	-0.0711	-0.0557	-0.0528
174	-0.0991	-0.1004	-0.0462
175	-0.0571	-0.0402	-0.0228
176	0.0526	0.0699	-0.0341
177	0.0042	-0.0491	0.0155
178	0.0140	0.0269	-0.0161
179	-0.0109	-0.0342	0.0028
180	0.1613	0.1545	0.1247
181	0.0306	-0.0131	-0.0398
182	-0.0537	-0.0502	-0.0257
183	0.0045	-0.0457	-0.0040
184	-0.0465	-0.0139	-0.0457
185	0.1305	0.0389	0.0091
186	-0.0448	-0.0610	0.0488
187	-0.0154	-0.0068	-0.0512
188	0.0337	-0.0151	-0.0423
189	0.0806	0.0148	0.0595
190	-0.0273	-0.0114	0.0093
191	0.0275	0.0478	0.0249
192	-0.0306	-0.0250	-0.0011
193	-0.0384	-0.0230	-0.0474
194	-0.1442	-0.1062	-0.0584
195	0.0345	0.0515	-0.0409
196	0.0207	0.0272	-0.0437
197	0.0646	0.0168	-0.0630
198	0.0029	-0.0284	0.0105
199	0.0485	0.1298	0.0481
200	-0.0218	-0.0757	-0.0520
201	0.0170	0.0436	0.0671
202	-0.1346	-0.1472	-0.0936
203	-0.0155	0.0197	-0.0399
204	0.1914	0.2092	0.1648
205	-0.0475	-0.0909	-0.0783
206	-0.0550	-0.0357	-0.0464
207	-0.0636	-0.0187	-0.0498
208	-0.0595	-0.0683	-0.0467
209	0.0349	0.0230	0.0180
210	0.0574	-0.0293	-0.0264
211	-0.0420	-0.0618	-0.0346
212	0.0519	0.0185	0.0312
213	0.0923	0.0342	0.0770
214	-0.0783	0.0238	-0.0567
215	0.0120	-0.0112	-0.0201
216	-0.0294	-0.0063	0.0044
217	0.0513	0.0434	-0.0360
218	-0.0796	-0.0930	-0.0522
219	-0.0581	-0.0515	-0.0586
220	0.0540	0.0381	0.1262
221	-0.0019	-0.0794	-0.0391
222	0.0055	-0.0478	0.0716
223	-0.0574	-0.0752	-0.0361
224	0.0248	0.0177	0.0932
225	0.0068	-0.0016	-0.0374
226	0.0687	0.0052	0.0089
227	0.0868	0.0957	0.0705
228	-0.0537	-0.0046	-0.0729
229	0.0109	0.0604	-0.0490
230	-0.0461	-0.0373	-0.0458
231	0.0060	-0.0115	-0.0072
232	-0.1066	-0.1104	-0.0618
233	0.0296	-0.0044	0.0020
234	-0.0721	-0.0229	-0.0382
235	-0.1278	-0.0158	-0.0370
236	-0.0156	-0.0129	0.0071
237	-0.0454	-0.0091	-0.0459
238	0.0543	-0.0049	-0.0494
239	-0.0451	-0.0704	-0.0465
240	-0.0660	-0.0604	-0.0459
241	0.0321	-0.0271	-0.0356
242	-0.1326	-0.1346	-0.0663
243	-0.0472	0.0234	-0.0561
244	0.0701	0.0794	0.0129
245	-0.0220	-0.0452	-0.0428
246	-0.0001	-0.0694	-0.0364
247	-0.0340	-0.0470	-0.0379
248	0.0006	-0.0276	-0.0515
249	0.0191	0.0148	0.0446

Source: M2_RECENT_DPO_LORA_SPEAKER_EMOTION_STUDY_2026-10-02.html · SHA-256 51c90e04b8d0c373…

g02GermanDPO acting study

HVSAC-014 · de · targets: Anger, Sadness, Affection

Generated TTS prediction · Rank 64 × 1.00 · C01 · 17.1 s

Du darfst mir das nicht auch noch nehmen! Ich habe den ganzen Tag versucht, ruhig zu bleiben, doch die Wellen sind lauter als meine Ausreden... ich bin wütend, ich bin verzweifelt, und ich liebe dich noch immer. Dann soll das Meer es eben hören.

Tiny Base · values are model estimates, not ground truth

Strongest emotions relative to training

Fatigue Exhaustion

z +3.63 / +3.31raw 1.98 / 1.81

Sadness

z +2.61 / +2.31raw 1.98 / 1.75

Disappointment

z +2.56 / +2.59raw 1.79 / 1.82

Bitterness

z +2.42 / +2.49raw 1.02 / 1.05

Longing

z +2.38 / +2.05raw 1.59 / 1.38

Shame

z +2.23 / +1.83raw 1.15 / 0.95

Helplessness

z +2.13 / +1.96raw 1.48 / 1.36

The center of each bar is the S9 teacher median. Positive z is to the right; negative z is to the left. Ranking uses z, not raw teacher units.

Strongest VoiceNet dimensions relative to training

Tension (TENS)

z +1.52 / +1.68raw 2.86 / 2.99

Ranting or angry style (S_RANT)

z +1.26 / +1.32raw 2.84 / 2.91

Perceived voice age (AGEV)

z +1.22 / +1.03raw 4.49 / 4.26

Chest resonance (R_CHST)

z +1.21 / +1.19raw 3.16 / 3.14

Narrator style (S_NARR)

z +0.98 / +1.05raw 2.73 / 2.83

Cartoonish style (S_CART)

z +0.70 / +0.98raw 2.55 / 2.94

Storytelling style (S_STRY)

z +0.66 / +0.98raw 3.39 / 3.82

All 57 VoiceNet predictions, including raw units, are in the full table below. These seven are ranked by z; the top values may differ from the strongest raw dimensions.

Voice, speed and quality scores in context

Genuineness (0–6)z -0.64 / -0.60raw 1.29 / 1.36

Vocal-burst blend (0–10)z -2.04 / -2.00raw 1.10 / 1.19

Content enjoyment (CE)z +0.40 / +0.58raw 5.21 / 5.39

Production quality (PQ)z +0.80 / +0.80raw 7.75 / 7.74

Speech signal quality, calibratedz +0.30 / +0.29raw 3.64 / 3.63

Background quality, calibratedz +0.73 / +0.63raw 4.06 / 3.98

Overall quality, calibratedz +0.82 / +0.76raw 3.34 / 3.30

P.808 MOS estimatez +1.14 / +0.98raw 3.99 / 3.91

score content enjoymentz +1.09 / +1.12raw 4.84 / 4.85

score overall qualityz +0.95 / +0.68raw 3.13 / 2.99

Background Noisez -1.25 / -0.61raw 0.48 / 0.65

Tempo (TEMP)z -1.20 / -0.80raw 0.69 / 1.16

Arousal (AROU)z -0.54 / -0.14raw 1.74 / 2.20

Valence (VALN)z -0.50 / -0.38raw 1.76 / 1.90

Recording quality (RCQL)z -0.64 / -0.58raw 2.18 / 2.23

Background noise (BKGN)z -0.03 / +0.12raw 2.68 / 2.79

talking speedz +0.27 / -0.37raw 10.05 / 7.63

Characters per second (CPS): 14.36 raw · z +1.42

Orange speaker embedding reconstruction

Cosine against Orange on this same clip (higher means closer to that teacher vector):

Embedding	Tiny	Base
Timbre · 128D	0.843	0.857
Identity · 250D	0.791	0.780

Vocal-burst regions

Tiny

Base

0 s17.1 s

Verified burst intervals are unavailable for this clip.

Tiny: 1 regions, count-head estimate 0.98; Base: 1 regions, count-head estimate 0.88.

Exact predicted start and end times

Model	Region	Start (s)	End (s)	Duration (s)
Tiny	1	2.72	3.38	0.66
Base	1	2.72	3.38	0.66

All 192 score slots · raw and z values

#	Target	Tiny raw	Tiny z	Base raw	Base z	Train median	Train SD
Emotion scores Forty clip-level Empathic Insight emotion teacher outputs. Each row evaluates one named emotion score.
0	Affectionemo_Affection	0.760	+1.32	0.685	+1.19	0.007	0.570
1	Amusementemo_Amusement	0.251	+0.28	0.357	+0.40	-0.001	0.885
2	Angeremo_Anger	0.793	+1.29	1.004	+1.63	0.004	0.613
3	Astonishment Surpriseemo_Astonishment_Surprise	-0.007	-0.02	-0.016	-0.04	0.005	0.572
4	Aweemo_Awe	-0.001	-0.00	-0.020	-0.05	0.000	0.427
5	Bitternessemo_Bitterness	1.021	+2.42	1.046	+2.49	0.013	0.415
6	Concentrationemo_Concentration	0.378	-0.35	0.262	-0.50	0.634	0.741
7	Confusionemo_Confusion	0.707	+1.31	0.482	+0.89	0.001	0.540
8	Contemplationemo_Contemplation	0.913	+1.39	0.745	+1.11	0.082	0.598
9	Contemptemo_Contempt	0.085	+0.18	0.300	+0.65	-0.000	0.464
10	Contentmentemo_Contentment	0.010	+0.02	0.045	+0.09	0.000	0.514
11	Disappointmentemo_Disappointment	1.788	+2.56	1.816	+2.59	0.000	0.700
12	Disgustemo_Disgust	0.192	+0.38	0.416	+0.84	0.007	0.489
13	Distressemo_Distress	1.621	+1.97	1.532	+1.86	0.000	0.821
14	Doubtemo_Doubt	0.504	+1.07	0.487	+1.03	0.006	0.466
15	Elationemo_Elation	-0.104	-0.16	-0.034	-0.06	0.012	0.728
16	Embarrassmentemo_Embarrassment	0.555	+1.19	0.628	+1.36	0.043	0.430
17	Emotional Numbnessemo_Emotional_Numbness	0.819	+0.89	0.532	+0.58	0.004	0.917
18	Fatigue Exhaustionemo_Fatigue_Exhaustion	1.981	+3.63	1.812	+3.31	0.028	0.539
19	Fearemo_Fear	0.258	+0.40	0.054	+0.06	0.015	0.610
20	Helplessnessemo_Helplessness	1.476	+2.13	1.360	+1.96	-0.004	0.696
21	Hope Enthusiasm Optimismemo_Hope_Enthusiasm_Optimism	0.009	-0.14	0.083	-0.05	0.117	0.760
22	Impatience and Irritabilityemo_Impatience_and_Irritability	1.220	+1.52	1.599	+2.06	0.149	0.705
23	Infatuationemo_Infatuation	0.552	+1.06	0.253	+0.50	-0.015	0.533
24	Interestemo_Interest	1.135	-0.50	0.999	-0.65	1.589	0.907
25	Intoxication Altered States of Consciousnessemo_Intoxication_Altered_States_of_Consciousness	0.616	+1.15	0.477	+0.90	-0.025	0.559
26	Jealousy and Envyemo_Jealousy_and_Envy	0.342	+0.64	0.294	+0.53	0.059	0.442
27	Longingemo_Longing	1.593	+2.38	1.384	+2.05	0.087	0.632
28	Malevolence Maliceemo_Malevolence_Malice	0.162	+0.20	0.306	+0.47	0.055	0.534
29	Painemo_Pain	0.745	+1.29	0.659	+1.14	-0.002	0.579
30	Pleasure Ecstasyemo_Pleasure_Ecstasy	0.020	+0.01	0.006	-0.02	0.017	0.614
31	Prideemo_Pride	0.005	+0.01	-0.019	-0.04	0.002	0.509
32	Reliefemo_Relief	0.405	+0.55	0.587	+0.81	0.033	0.681
33	Sadnessemo_Sadness	1.981	+2.61	1.755	+2.31	0.000	0.759
34	Sexual Lustemo_Sexual_Lust	0.172	+0.29	0.118	+0.18	0.030	0.494
35	Shameemo_Shame	1.149	+2.23	0.948	+1.83	0.013	0.510
36	Sournessemo_Sourness	0.543	+1.25	0.796	+1.82	-0.005	0.439
37	Teasingemo_Teasing	0.665	+1.22	1.153	+2.11	0.000	0.545
38	Thankfulness Gratitudeemo_Thankfulness_Gratitude	0.238	+0.28	0.337	+0.42	0.041	0.697
39	Triumphemo_Triumph	-0.024	-0.03	-0.044	-0.07	-0.007	0.521
VoiceNet dimensions Fifty-seven VoiceNet voice, delivery, style, and recording dimensions. Codes are expanded in the target column.
40	Perceived voice age (AGEV)vn_AGEV_reg	4.493	+1.22	4.256	+1.03	2.984	1.238
41	Arousal (AROU)vn_AROU_reg	1.737	-0.54	2.200	-0.14	2.359	1.147
42	Arousal shift (ARSH)vn_ARSH_reg	1.027	-1.79	1.109	-1.70	2.580	0.867
43	Vocal attack (ATCK)vn_ATCK_reg	2.741	+0.45	2.865	+0.54	2.162	1.295
44	Background noise (BKGN)vn_BKGN_reg	2.679	-0.03	2.792	+0.12	2.703	0.761
45	Brightness (BRGT)vn_BRGT_reg	1.606	-0.47	1.723	-0.33	1.991	0.813
46	Speech chunking (CHNK)vn_CHNK_reg	0.981	-0.70	1.113	-0.59	1.847	1.239
47	Articulation clarity (CLRT)vn_CLRT_reg	1.960	-0.06	2.001	-0.02	2.018	0.945
48	Cognitive load (COGL)vn_COGL_reg	2.433	+0.32	2.406	+0.29	2.094	1.061
49	Dynamic arc (DARC)vn_DARC_reg	1.232	-0.28	1.625	+0.01	1.615	1.380
50	Disfluency (DFLU)vn_DFLU_reg	3.253	+0.65	3.258	+0.65	2.488	1.184
51	Emphasis (EMPH)vn_EMPH_reg	3.025	+0.27	3.595	+0.65	2.607	1.524
52	Esthetics (ESTH)vn_ESTH_reg	1.799	-0.77	2.124	-0.36	2.402	0.782
53	Content appropriateness (EXPL)vn_EXPL_reg	-0.079	-0.51	0.098	+0.04	0.086	0.322
54	Focus (FOCS)vn_FOCS_reg	1.452	-0.81	1.578	-0.70	2.344	1.102
55	Fullness (FULL)vn_FULL_reg	1.174	-0.68	1.488	-0.33	1.778	0.889
56	Perceived gender (GEND)vn_GEND_reg	5.424	+0.86	5.424	+0.86	4.055	1.588
57	Harmonicity (HARM)vn_HARM_reg	2.202	-0.33	2.093	-0.46	2.480	0.836
58	Metallic character (METL)vn_METL_reg	1.998	+0.39	1.994	+0.39	1.621	0.958
59	Pitch range (RANG)vn_RANG_reg	3.490	+0.64	3.665	+0.84	2.914	0.897
60	Recording quality (RCQL)vn_RCQL_reg	2.182	-0.64	2.235	-0.58	2.754	0.888
61	Vocal register (REGS)vn_REGS_reg	-0.226	-1.12	-0.079	-1.01	1.198	1.268
62	Respiration (RESP)vn_RESP_reg	2.312	-0.35	2.639	-0.04	2.680	1.056
63	Roughness (ROUG)vn_ROUG_reg	1.897	-0.15	2.157	+0.14	2.033	0.887
64	Chest resonance (R_CHST)vn_R_CHST_reg	3.156	+1.21	3.136	+1.19	2.135	0.844
65	Head resonance (R_HEAD)vn_R_HEAD_reg	1.500	-0.79	1.606	-0.66	2.148	0.822
66	Mask resonance (R_MASK)vn_R_MASK_reg	1.542	-0.36	1.653	-0.25	1.908	1.005
67	Mixed resonance (R_MIXD)vn_R_MIXD_reg	0.778	-0.78	1.208	-0.27	1.436	0.841
68	Nasal resonance (R_NASL)vn_R_NASL_reg	3.110	+0.30	3.431	+0.61	2.791	1.047
69	Oral resonance (R_ORAL)vn_R_ORAL_reg	1.803	-0.51	1.767	-0.56	2.184	0.741
70	Throat resonance (R_THRT)vn_R_THRT_reg	2.395	+0.40	2.423	+0.44	2.070	0.803
71	Smoothness (SMTH)vn_SMTH_reg	1.623	-0.48	1.768	-0.34	2.143	1.093
72	Stance (STNC)vn_STNC_reg	2.876	+0.21	3.123	+0.43	2.633	1.137
73	Speech structure (STRU)vn_STRU_reg	2.112	-0.03	2.141	+0.00	2.137	0.958
74	ASMR style (S_ASMR)vn_S_ASMR_reg	0.650	-0.51	0.413	-0.68	1.370	1.411
75	Authoritative style (S_AUTH)vn_S_AUTH_reg	1.455	+0.35	1.337	+0.24	1.088	1.043
76	Cartoonish style (S_CART)vn_S_CART_reg	2.546	+0.70	2.936	+0.98	1.560	1.401
77	Casual style (S_CASU)vn_S_CASU_reg	2.664	-0.88	3.008	-0.61	3.793	1.278
78	Conversational style (S_CONV)vn_S_CONV_reg	1.990	-0.46	2.660	+0.05	2.594	1.318
79	Dramatic style (S_DRAM)vn_S_DRAM_reg	2.978	+0.22	3.442	+0.63	2.721	1.148
80	Formal style (S_FORM)vn_S_FORM_reg	0.958	-0.23	0.753	-0.43	1.195	1.021
81	Monologue style (S_MONO)vn_S_MONO_reg	3.481	+0.51	3.586	+0.59	2.824	1.284
82	Narrator style (S_NARR)vn_S_NARR_reg	2.725	+0.98	2.832	+1.05	1.307	1.446
83	Newsreader style (S_NEWS)vn_S_NEWS_reg	0.718	+0.55	0.492	+0.15	0.408	0.568
84	Playful style (S_PLAY)vn_S_PLAY_reg	2.334	-0.01	2.583	+0.18	2.352	1.315
85	Ranting or angry style (S_RANT)vn_S_RANT_reg	2.840	+1.26	2.910	+1.32	1.213	1.289
86	Storytelling style (S_STRY)vn_S_STRY_reg	3.387	+0.66	3.823	+0.98	2.480	1.366
87	Teacher or didactic style (S_TECH)vn_S_TECH_reg	-0.475	-0.91	-0.366	-0.83	0.646	1.227
88	Whispered talking style (S_WHIS)vn_S_WHIS_reg	2.081	+0.30	2.062	+0.29	1.597	1.618
89	Tempo (TEMP)vn_TEMP_reg	0.689	-1.20	1.163	-0.80	2.117	1.190
90	Tension (TENS)vn_TENS_reg	2.856	+1.52	2.986	+1.68	1.559	0.852
91	Valence (VALN)vn_VALN_reg	1.765	-0.50	1.899	-0.38	2.328	1.118
92	Valence shift (VALS)vn_VALS_reg	0.885	-1.51	1.065	-1.35	2.518	1.079
93	Velocity flux (VFLX)vn_VFLX_reg	-1.196	-2.86	-1.121	-2.79	2.256	1.208
94	Volatility (VOLT)vn_VOLT_reg	2.523	-0.07	2.874	+0.33	2.586	0.886
95	Vulnerability (VULN)vn_VULN_reg	2.609	-0.04	2.847	+0.20	2.648	0.984
96	Warmth (WARM)vn_WARM_reg	2.393	-0.20	2.547	-0.03	2.578	0.909
Genuineness, blend, and legacy quality Genuineness and vocal-burst blend are predicted. R_quality has Ladder training labels but no valid P3 test labels.
97	Genuineness (0–6)genuineness_0_6	1.294	-0.64	1.363	-0.60	2.332	1.621
98	Vocal-burst blend (0–10)blend_0_10	1.102	-2.04	1.187	-2.00	6.676	2.738
99	Legacy R_quality (no P3 test labels)R_quality	0.340	-2.24	0.355	-2.19	1.095	0.338
Empathic Insight Plus extra scores Nineteen additional clip-level teacher scores, including background noise and content enjoyment.
100	Ageeiv_extra:Age	3.376	+0.43	3.170	-0.27	3.250	0.293
101	Arousaleiv_extra:Arousal	1.460	+0.39	1.690	+0.92	1.289	0.435
102	Authenticityeiv_extra:Authenticity	2.927	+1.70	2.878	+1.38	2.667	0.153
103	Background Noiseeiv_extra:Background_Noise	0.476	-1.25	0.645	-0.61	0.808	0.264
104	Confident vs. Hesitanteiv_extra:Confident_vs._Hesitant	1.423	+1.27	1.439	+1.32	1.040	0.303
105	Gendereiv_extra:Gender	-0.685	-0.06	-0.604	+0.02	-0.621	0.999
106	High-Pitched vs. Low-Pitchedeiv_extra:High-Pitched_vs._Low-Pitched	1.861	+0.13	1.889	+0.25	1.827	0.250
107	Monotone vs. Expressiveeiv_extra:Monotone_vs._Expressive	1.948	+0.19	2.157	+0.63	1.859	0.470
108	Recording Qualityeiv_extra:Recording_Quality	2.188	+0.13	2.119	-0.08	2.144	0.332
109	Serious vs. Humorouseiv_extra:Serious_vs._Humorous	0.934	+0.01	1.109	+0.53	0.929	0.340
110	Soft vs. Harsheiv_extra:Soft_vs._Harsh	0.324	+0.14	0.417	+0.43	0.281	0.320
111	Submissive vs. Dominanteiv_extra:Submissive_vs._Dominant	0.606	+0.71	0.434	+0.18	0.376	0.324
112	Valenceeiv_extra:Valence	-0.606	-1.61	-0.668	-1.77	0.005	0.380
113	Vulnerable vs. Emotionally Detachedeiv_extra:Vulnerable_vs._Emotionally_Detached	1.304	-0.94	1.211	-1.15	1.715	0.437
114	Warm vs. Coldeiv_extra:Warm_vs._Cold	-0.184	-0.78	-0.106	-0.52	0.051	0.300
115	score background qualityeiv_extra:score_background_quality	3.716	+0.60	3.654	+0.51	3.301	0.693
116	score content enjoymenteiv_extra:score_content_enjoyment	4.838	+1.09	4.847	+1.12	4.507	0.303
117	score overall qualityeiv_extra:score_overall_quality	3.131	+0.95	2.994	+0.68	2.652	0.507
118	score speech qualityeiv_extra:score_speech_quality	1.912	+0.72	1.876	+0.47	1.808	0.146
Meta AudioBox Aesthetics Four AudioBox aesthetic teacher outputs. Expansions follow the official Meta model card.
119	Content enjoyment (CE)audiobox:CE	5.208	+0.40	5.391	+0.58	4.799	1.018
120	Content usefulness (CU)audiobox:CU	6.335	+0.69	6.077	+0.43	5.649	1.001
121	Production complexity (PC)audiobox:PC	1.707	-0.39	1.915	-0.26	2.331	1.617
122	Production quality (PQ)audiobox:PQ	7.751	+0.80	7.744	+0.80	7.044	0.879
Microsoft DNSMOS Seven DNSMOS teacher outputs: raw and calibrated SIG/BAK/OVRL estimates plus P.808 MOS.
123	Speech signal quality, rawdnsmos:SIG_raw	4.163	+0.39	4.137	+0.35	3.900	0.669
124	Background quality, rawdnsmos:BAK_raw	4.307	+0.98	4.245	+0.92	3.211	1.124
125	Overall quality, rawdnsmos:OVRL_raw	3.865	+0.96	3.808	+0.89	3.085	0.812
126	Speech signal quality, calibrateddnsmos:SIG	3.640	+0.30	3.632	+0.29	3.488	0.501
127	Background quality, calibrateddnsmos:BAK	4.064	+0.73	3.977	+0.63	3.389	0.928
128	Overall quality, calibrateddnsmos:OVRL	3.340	+0.82	3.300	+0.76	2.840	0.606
129	P.808 MOS estimatednsmos:P808_MOS	3.989	+1.14	3.907	+0.98	3.421	0.496
Vocal-burst count The regression target is log(1 + count). A separate table also reports count error after inverse transformation.
130	Vocal-burst count, log(1 + count)burst_count_log1p	0.683	+1.05	0.630	+0.97	0.000	0.647
VoiceCLAP attributes Sixty-one individual VoiceCLAP attribute teacher scores. The raw 768D VoiceCLAP embedding is stored in sidecars but is not a model output.
131	Affectionvoiceclap_attribute:Affection	0.227	-1.30	0.379	-1.03	0.947	0.554
132	Agevoiceclap_attribute:Age	3.391	+0.30	3.306	+0.14	3.229	0.547
133	Amusementvoiceclap_attribute:Amusement	0.276	-0.20	0.357	-0.06	0.392	0.572
134	Angervoiceclap_attribute:Anger	1.620	+1.24	1.623	+1.25	0.992	0.506
135	Arousalvoiceclap_attribute:Arousal	1.578	+0.25	1.725	+0.49	1.420	0.622
136	Astonishment Surprisevoiceclap_attribute:Astonishment_Surprise	0.446	-0.13	0.734	+0.47	0.509	0.479
137	Authenticityvoiceclap_attribute:Authenticity	2.865	+0.57	2.815	+0.27	2.770	0.167
138	Awevoiceclap_attribute:Awe	0.168	-1.43	0.257	-1.09	0.539	0.259
139	Background Noisevoiceclap_attribute:Background_Noise	0.431	-0.52	0.599	+0.12	0.567	0.264
140	Bitternessvoiceclap_attribute:Bitterness	0.952	+1.52	0.934	+1.45	0.592	0.236
141	Concentrationvoiceclap_attribute:Concentration	0.993	-0.42	0.981	-0.44	1.214	0.531
142	Confident vs. Hesitantvoiceclap_attribute:Confident_vs._Hesitant	1.331	+0.56	1.562	+1.05	1.069	0.468
143	Confusionvoiceclap_attribute:Confusion	1.040	+1.19	1.114	+1.41	0.643	0.334
144	Contemplationvoiceclap_attribute:Contemplation	1.084	+0.75	0.974	+0.48	0.780	0.406
145	Contemptvoiceclap_attribute:Contempt	0.876	+0.49	0.850	+0.42	0.709	0.339
146	Contentmentvoiceclap_attribute:Contentment	0.206	-1.25	0.295	-0.96	0.588	0.307
147	Disappointmentvoiceclap_attribute:Disappointment	1.469	+2.43	1.419	+2.26	0.760	0.291
148	Disgustvoiceclap_attribute:Disgust	0.742	+0.57	0.799	+0.84	0.625	0.207
149	Distressvoiceclap_attribute:Distress	1.345	+1.19	1.278	+1.00	0.927	0.350
150	Doubtvoiceclap_attribute:Doubt	0.873	+1.80	0.844	+1.64	0.535	0.188
151	Elationvoiceclap_attribute:Elation	0.263	-0.70	0.248	-0.73	0.539	0.397
152	Embarrassmentvoiceclap_attribute:Embarrassment	0.447	+0.44	0.503	+0.62	0.307	0.314
153	Emotional Numbnessvoiceclap_attribute:Emotional_Numbness	0.852	+0.71	0.681	+0.06	0.664	0.266
154	Fatigue Exhaustionvoiceclap_attribute:Fatigue_Exhaustion	1.220	+2.90	1.033	+2.19	0.462	0.261
155	Fearvoiceclap_attribute:Fear	0.854	+1.11	0.853	+1.11	0.618	0.212
156	Gendervoiceclap_attribute:Gender	-0.653	-0.50	-0.579	-0.43	-0.151	1.005
157	Helplessnessvoiceclap_attribute:Helplessness	1.131	+1.76	1.084	+1.59	0.658	0.268
158	High-Pitched vs. Low-Pitchedvoiceclap_attribute:High-Pitched_vs._Low-Pitched	2.104	+0.70	2.047	+0.55	1.840	0.375
159	Hope Enthusiasm Optimismvoiceclap_attribute:Hope_Enthusiasm_Optimism	0.336	-0.93	0.315	-0.99	0.705	0.396
160	Impatience and Irritabilityvoiceclap_attribute:Impatience_and_Irritability	1.849	+1.47	1.857	+1.49	1.052	0.541
161	Infatuationvoiceclap_attribute:Infatuation	0.421	-0.56	0.459	-0.45	0.608	0.332
162	Interestvoiceclap_attribute:Interest	0.672	-2.11	1.077	-1.18	1.598	0.440
163	Intoxication Altered States of Consciousnessvoiceclap_attribute:Intoxication_Altered_States_of_Consciousness	0.959	+0.99	0.898	+0.85	0.502	0.463
164	Jealousy & Envyvoiceclap_attribute:Jealousy_&_Envy	0.721	+0.81	0.750	+0.93	0.523	0.245
165	Longingvoiceclap_attribute:Longing	0.741	+0.92	0.657	+0.54	0.538	0.220
166	Malevolence Malicevoiceclap_attribute:Malevolence_Malice	0.839	+0.02	0.905	+0.21	0.833	0.346
167	Monotone vs. Expressivevoiceclap_attribute:Monotone_vs._Expressive	1.776	+0.00	1.935	+0.27	1.775	0.594
168	Painvoiceclap_attribute:Pain	0.697	+1.44	0.761	+1.74	0.381	0.218
169	Pleasure Ecstasyvoiceclap_attribute:Pleasure_Ecstasy	0.273	-0.77	0.395	-0.36	0.503	0.301
170	Pridevoiceclap_attribute:Pride	1.172	+1.12	1.069	+0.83	0.780	0.349
171	Recording Qualityvoiceclap_attribute:Recording_Quality	2.157	-0.48	2.000	-0.96	2.313	0.328
172	Reliefvoiceclap_attribute:Relief	1.099	+0.18	1.333	+0.74	1.025	0.415
173	Sadnessvoiceclap_attribute:Sadness	1.244	+1.57	1.057	+0.98	0.752	0.313
174	Serious vs. Humorousvoiceclap_attribute:Serious_vs._Humorous	0.659	-0.25	0.674	-0.23	0.803	0.568
175	Sexual Lustvoiceclap_attribute:Sexual_Lust	0.190	-1.06	0.193	-1.06	0.635	0.419
176	Shamevoiceclap_attribute:Shame	1.037	+1.80	0.925	+1.41	0.526	0.283
177	Soft vs. Harshvoiceclap_attribute:Soft_vs._Harsh	-0.034	-0.54	0.060	-0.28	0.160	0.360
178	Sournessvoiceclap_attribute:Sourness	1.075	+1.27	1.152	+1.54	0.706	0.291
179	Submissive vs. Dominantvoiceclap_attribute:Submissive_vs._Dominant	0.854	+0.64	0.711	+0.25	0.623	0.359
180	Teasingvoiceclap_attribute:Teasing	0.817	+0.73	1.008	+1.23	0.540	0.379
181	Thankfulness Gratitudevoiceclap_attribute:Thankfulness_Gratitude	0.868	-0.97	0.916	-0.88	1.384	0.529
182	Triumphvoiceclap_attribute:Triumph	0.890	+0.48	0.867	+0.42	0.716	0.359
183	Valencevoiceclap_attribute:Valence	-1.344	-2.11	-1.314	-2.06	-0.007	0.635
184	Vulnerable vs. Emotionally Detachedvoiceclap_attribute:Vulnerable_vs._Emotionally_Detached	1.432	-0.37	1.201	-0.79	1.638	0.556
185	Warm vs. Coldvoiceclap_attribute:Warm_vs._Cold	-0.562	-1.24	-0.737	-1.68	-0.066	0.400
186	durationvoiceclap_attribute:duration	16.014	+0.80	18.563	+1.20	10.914	6.354
187	score background qualityvoiceclap_attribute:score_background_quality	3.729	+0.97	3.869	+1.25	3.245	0.498
188	score content enjoymentvoiceclap_attribute:score_content_enjoyment	4.811	+1.05	4.818	+1.10	4.656	0.147
189	score overall qualityvoiceclap_attribute:score_overall_quality	3.068	+1.05	3.164	+1.28	2.635	0.412
190	score speech qualityvoiceclap_attribute:score_speech_quality	1.938	+0.68	1.911	+0.29	1.891	0.069
191	talking speedvoiceclap_attribute:talking_speed	10.053	+0.27	7.627	-0.37	9.028	3.756

All Orange embedding components

The cosine above is the meaningful vector-level comparison; component values have no standalone semantic label.

Timbre — all 128 vector components

Dimension	Tiny	Base	Orange teacher
0	0.0831	0.0385	0.0136
1	-0.0389	-0.0069	-0.0754
2	-0.0237	-0.0492	-0.0744
3	-0.1192	-0.1376	-0.0769
4	0.1410	0.1397	0.0614
5	0.0892	0.1369	0.1392
6	0.1305	0.1953	0.1639
7	-0.0326	-0.0269	-0.0695
8	0.0073	-0.0075	-0.0510
9	-0.0461	-0.1034	-0.1142
10	0.0788	0.1005	0.0439
11	-0.0692	-0.0250	-0.0510
12	-0.0174	0.0346	0.0361
13	-0.0640	-0.0663	-0.0219
14	0.0119	-0.0495	-0.0790
15	-0.0849	-0.0809	-0.0680
16	-0.0339	0.0050	-0.0228
17	-0.0300	-0.0485	-0.0789
18	0.0413	0.0773	0.0827
19	-0.0205	-0.0144	-0.0669
20	-0.0193	-0.0085	0.0935
21	-0.0049	0.0681	-0.0002
22	-0.0335	-0.0305	-0.0228
23	-0.0045	-0.0040	-0.0443
24	-0.0648	-0.0667	-0.0612
25	-0.0775	-0.0816	-0.0667
26	0.0084	0.0125	-0.0712
27	-0.0762	-0.0506	-0.0707
28	-0.0849	-0.0788	-0.0836
29	0.0129	0.0118	-0.0812
30	0.1862	0.1461	0.1342
31	0.1175	0.1126	0.1227
32	0.0696	0.0228	0.0162
33	0.0246	0.0577	-0.0836
34	-0.0148	0.0004	0.0368
35	0.0574	0.0927	0.1516
36	-0.0322	-0.0405	0.0242
37	0.1332	0.1911	0.1985
38	-0.1201	-0.1262	-0.0757
39	-0.0605	-0.0745	-0.0765
40	-0.1044	-0.1119	-0.0732
41	-0.0065	-0.0517	-0.0961
42	-0.0090	-0.0499	-0.0280
43	-0.0988	-0.0912	-0.0781
44	-0.0298	-0.0143	-0.0165
45	0.0285	-0.0189	-0.1020
46	0.0128	-0.0285	-0.0459
47	-0.1140	-0.0984	-0.0767
48	0.0313	0.0510	0.0377
49	-0.0762	-0.0720	-0.0688
50	0.2054	0.2923	0.2622
51	0.0302	-0.0113	0.0840
52	-0.0648	-0.0510	-0.0393
53	-0.0936	-0.0838	-0.0773
54	0.0627	0.0777	0.1101
55	-0.0596	-0.0244	-0.0368
56	0.0896	0.0863	0.0864
57	-0.0683	-0.0372	-0.0745
58	-0.1210	-0.1283	-0.0808
59	0.0348	0.0517	0.0561
60	0.0657	0.0444	0.1104
61	-0.0796	-0.0592	-0.0699
62	-0.0779	-0.1133	-0.0709
63	-0.0044	-0.0216	-0.0575
64	0.0516	0.0485	0.0003
65	-0.0783	-0.0699	-0.0619
66	0.0359	0.0331	-0.0715
67	0.0997	0.1076	0.1566
68	0.0281	0.0081	-0.0802
69	-0.0444	-0.0524	-0.0695
70	-0.1053	-0.0998	-0.0786
71	0.0740	0.0791	0.0314
72	-0.0322	-0.0841	-0.0734
73	0.0169	0.0927	-0.0015
74	-0.0923	-0.1041	-0.0829
75	0.0233	0.0741	-0.0714
76	0.1532	0.1240	0.1016
77	0.1375	0.1233	0.1556
78	0.0783	0.0285	0.0999
79	-0.0722	-0.0777	-0.0658
80	0.0801	0.0617	0.0833
81	0.1279	0.0927	0.0700
82	0.1419	0.1248	0.1306
83	-0.0161	-0.0435	-0.0597
84	-0.1358	-0.1084	-0.0941
85	-0.0047	0.0770	0.1128
86	-0.0261	-0.0237	-0.0879
87	-0.0468	-0.0428	-0.0767
88	0.0079	-0.0039	0.0593
89	0.0570	0.0531	0.0353
90	0.0011	-0.0659	-0.0434
91	0.1593	0.2181	0.1021
92	-0.1297	-0.1183	-0.0737
93	-0.0190	-0.0032	-0.0072
94	0.0092	0.0446	0.0452
95	0.0385	0.0166	0.1127
96	-0.0135	0.0098	-0.0386
97	0.0289	-0.0342	0.0269
98	-0.0831	-0.0773	-0.0767
99	0.3655	0.2438	0.2898
100	0.1384	0.1126	0.1153
101	-0.0061	0.0481	-0.0466
102	-0.1506	-0.0542	-0.0812
103	-0.0335	-0.0606	-0.0801
104	-0.0775	-0.0517	-0.0742
105	-0.1262	-0.0773	-0.0732
106	-0.1532	-0.1533	-0.0912
107	0.1532	0.1255	0.0688
108	0.0936	0.0955	0.0872
109	-0.0622	-0.0563	-0.0744
110	0.0901	0.1019	0.0890
111	-0.0479	-0.0681	-0.0880
112	-0.0640	-0.0610	-0.0748
113	-0.0753	-0.0351	-0.0829
114	0.0289	-0.0027	-0.0599
115	-0.0313	-0.0431	-0.0719
116	-0.0487	-0.0941	-0.0650
117	-0.0849	-0.1084	-0.0883
118	-0.0379	-0.0367	-0.0739
119	0.0270	0.0731	-0.0095
120	0.2594	0.2267	0.2325
121	-0.1044	-0.0962	-0.0524
122	-0.1031	-0.0749	-0.0779
123	-0.0313	-0.0962	-0.0876
124	-0.0403	-0.0060	-0.0798
125	-0.0788	-0.0873	-0.0756
126	-0.1040	-0.0977	-0.0654
127	0.0879	0.1019	0.0667

Identity — all 250 vector components

Dimension	Tiny	Base	Orange teacher
0	-0.0677	-0.0851	-0.0443
1	-0.0515	-0.0494	-0.0389
2	-0.1192	-0.0290	-0.0343
3	-0.0430	-0.0814	-0.0764
4	-0.0385	0.0143	-0.0366
5	0.0443	0.0371	0.0656
6	0.0596	0.0652	0.1120
7	0.1177	0.0772	0.1217
8	0.0461	-0.0524	0.0302
9	0.0273	0.0025	-0.0032
10	-0.1076	-0.0298	-0.0291
11	-0.0459	-0.0204	-0.0461
12	0.0801	0.1092	0.1447
13	0.0650	0.1123	0.0652
14	-0.0385	-0.0584	-0.0046
15	0.0933	0.0486	-0.0474
16	0.0685	0.1047	0.0520
17	-0.0286	0.0326	0.1077
18	0.0052	-0.0185	-0.0409
19	0.0157	0.0480	0.0567
20	-0.0165	0.0214	-0.0403
21	-0.0557	-0.0505	-0.0373
22	-0.0250	-0.0516	-0.0417
23	-0.0298	-0.0348	-0.0389
24	-0.0089	0.0187	-0.0305
25	-0.0639	-0.1085	-0.0434
26	0.1749	0.1560	0.1337
27	-0.0565	-0.0350	-0.0327
28	-0.0164	-0.0004	0.0222
29	-0.0397	-0.0482	-0.0387
30	-0.0281	-0.0201	-0.0350
31	-0.0979	-0.0844	-0.0505
32	0.0344	0.0068	0.0047
33	0.0476	0.0569	0.0986
34	0.0813	0.1221	0.0589
35	-0.0331	0.0231	-0.0332
36	0.0319	0.0723	-0.0274
37	-0.0290	-0.0614	-0.0278
38	0.0207	-0.0032	0.0810
39	0.0186	0.0161	0.1051
40	-0.0453	-0.0554	-0.0466
41	-0.0096	-0.0069	0.0515
42	0.0183	0.0230	0.0294
43	0.1068	0.0367	0.0697
44	-0.0492	-0.0135	-0.0385
45	-0.0466	-0.0727	-0.0461
46	-0.0211	-0.0196	-0.0591
47	0.0404	0.0979	0.0998
48	-0.0000	-0.0191	0.0148
49	-0.0492	-0.0087	-0.0309
50	0.0304	0.0350	-0.0307
51	-0.0490	0.0046	-0.0163
52	-0.0774	-0.0667	-0.0397
53	0.0437	0.0561	0.0352
54	-0.0018	-0.0995	0.0625
55	0.0433	0.0678	0.0930
56	-0.0002	-0.0226	-0.0410
57	0.1858	0.1349	0.1589
58	-0.0009	-0.0292	0.0328
59	0.0003	-0.0017	-0.0287
60	0.0168	-0.0433	0.0258
61	-0.0211	-0.0109	-0.0374
62	-0.0507	-0.0114	-0.0037
63	0.0076	-0.0235	-0.0061
64	0.0125	0.0207	-0.0040
65	0.0557	0.0337	0.0889
66	0.0239	0.1055	0.0355
67	0.1417	0.0942	0.1766
68	-0.0201	-0.0173	-0.0433
69	0.0134	-0.0174	-0.0236
70	-0.0116	-0.0118	0.0573
71	0.0002	0.0213	-0.0421
72	0.0185	0.0193	-0.0156
73	0.0468	0.0987	0.0970
74	-0.0523	-0.0501	-0.0434
75	0.1099	0.0633	0.1294
76	0.0677	0.0099	0.0788
77	0.0201	-0.0352	-0.0190
78	0.1223	0.1175	-0.0006
79	0.0104	0.0192	-0.0343
80	-0.0269	0.0183	-0.0427
81	-0.0381	-0.0550	-0.0482
82	-0.0592	-0.0377	-0.0386
83	-0.0635	-0.0201	-0.0357
84	-0.0435	-0.0625	-0.0605
85	-0.0339	-0.0712	-0.0189
86	0.0255	0.0202	0.0145
87	-0.0092	0.0192	0.0212
88	-0.0162	-0.0069	0.0021
89	-0.0370	-0.0806	-0.0388
90	0.0685	0.0949	0.0958
91	0.0561	0.0866	0.0466
92	-0.0455	-0.0591	-0.0371
93	-0.0561	-0.0870	-0.0487
94	-0.0248	-0.0204	-0.0558
95	-0.0219	-0.0155	-0.0448
96	-0.0863	-0.0573	-0.0384
97	-0.0627	-0.0953	-0.0506
98	-0.0232	0.0089	-0.0066
99	-0.0121	-0.0527	-0.0537
100	-0.0065	-0.0160	-0.0202
101	-0.0348	-0.0367	-0.0038
102	-0.0350	-0.0761	-0.0480
103	-0.0490	-0.1062	-0.0139
104	-0.0261	-0.0284	-0.0193
105	-0.0352	-0.0284	-0.0225
106	-0.0466	-0.0339	-0.0331
107	0.0397	0.0435	0.0414
108	0.1084	0.0251	0.0390
109	0.1115	0.0469	0.1041
110	0.0894	0.0390	0.1049
111	0.1231	0.0908	0.1195
112	-0.0090	-0.0056	0.0964
113	0.0197	-0.0065	-0.0268
114	-0.0315	-0.0516	-0.0599
115	-0.0375	-0.0150	-0.0304
116	-0.0325	0.0105	-0.0474
117	-0.1022	-0.0787	-0.0701
118	-0.0094	0.0039	-0.0408
119	-0.0712	-0.0949	-0.0442
120	-0.0685	-0.0535	-0.0547
121	0.0859	0.0961	0.1307
122	-0.0306	-0.0175	0.0160
123	-0.0319	-0.0482	-0.0444
124	-0.0596	-0.0469	-0.0428
125	-0.0171	-0.0294	-0.0417
126	0.1030	0.0505	0.0227
127	-0.0263	-0.0397	-0.0442
128	-0.0490	-0.0761	-0.0453
129	-0.0166	-0.0512	-0.0249
130	-0.0214	-0.0490	-0.0432
131	-0.0673	-0.0652	-0.0376
132	-0.0416	-0.0904	-0.0455
133	-0.0751	-0.0443	-0.0424
134	0.0948	0.1115	0.0859
135	-0.0048	-0.0360	-0.0432
136	-0.0677	-0.0254	-0.0460
137	-0.0898	-0.0471	-0.0399
138	-0.0010	0.0301	0.0784
139	0.0230	-0.0019	-0.0437
140	-0.0573	-0.0795	-0.0506
141	0.1362	0.0644	0.0473
142	-0.0298	-0.0262	-0.0371
143	0.0288	0.1017	0.0609
144	-0.0194	0.0131	0.0560
145	-0.0441	-0.0441	-0.0101
146	0.0321	0.0416	0.0028
147	0.0581	0.0315	0.0153
148	0.0654	0.0505	0.0974
149	0.0189	0.0569	0.0687
150	0.0646	0.0934	0.0055
151	0.1285	0.0979	0.1863
152	0.0210	-0.0204	-0.0476
153	-0.0099	-0.0007	-0.0676
154	0.0805	0.0942	0.0908
155	0.0577	0.0915	0.0113
156	-0.0217	0.0089	-0.0430
157	0.1184	0.0987	0.0790
158	0.0101	-0.0433	-0.0301
159	-0.0304	-0.0303	-0.0503
160	-0.0302	-0.0103	-0.0170
161	-0.0894	-0.0697	-0.0280
162	-0.0708	-0.0439	-0.0498
163	0.0254	0.0558	0.0634
164	0.0404	0.0127	0.0010
165	-0.0171	-0.0671	-0.0592
166	0.0484	0.0791	0.0728
167	0.0426	0.0671	0.0359
168	-0.1061	-0.0648	-0.0607
169	0.0476	0.0746	0.0390
170	-0.0488	-0.0686	-0.0402
171	0.0422	0.0326	-0.0378
172	-0.0542	-0.0048	-0.0093
173	0.0697	0.0094	0.0803
174	-0.0689	-0.0494	-0.0441
175	-0.0542	-0.0384	-0.0411
176	0.1966	0.1499	0.2122
177	-0.0515	-0.0337	-0.0354
178	0.0910	0.1356	0.1599
179	0.0809	0.0893	0.0790
180	0.0681	0.1673	0.1648
181	-0.0809	-0.1040	-0.0612
182	-0.0604	-0.0712	-0.0371
183	-0.0250	-0.0689	-0.0193
184	-0.0220	-0.0097	-0.0436
185	-0.0087	-0.0028	-0.0284
186	0.0813	0.0465	0.0494
187	-0.0786	-0.0294	-0.0489
188	0.0379	-0.0045	0.0318
189	0.0069	0.0855	0.0861
190	0.0925	0.0742	0.1501
191	0.0298	-0.0068	0.0005
192	0.0292	0.0893	0.0772
193	-0.0724	-0.0701	-0.0452
194	0.0511	0.1062	0.0577
195	0.0364	0.0403	0.0275
196	0.1587	0.1748	0.2159
197	-0.0577	-0.0199	-0.0601
198	-0.0387	-0.0135	-0.0415
199	0.0233	0.0313	0.0304
200	-0.0790	-0.1085	-0.0496
201	0.0894	0.0473	0.0030
202	-0.1564	-0.0753	-0.0893
203	0.0890	0.0595	-0.0131
204	0.0852	0.0882	0.1144
205	-0.1301	-0.1529	-0.0747
206	-0.0286	-0.0137	-0.0443
207	-0.0530	-0.0863	-0.0529
208	-0.0503	-0.0591	-0.0445
209	-0.0352	-0.0569	-0.0461
210	0.1316	0.1281	0.0832
211	-0.0250	0.0138	0.0295
212	0.1037	0.0599	0.0808
213	0.2137	0.1740	0.1219
214	0.0991	0.0414	-0.0060
215	0.0279	0.0049	0.0102
216	0.0801	0.1115	0.0733
217	-0.0809	-0.1017	-0.0786
218	-0.1006	-0.0390	-0.0498
219	-0.0263	-0.0478	-0.0381
220	0.0408	0.0021	0.0326
221	0.0422	0.0279	0.1632
222	-0.0341	-0.0168	-0.0499
223	-0.0499	-0.0610	-0.0344
224	0.0001	-0.0224	-0.0392
225	0.0228	0.0022	-0.0150
226	0.0480	0.0309	0.0265
227	-0.0375	-0.0882	-0.0567
228	-0.0581	-0.0046	-0.0236
229	0.1037	0.1492	0.1219
230	-0.0666	-0.0211	-0.0437
231	-0.0218	0.0085	-0.0009
232	0.0213	0.0092	-0.0161
233	-0.0732	-0.0403	-0.0722
234	0.0612	0.0712	0.0298
235	-0.0017	0.0142	-0.0353
236	-0.0414	-0.0335	-0.0369
237	-0.0197	-0.0172	-0.0195
238	0.0312	0.0337	-0.0471
239	-0.0202	-0.0428	-0.0444
240	-0.0542	-0.0114	-0.0438
241	0.0219	-0.0335	0.0669
242	-0.0247	-0.0663	-0.0632
243	0.0053	-0.0159	0.0007
244	-0.0327	0.0058	-0.0456
245	-0.0685	-0.1386	-0.0408
246	-0.0530	-0.0674	-0.0348
247	-0.0565	-0.0772	-0.0361
248	-0.0588	-0.0697	-0.0491
249	-0.0375	-0.0006	-0.0205

Source: M2_RECENT_DPO_LORA_SPEAKER_EMOTION_STUDY_2026-10-02.html · SHA-256 4d40ef1f8b7810a1…

g03EnglishDPO acting study

HVSAC-017 · en · targets: Pain, Fear, Triumph

Generated TTS prediction · Rank 16 × 1.00 · C01 · 16.8 s

My fingers have gone numb, and the station lights keep blinking. I can hear the wind pushing at the door... please tell me the heater is still working. I need to stay awake until the crew gets here.

Tiny Base · values are model estimates, not ground truth

Strongest emotions relative to training

Fatigue Exhaustion

z +3.99 / +3.12raw 2.18 / 1.71

Helplessness

z +3.47 / +3.17raw 2.41 / 2.20

Distress

z +3.33 / +3.06raw 2.73 / 2.52

Fear

z +3.14 / +3.25raw 1.93 / 1.99

Sadness

z +3.08 / +2.71raw 2.33 / 2.06

Disappointment

z +2.81 / +2.65raw 1.97 / 1.85

Shame

z +2.47 / +1.84raw 1.28 / 0.95

The center of each bar is the S9 teacher median. Positive z is to the right; negative z is to the left. Ranking uses z, not raw teacher units.

Strongest VoiceNet dimensions relative to training

Tension (TENS)

z +1.78 / +2.13raw 3.07 / 3.38

Newsreader style (S_NEWS)

z +1.11 / +1.39raw 1.04 / 1.20

Mixed resonance (R_MIXD)

z +0.97 / +1.27raw 2.25 / 2.51

Whispered talking style (S_WHIS)

z +1.15 / +0.99raw 3.45 / 3.19

Vulnerability (VULN)

z +1.10 / +1.01raw 3.73 / 3.64

Cognitive load (COGL)

z +1.00 / +0.56raw 3.15 / 2.69

Perceived gender (GEND)

z +0.93 / +0.77raw 5.52 / 5.27

All 57 VoiceNet predictions, including raw units, are in the full table below. These seven are ranked by z; the top values may differ from the strongest raw dimensions.

Voice, speed and quality scores in context

Genuineness (0–6)z -0.17 / -0.28raw 2.06 / 1.87

Vocal-burst blend (0–10)z +0.22 / +0.11raw 7.28 / 6.98

Content enjoyment (CE)z +0.42 / +0.99raw 5.22 / 5.80

Production quality (PQ)z +0.64 / +0.28raw 7.61 / 7.29

Speech signal quality, calibratedz -0.47 / -1.45raw 3.25 / 2.76

Background quality, calibratedz +0.46 / -0.04raw 3.81 / 3.35

Overall quality, calibratedz +0.22 / -0.35raw 2.97 / 2.63

P.808 MOS estimatez +0.27 / +0.31raw 3.56 / 3.57

score content enjoymentz -0.25 / +0.21raw 4.43 / 4.57

score overall qualityz +0.52 / +0.38raw 2.91 / 2.84

Background Noisez -0.27 / -0.48raw 0.73 / 0.68

Tempo (TEMP)z -0.98 / -1.14raw 0.95 / 0.76

Arousal (AROU)z -1.24 / -0.77raw 0.94 / 1.47

Valence (VALN)z -1.49 / -1.47raw 0.66 / 0.69

Recording quality (RCQL)z -0.41 / -0.70raw 2.39 / 2.13

Background noise (BKGN)z -0.49 / -0.61raw 2.33 / 2.24

talking speedz +0.75 / -0.21raw 11.86 / 8.23

Characters per second (CPS): 11.77 raw · z +0.73

Orange speaker embedding reconstruction

Cosine against Orange on this same clip (higher means closer to that teacher vector):

Embedding	Tiny	Base
Timbre · 128D	0.808	0.876
Identity · 250D	0.699	0.671

Vocal-burst regions

Tiny

Base

0 s16.8 s

Verified burst intervals are unavailable for this clip.

Tiny: 2 regions, count-head estimate 1.72; Base: 2 regions, count-head estimate 1.80.

Exact predicted start and end times

Model	Region	Start (s)	End (s)	Duration (s)
Tiny	1	5.56	5.72	0.16
Tiny	2	10.90	11.22	0.32
Base	1	5.56	5.72	0.16
Base	2	10.90	11.22	0.32

All 192 score slots · raw and z values

#	Target	Tiny raw	Tiny z	Base raw	Base z	Train median	Train SD
Emotion scores Forty clip-level Empathic Insight emotion teacher outputs. Each row evaluates one named emotion score.
0	Affectionemo_Affection	0.180	+0.30	0.198	+0.34	0.007	0.570
1	Amusementemo_Amusement	0.047	+0.05	0.061	+0.07	-0.001	0.885
2	Angeremo_Anger	0.094	+0.15	0.021	+0.03	0.004	0.613
3	Astonishment Surpriseemo_Astonishment_Surprise	0.052	+0.08	0.020	+0.03	0.005	0.572
4	Aweemo_Awe	0.017	+0.04	0.001	+0.00	0.000	0.427
5	Bitternessemo_Bitterness	0.283	+0.65	0.151	+0.33	0.013	0.415
6	Concentrationemo_Concentration	0.887	+0.34	0.887	+0.34	0.634	0.741
7	Confusionemo_Confusion	0.753	+1.39	0.689	+1.27	0.001	0.540
8	Contemplationemo_Contemplation	0.816	+1.23	0.737	+1.09	0.082	0.598
9	Contemptemo_Contempt	0.018	+0.04	-0.012	-0.02	-0.000	0.464
10	Contentmentemo_Contentment	0.002	+0.00	-0.045	-0.09	0.000	0.514
11	Disappointmentemo_Disappointment	1.969	+2.81	1.854	+2.65	0.000	0.700
12	Disgustemo_Disgust	0.012	+0.01	-0.025	-0.07	0.007	0.489
13	Distressemo_Distress	2.732	+3.33	2.515	+3.06	0.000	0.821
14	Doubtemo_Doubt	0.941	+2.01	0.944	+2.02	0.006	0.466
15	Elationemo_Elation	0.031	+0.03	-0.003	-0.02	0.012	0.728
16	Embarrassmentemo_Embarrassment	0.639	+1.39	0.627	+1.36	0.043	0.430
17	Emotional Numbnessemo_Emotional_Numbness	0.292	+0.31	0.250	+0.27	0.004	0.917
18	Fatigue Exhaustionemo_Fatigue_Exhaustion	2.176	+3.99	1.711	+3.12	0.028	0.539
19	Fearemo_Fear	1.928	+3.14	1.994	+3.25	0.015	0.610
20	Helplessnessemo_Helplessness	2.411	+3.47	2.201	+3.17	-0.004	0.696
21	Hope Enthusiasm Optimismemo_Hope_Enthusiasm_Optimism	0.024	-0.12	-0.006	-0.16	0.117	0.760
22	Impatience and Irritabilityemo_Impatience_and_Irritability	0.462	+0.44	0.379	+0.33	0.149	0.705
23	Infatuationemo_Infatuation	0.160	+0.33	0.120	+0.25	-0.015	0.533
24	Interestemo_Interest	0.617	-1.07	0.987	-0.66	1.589	0.907
25	Intoxication Altered States of Consciousnessemo_Intoxication_Altered_States_of_Consciousness	0.024	+0.09	0.231	+0.46	-0.025	0.559
26	Jealousy and Envyemo_Jealousy_and_Envy	0.102	+0.10	0.077	+0.04	0.059	0.442
27	Longingemo_Longing	1.647	+2.47	1.518	+2.27	0.087	0.632
28	Malevolence Maliceemo_Malevolence_Malice	0.056	+0.00	0.043	-0.02	0.055	0.534
29	Painemo_Pain	1.232	+2.13	1.066	+1.84	-0.002	0.579
30	Pleasure Ecstasyemo_Pleasure_Ecstasy	-0.104	-0.20	0.025	+0.01	0.017	0.614
31	Prideemo_Pride	0.024	+0.04	-0.009	-0.02	0.002	0.509
32	Reliefemo_Relief	1.052	+1.50	1.079	+1.54	0.033	0.681
33	Sadnessemo_Sadness	2.334	+3.08	2.059	+2.71	0.000	0.759
34	Sexual Lustemo_Sexual_Lust	0.237	+0.42	0.428	+0.81	0.030	0.494
35	Shameemo_Shame	1.276	+2.47	0.952	+1.84	0.013	0.510
36	Sournessemo_Sourness	-0.033	-0.06	-0.010	-0.01	-0.005	0.439
37	Teasingemo_Teasing	0.056	+0.10	-0.031	-0.06	0.000	0.545
38	Thankfulness Gratitudeemo_Thankfulness_Gratitude	0.208	+0.24	0.177	+0.20	0.041	0.697
39	Triumphemo_Triumph	0.004	+0.02	-0.039	-0.06	-0.007	0.521
VoiceNet dimensions Fifty-seven VoiceNet voice, delivery, style, and recording dimensions. Codes are expanded in the target column.
40	Perceived voice age (AGEV)vn_AGEV_reg	3.380	+0.32	3.191	+0.17	2.984	1.238
41	Arousal (AROU)vn_AROU_reg	0.941	-1.24	1.473	-0.77	2.359	1.147
42	Arousal shift (ARSH)vn_ARSH_reg	0.602	-2.28	0.794	-2.06	2.580	0.867
43	Vocal attack (ATCK)vn_ATCK_reg	0.493	-1.29	0.637	-1.18	2.162	1.295
44	Background noise (BKGN)vn_BKGN_reg	2.330	-0.49	2.235	-0.61	2.703	0.761
45	Brightness (BRGT)vn_BRGT_reg	2.133	+0.17	2.238	+0.30	1.991	0.813
46	Speech chunking (CHNK)vn_CHNK_reg	0.937	-0.73	1.254	-0.48	1.847	1.239
47	Articulation clarity (CLRT)vn_CLRT_reg	1.474	-0.58	1.406	-0.65	2.018	0.945
48	Cognitive load (COGL)vn_COGL_reg	3.150	+1.00	2.693	+0.56	2.094	1.061
49	Dynamic arc (DARC)vn_DARC_reg	-0.367	-1.44	-0.324	-1.41	1.615	1.380
50	Disfluency (DFLU)vn_DFLU_reg	2.893	+0.34	2.674	+0.16	2.488	1.184
51	Emphasis (EMPH)vn_EMPH_reg	1.331	-0.84	1.607	-0.66	2.607	1.524
52	Esthetics (ESTH)vn_ESTH_reg	2.478	+0.10	2.561	+0.20	2.402	0.782
53	Content appropriateness (EXPL)vn_EXPL_reg	-0.042	-0.40	0.108	+0.07	0.086	0.322
54	Focus (FOCS)vn_FOCS_reg	0.776	-1.42	1.079	-1.15	2.344	1.102
55	Fullness (FULL)vn_FULL_reg	2.462	+0.77	2.548	+0.87	1.778	0.889
56	Perceived gender (GEND)vn_GEND_reg	5.524	+0.93	5.275	+0.77	4.055	1.588
57	Harmonicity (HARM)vn_HARM_reg	2.095	-0.46	2.190	-0.35	2.480	0.836
58	Metallic character (METL)vn_METL_reg	0.771	-0.89	0.846	-0.81	1.621	0.958
59	Pitch range (RANG)vn_RANG_reg	1.673	-1.38	1.930	-1.10	2.914	0.897
60	Recording quality (RCQL)vn_RCQL_reg	2.389	-0.41	2.133	-0.70	2.754	0.888
61	Vocal register (REGS)vn_REGS_reg	0.937	-0.21	0.844	-0.28	1.198	1.268
62	Respiration (RESP)vn_RESP_reg	3.528	+0.80	3.540	+0.81	2.680	1.056
63	Roughness (ROUG)vn_ROUG_reg	1.406	-0.71	1.451	-0.66	2.033	0.887
64	Chest resonance (R_CHST)vn_R_CHST_reg	2.598	+0.55	2.471	+0.40	2.135	0.844
65	Head resonance (R_HEAD)vn_R_HEAD_reg	0.799	-1.64	0.767	-1.68	2.148	0.822
66	Mask resonance (R_MASK)vn_R_MASK_reg	1.007	-0.90	0.883	-1.02	1.908	1.005
67	Mixed resonance (R_MIXD)vn_R_MIXD_reg	2.249	+0.97	2.507	+1.27	1.436	0.841
68	Nasal resonance (R_NASL)vn_R_NASL_reg	0.432	-2.25	0.416	-2.27	2.791	1.047
69	Oral resonance (R_ORAL)vn_R_ORAL_reg	1.975	-0.28	2.138	-0.06	2.184	0.741
70	Throat resonance (R_THRT)vn_R_THRT_reg	0.382	-2.10	0.596	-1.84	2.070	0.803
71	Smoothness (SMTH)vn_SMTH_reg	1.134	-0.92	1.073	-0.98	2.143	1.093
72	Stance (STNC)vn_STNC_reg	0.910	-1.51	1.355	-1.12	2.633	1.137
73	Speech structure (STRU)vn_STRU_reg	1.662	-0.50	1.484	-0.68	2.137	0.958
74	ASMR style (S_ASMR)vn_S_ASMR_reg	1.959	+0.42	1.797	+0.30	1.370	1.411
75	Authoritative style (S_AUTH)vn_S_AUTH_reg	0.814	-0.26	1.090	+0.00	1.088	1.043
76	Cartoonish style (S_CART)vn_S_CART_reg	1.373	-0.13	1.326	-0.17	1.560	1.401
77	Casual style (S_CASU)vn_S_CASU_reg	3.190	-0.47	3.489	-0.24	3.793	1.278
78	Conversational style (S_CONV)vn_S_CONV_reg	1.575	-0.77	1.779	-0.62	2.594	1.318
79	Dramatic style (S_DRAM)vn_S_DRAM_reg	1.978	-0.65	2.290	-0.38	2.721	1.148
80	Formal style (S_FORM)vn_S_FORM_reg	1.510	+0.31	1.361	+0.16	1.195	1.021
81	Monologue style (S_MONO)vn_S_MONO_reg	3.007	+0.14	2.777	-0.04	2.824	1.284
82	Narrator style (S_NARR)vn_S_NARR_reg	1.001	-0.21	1.246	-0.04	1.307	1.446
83	Newsreader style (S_NEWS)vn_S_NEWS_reg	1.038	+1.11	1.198	+1.39	0.408	0.568
84	Playful style (S_PLAY)vn_S_PLAY_reg	-0.149	-1.90	0.075	-1.73	2.352	1.315
85	Ranting or angry style (S_RANT)vn_S_RANT_reg	0.859	-0.27	0.898	-0.24	1.213	1.289
86	Storytelling style (S_STRY)vn_S_STRY_reg	1.335	-0.84	1.705	-0.57	2.480	1.366
87	Teacher or didactic style (S_TECH)vn_S_TECH_reg	-0.332	-0.80	-0.156	-0.65	0.646	1.227
88	Whispered talking style (S_WHIS)vn_S_WHIS_reg	3.453	+1.15	3.191	+0.99	1.597	1.618
89	Tempo (TEMP)vn_TEMP_reg	0.952	-0.98	0.764	-1.14	2.117	1.190
90	Tension (TENS)vn_TENS_reg	3.070	+1.78	3.376	+2.13	1.559	0.852
91	Valence (VALN)vn_VALN_reg	0.659	-1.49	0.686	-1.47	2.328	1.118
92	Valence shift (VALS)vn_VALS_reg	0.996	-1.41	0.996	-1.41	2.518	1.079
93	Velocity flux (VFLX)vn_VFLX_reg	-1.083	-2.76	-0.876	-2.59	2.256	1.208
94	Volatility (VOLT)vn_VOLT_reg	2.877	+0.33	2.863	+0.31	2.586	0.886
95	Vulnerability (VULN)vn_VULN_reg	3.731	+1.10	3.638	+1.01	2.648	0.984
96	Warmth (WARM)vn_WARM_reg	2.797	+0.24	2.677	+0.11	2.578	0.909
Genuineness, blend, and legacy quality Genuineness and vocal-burst blend are predicted. R_quality has Ladder training labels but no valid P3 test labels.
97	Genuineness (0–6)genuineness_0_6	2.057	-0.17	1.871	-0.28	2.332	1.621
98	Vocal-burst blend (0–10)blend_0_10	7.278	+0.22	6.984	+0.11	6.676	2.738
99	Legacy R_quality (no P3 test labels)R_quality	1.063	-0.09	1.008	-0.26	1.095	0.338
Empathic Insight Plus extra scores Nineteen additional clip-level teacher scores, including background noise and content enjoyment.
100	Ageeiv_extra:Age	3.543	+1.00	3.224	-0.09	3.250	0.293
101	Arousaleiv_extra:Arousal	1.350	+0.14	1.438	+0.34	1.289	0.435
102	Authenticityeiv_extra:Authenticity	2.736	+0.45	2.934	+1.75	2.667	0.153
103	Background Noiseeiv_extra:Background_Noise	0.735	-0.27	0.680	-0.48	0.808	0.264
104	Confident vs. Hesitanteiv_extra:Confident_vs._Hesitant	1.544	+1.67	1.183	+0.47	1.040	0.303
105	Gendereiv_extra:Gender	-0.268	+0.35	-0.376	+0.25	-0.621	0.999
106	High-Pitched vs. Low-Pitchedeiv_extra:High-Pitched_vs._Low-Pitched	1.833	+0.02	1.806	-0.09	1.827	0.250
107	Monotone vs. Expressiveeiv_extra:Monotone_vs._Expressive	1.525	-0.71	1.718	-0.30	1.859	0.470
108	Recording Qualityeiv_extra:Recording_Quality	2.066	-0.23	2.163	+0.06	2.144	0.332
109	Serious vs. Humorouseiv_extra:Serious_vs._Humorous	0.082	-2.49	0.564	-1.07	0.929	0.340
110	Soft vs. Harsheiv_extra:Soft_vs._Harsh	0.453	+0.54	0.481	+0.63	0.281	0.320
111	Submissive vs. Dominanteiv_extra:Submissive_vs._Dominant	0.239	-0.42	0.455	+0.25	0.376	0.324
112	Valenceeiv_extra:Valence	-0.629	-1.67	-1.056	-2.79	0.005	0.380
113	Vulnerable vs. Emotionally Detachedeiv_extra:Vulnerable_vs._Emotionally_Detached	1.388	-0.75	1.516	-0.46	1.715	0.437
114	Warm vs. Coldeiv_extra:Warm_vs._Cold	-0.048	-0.33	-0.153	-0.68	0.051	0.300
115	score background qualityeiv_extra:score_background_quality	3.461	+0.23	3.532	+0.33	3.301	0.693
116	score content enjoymenteiv_extra:score_content_enjoyment	4.432	-0.25	4.570	+0.21	4.507	0.303
117	score overall qualityeiv_extra:score_overall_quality	2.913	+0.52	2.842	+0.38	2.652	0.507
118	score speech qualityeiv_extra:score_speech_quality	1.738	-0.48	1.798	-0.07	1.808	0.146
Meta AudioBox Aesthetics Four AudioBox aesthetic teacher outputs. Expansions follow the official Meta model card.
119	Content enjoyment (CE)audiobox:CE	5.222	+0.42	5.804	+0.99	4.799	1.018
120	Content usefulness (CU)audiobox:CU	6.526	+0.88	6.167	+0.52	5.649	1.001
121	Production complexity (PC)audiobox:PC	2.555	+0.14	1.719	-0.38	2.331	1.617
122	Production quality (PQ)audiobox:PQ	7.607	+0.64	7.287	+0.28	7.044	0.879
Microsoft DNSMOS Seven DNSMOS teacher outputs: raw and calibrated SIG/BAK/OVRL estimates plus P.808 MOS.
123	Speech signal quality, rawdnsmos:SIG_raw	3.627	-0.41	2.934	-1.44	3.900	0.669
124	Background quality, rawdnsmos:BAK_raw	3.749	+0.48	3.434	+0.20	3.211	1.124
125	Overall quality, rawdnsmos:OVRL_raw	3.273	+0.23	2.908	-0.22	3.085	0.812
126	Speech signal quality, calibrateddnsmos:SIG	3.251	-0.47	2.761	-1.45	3.488	0.501
127	Background quality, calibrateddnsmos:BAK	3.814	+0.46	3.352	-0.04	3.389	0.928
128	Overall quality, calibrateddnsmos:OVRL	2.974	+0.22	2.627	-0.35	2.840	0.606
129	P.808 MOS estimatednsmos:P808_MOS	3.555	+0.27	3.575	+0.31	3.421	0.496
Vocal-burst count The regression target is log(1 + count). A separate table also reports count error after inverse transformation.
130	Vocal-burst count, log(1 + count)burst_count_log1p	1.001	+1.55	1.028	+1.59	0.000	0.647
VoiceCLAP attributes Sixty-one individual VoiceCLAP attribute teacher scores. The raw 768D VoiceCLAP embedding is stored in sidecars but is not a model output.
131	Affectionvoiceclap_attribute:Affection	0.997	+0.09	1.002	+0.10	0.947	0.554
132	Agevoiceclap_attribute:Age	2.899	-0.60	3.124	-0.19	3.229	0.547
133	Amusementvoiceclap_attribute:Amusement	0.162	-0.40	0.052	-0.59	0.392	0.572
134	Angervoiceclap_attribute:Anger	0.581	-0.81	0.812	-0.36	0.992	0.506
135	Arousalvoiceclap_attribute:Arousal	1.243	-0.28	1.555	+0.22	1.420	0.622
136	Astonishment Surprisevoiceclap_attribute:Astonishment_Surprise	0.350	-0.33	0.547	+0.08	0.509	0.479
137	Authenticityvoiceclap_attribute:Authenticity	2.943	+1.04	2.970	+1.19	2.770	0.167
138	Awevoiceclap_attribute:Awe	0.233	-1.18	0.432	-0.41	0.539	0.259
139	Background Noisevoiceclap_attribute:Background_Noise	0.405	-0.62	0.624	+0.21	0.567	0.264
140	Bitternessvoiceclap_attribute:Bitterness	0.608	+0.07	0.795	+0.86	0.592	0.236
141	Concentrationvoiceclap_attribute:Concentration	0.918	-0.56	0.673	-1.02	1.214	0.531
142	Confident vs. Hesitantvoiceclap_attribute:Confident_vs._Hesitant	1.160	+0.19	1.125	+0.12	1.069	0.468
143	Confusionvoiceclap_attribute:Confusion	0.726	+0.25	0.752	+0.33	0.643	0.334
144	Contemplationvoiceclap_attribute:Contemplation	1.234	+1.12	0.768	-0.03	0.780	0.406
145	Contemptvoiceclap_attribute:Contempt	0.438	-0.80	0.178	-1.57	0.709	0.339
146	Contentmentvoiceclap_attribute:Contentment	0.500	-0.29	0.110	-1.56	0.588	0.307
147	Disappointmentvoiceclap_attribute:Disappointment	1.072	+1.07	1.344	+2.01	0.760	0.291
148	Disgustvoiceclap_attribute:Disgust	0.363	-1.26	0.520	-0.51	0.625	0.207
149	Distressvoiceclap_attribute:Distress	1.539	+1.75	1.922	+2.84	0.927	0.350
150	Doubtvoiceclap_attribute:Doubt	0.773	+1.27	0.865	+1.76	0.535	0.188
151	Elationvoiceclap_attribute:Elation	-0.274	-2.05	0.003	-1.35	0.539	0.397
152	Embarrassmentvoiceclap_attribute:Embarrassment	0.408	+0.32	0.279	-0.09	0.307	0.314
153	Emotional Numbnessvoiceclap_attribute:Emotional_Numbness	1.092	+1.61	0.978	+1.18	0.664	0.266
154	Fatigue Exhaustionvoiceclap_attribute:Fatigue_Exhaustion	0.785	+1.24	0.679	+0.83	0.462	0.261
155	Fearvoiceclap_attribute:Fear	1.059	+2.08	1.087	+2.21	0.618	0.212
156	Gendervoiceclap_attribute:Gender	-0.137	+0.01	-0.233	-0.08	-0.151	1.005
157	Helplessnessvoiceclap_attribute:Helplessness	1.164	+1.88	1.445	+2.93	0.658	0.268
158	High-Pitched vs. Low-Pitchedvoiceclap_attribute:High-Pitched_vs._Low-Pitched	1.949	+0.29	2.031	+0.51	1.840	0.375
159	Hope Enthusiasm Optimismvoiceclap_attribute:Hope_Enthusiasm_Optimism	0.144	-1.42	0.159	-1.38	0.705	0.396
160	Impatience and Irritabilityvoiceclap_attribute:Impatience_and_Irritability	1.042	-0.02	1.354	+0.56	1.052	0.541
161	Infatuationvoiceclap_attribute:Infatuation	0.570	-0.12	0.417	-0.58	0.608	0.332
162	Interestvoiceclap_attribute:Interest	0.840	-1.72	0.998	-1.36	1.598	0.440
163	Intoxication Altered States of Consciousnessvoiceclap_attribute:Intoxication_Altered_States_of_Consciousness	0.679	+0.38	0.455	-0.10	0.502	0.463
164	Jealousy & Envyvoiceclap_attribute:Jealousy_&_Envy	0.560	+0.15	0.485	-0.15	0.523	0.245
165	Longingvoiceclap_attribute:Longing	0.691	+0.70	0.782	+1.11	0.538	0.220
166	Malevolence Malicevoiceclap_attribute:Malevolence_Malice	0.661	-0.50	0.683	-0.43	0.833	0.346
167	Monotone vs. Expressivevoiceclap_attribute:Monotone_vs._Expressive	1.427	-0.59	1.668	-0.18	1.775	0.594
168	Painvoiceclap_attribute:Pain	0.877	+2.27	0.953	+2.62	0.381	0.218
169	Pleasure Ecstasyvoiceclap_attribute:Pleasure_Ecstasy	0.114	-1.29	0.081	-1.40	0.503	0.301
170	Pridevoiceclap_attribute:Pride	0.762	-0.05	0.527	-0.73	0.780	0.349
171	Recording Qualityvoiceclap_attribute:Recording_Quality	2.234	-0.24	2.143	-0.52	2.313	0.328
172	Reliefvoiceclap_attribute:Relief	0.844	-0.43	1.173	+0.36	1.025	0.415
173	Sadnessvoiceclap_attribute:Sadness	1.178	+1.36	1.613	+2.75	0.752	0.313
174	Serious vs. Humorousvoiceclap_attribute:Serious_vs._Humorous	0.676	-0.22	0.731	-0.13	0.803	0.568
175	Sexual Lustvoiceclap_attribute:Sexual_Lust	0.376	-0.62	0.007	-1.50	0.635	0.419
176	Shamevoiceclap_attribute:Shame	0.592	+0.23	0.615	+0.31	0.526	0.283
177	Soft vs. Harshvoiceclap_attribute:Soft_vs._Harsh	0.415	+0.71	0.396	+0.66	0.160	0.360
178	Sournessvoiceclap_attribute:Sourness	0.531	-0.60	0.362	-1.18	0.706	0.291
179	Submissive vs. Dominantvoiceclap_attribute:Submissive_vs._Dominant	0.149	-1.32	0.099	-1.46	0.623	0.359
180	Teasingvoiceclap_attribute:Teasing	0.487	-0.14	0.545	+0.01	0.540	0.379
181	Thankfulness Gratitudevoiceclap_attribute:Thankfulness_Gratitude	1.176	-0.39	0.742	-1.21	1.384	0.529
182	Triumphvoiceclap_attribute:Triumph	0.589	-0.35	0.486	-0.64	0.716	0.359
183	Valencevoiceclap_attribute:Valence	-1.324	-2.08	-1.523	-2.39	-0.007	0.635
184	Vulnerable vs. Emotionally Detachedvoiceclap_attribute:Vulnerable_vs._Emotionally_Detached	1.496	-0.26	1.474	-0.30	1.638	0.556
185	Warm vs. Coldvoiceclap_attribute:Warm_vs._Cold	-0.117	-0.13	-0.038	+0.07	-0.066	0.400
186	durationvoiceclap_attribute:duration	17.301	+1.01	20.394	+1.49	10.914	6.354
187	score background qualityvoiceclap_attribute:score_background_quality	3.425	+0.36	3.342	+0.19	3.245	0.498
188	score content enjoymentvoiceclap_attribute:score_content_enjoyment	4.769	+0.77	4.849	+1.31	4.656	0.147
189	score overall qualityvoiceclap_attribute:score_overall_quality	2.648	+0.03	2.608	-0.07	2.635	0.412
190	score speech qualityvoiceclap_attribute:score_speech_quality	1.929	+0.55	1.894	+0.05	1.891	0.069
191	talking speedvoiceclap_attribute:talking_speed	11.856	+0.75	8.228	-0.21	9.028	3.756

All Orange embedding components

The cosine above is the meaningful vector-level comparison; component values have no standalone semantic label.

Timbre — all 128 vector components

Dimension	Tiny	Base	Orange teacher
0	-0.0484	-0.1252	-0.0913
1	0.0455	0.1242	0.0269
2	-0.0704	-0.0514	-0.0900
3	-0.1076	-0.0865	-0.0930
4	0.1006	0.0829	0.0112
5	-0.0353	-0.0804	-0.0942
6	0.0195	-0.0578	-0.0832
7	-0.0509	0.0244	0.0290
8	0.0401	-0.0575	0.0068
9	0.0244	0.0031	0.0640
10	0.0156	-0.0031	-0.0011
11	-0.1153	0.0008	-0.0640
12	0.0194	0.0073	-0.0288
13	-0.0767	-0.1160	-0.0906
14	-0.0353	-0.0296	0.0386
15	-0.0100	-0.0992	-0.0752
16	-0.1350	-0.0649	-0.1136
17	-0.0120	0.0354	0.0642
18	-0.0193	-0.0106	-0.0363
19	-0.0323	0.0379	-0.0334
20	-0.0089	-0.0267	-0.0380
21	0.1000	0.1354	0.1355
22	-0.1038	-0.0784	-0.0863
23	-0.1108	-0.0743	-0.0540
24	-0.0923	-0.0616	-0.0741
25	-0.0815	-0.0202	-0.0780
26	0.0580	0.0639	-0.0092
27	-0.0646	0.0083	-0.0836
28	-0.1337	-0.1099	-0.1011
29	0.0360	0.1033	0.1250
30	0.2611	0.1913	0.1816
31	0.1497	-0.0226	0.0707
32	-0.0666	-0.0656	-0.0782
33	0.0462	0.0677	0.0702
34	-0.1248	-0.0555	-0.0823
35	0.1987	0.2036	0.2054
36	-0.0264	-0.0672	-0.0986
37	-0.0471	-0.0285	-0.0820
38	-0.1465	-0.0957	-0.0916
39	-0.1083	-0.0997	-0.0926
40	-0.1102	-0.0794	-0.0541
41	-0.1102	-0.1323	-0.1318
42	-0.1490	-0.0298	-0.0926
43	-0.0646	-0.0132	-0.0674
44	0.1490	0.1333	0.1547
45	-0.0345	0.0085	0.0017
46	-0.1108	-0.0921	-0.0853
47	-0.0866	-0.0957	-0.0928
48	-0.0379	-0.0415	-0.0896
49	0.0136	-0.0992	-0.0811
50	0.0261	0.0936	0.0598
51	-0.0691	-0.0855	-0.0917
52	-0.0229	-0.1064	-0.0299
53	0.0465	0.0865	-0.0070
54	0.0089	0.0317	0.0404
55	0.0742	0.1995	0.1209
56	0.0828	0.0336	-0.0176
57	0.0007	0.0382	0.0309
58	-0.0443	-0.0707	-0.0719
59	-0.0013	-0.0422	0.0273
60	0.0250	-0.0296	-0.0885
61	0.0396	-0.0027	0.0439
62	-0.0745	-0.0545	-0.0858
63	0.2446	0.1608	0.1968
64	0.0751	0.0087	0.0242
65	-0.0853	-0.1023	-0.0748
66	0.1745	0.0870	0.1929
67	-0.0608	-0.0926	-0.0885
68	0.1516	0.0634	0.1421
69	-0.0793	-0.0896	-0.0840
70	0.0304	0.0435	0.0295
71	-0.0100	-0.0448	-0.0300
72	-0.0994	-0.1104	-0.0888
73	0.0374	0.0263	-0.0497
74	-0.1312	-0.1267	-0.1003
75	-0.0162	0.0328	0.1302
76	0.0860	0.1944	0.1569
77	-0.0239	-0.0410	-0.0184
78	0.0395	-0.0550	-0.0817
79	-0.0659	-0.0463	-0.0796
80	0.0153	-0.0697	-0.0301
81	-0.0229	-0.0738	-0.0831
82	-0.0050	-0.0753	-0.0878
83	-0.0396	-0.0539	-0.0714
84	0.0131	-0.0257	0.0412
85	-0.0503	-0.0486	-0.0845
86	0.0968	-0.0405	0.1168
87	-0.0930	-0.0108	-0.0308
88	0.0860	-0.0307	-0.0026
89	0.1974	0.1221	0.1423
90	-0.0471	-0.1135	-0.0995
91	0.2649	0.2748	0.2964
92	-0.1140	-0.1293	-0.0891
93	0.0234	0.0896	0.0498
94	0.0049	-0.0519	-0.0789
95	-0.0057	-0.0896	-0.0842
96	-0.0258	0.0422	0.0527
97	-0.0215	-0.0649	-0.0121
98	-0.0943	0.0789	0.1000
99	-0.0627	-0.0835	-0.0966
100	0.1127	0.0272	0.0064
101	-0.0688	-0.0057	-0.0367
102	0.0656	-0.0501	-0.0300
103	-0.1242	-0.0997	-0.0969
104	-0.0981	-0.0962	-0.0897
105	-0.0974	-0.0967	-0.0885
106	-0.1038	-0.0268	-0.0811
107	0.0244	0.1364	0.0847
108	0.0828	0.0448	0.0487
109	-0.0529	-0.0860	-0.0900
110	0.0202	0.0196	0.0619
111	-0.1293	-0.1191	-0.1064
112	-0.1000	-0.0870	-0.0905
113	0.0398	0.2209	0.1431
114	-0.1267	-0.1135	-0.0988
115	-0.0548	-0.0583	-0.0319
116	-0.0293	-0.0667	-0.0058
117	-0.0774	-0.1394	-0.1068
118	-0.0406	-0.0702	-0.0894
119	0.1197	0.1893	0.1194
120	0.0653	-0.0106	0.0008
121	-0.0834	-0.1033	-0.0930
122	-0.0122	-0.0865	-0.0238
123	-0.0834	-0.0077	-0.0164
124	0.0904	-0.0154	-0.0583
125	0.0446	0.0639	0.0401
126	-0.0548	-0.0896	-0.0791
127	0.0624	-0.0252	0.0548

Identity — all 250 vector components

Dimension	Tiny	Base	Orange teacher
0	-0.0404	-0.0338	-0.0547
1	0.0040	-0.0267	-0.0307
2	-0.0269	-0.0595	-0.0116
3	-0.1127	-0.0571	-0.0790
4	0.0633	0.1030	0.0482
5	-0.1465	-0.1297	-0.0519
6	0.0143	0.0710	-0.0638
7	-0.0157	-0.1516	-0.0503
8	-0.0290	0.0335	-0.0082
9	0.1370	0.1297	0.0997
10	-0.0392	-0.0769	-0.0521
11	-0.0392	-0.0149	0.0520
12	-0.0003	0.0651	-0.0375
13	-0.0685	-0.0528	-0.0439
14	-0.0592	0.0230	-0.0015
15	0.0364	0.1201	0.0901
16	0.0904	0.0737	0.0219
17	0.0511	0.0470	0.1395
18	-0.0187	0.0204	-0.0505
19	0.0153	0.0649	0.1340
20	0.0461	0.1313	0.0535
21	0.0108	-0.0131	-0.0196
22	-0.0438	-0.0510	-0.0022
23	-0.0452	-0.0422	-0.0370
24	0.1665	0.1484	0.1580
25	-0.0549	-0.0368	-0.0913
26	-0.0628	-0.0201	-0.0500
27	-0.0459	-0.0111	-0.0385
28	0.0751	-0.0031	0.0134
29	-0.0073	0.0185	0.0774
30	0.1579	0.1078	0.1146
31	0.0785	0.0774	0.1211
32	-0.0637	-0.0398	-0.0511
33	-0.0312	-0.0790	-0.0446
34	0.1008	0.0643	0.0407
35	0.0290	0.0961	0.0919
36	0.0435	0.0254	-0.0525
37	-0.0590	-0.0726	-0.0343
38	-0.2188	-0.1687	-0.0689
39	-0.0423	-0.0395	-0.0326
40	-0.0378	-0.0414	0.0421
41	0.0077	-0.0296	0.0492
42	0.0125	0.0139	-0.0076
43	-0.1589	-0.0454	-0.0587
44	-0.0713	-0.0606	-0.0598
45	-0.0523	-0.0026	0.0549
46	0.0502	0.0191	0.0622
47	-0.0002	0.0987	0.0253
48	-0.0253	-0.0366	-0.0530
49	0.0590	0.0155	0.0845
50	-0.0106	-0.0027	-0.0656
51	-0.0096	-0.0379	-0.0197
52	0.0459	-0.0034	0.0091
53	-0.0200	0.0214	0.0463
54	0.0007	0.0307	0.0589
55	0.0671	0.0595	0.0383
56	-0.0540	0.0312	0.0485
57	0.0164	0.0360	-0.0350
58	-0.0609	-0.0699	-0.0477
59	0.0818	0.0488	0.0980
60	-0.0499	-0.0694	-0.0520
61	-0.0369	-0.0338	-0.0461
62	-0.0206	-0.0398	-0.0436
63	-0.0837	-0.0358	-0.0540
64	0.0597	0.0147	0.1212
65	0.0885	0.0934	0.0494
66	-0.0210	0.0018	-0.0222
67	0.0252	0.0939	-0.0241
68	0.0288	0.0090	-0.0327
69	0.0047	-0.0184	-0.0489
70	-0.0080	-0.0408	-0.0720
71	0.1141	0.1420	0.2117
72	-0.0169	-0.0148	-0.0490
73	0.0913	0.0312	0.0506
74	-0.0321	-0.0291	-0.0536
75	-0.0126	0.0059	0.0117
76	0.0011	-0.0769	-0.0473
77	-0.1446	-0.1329	-0.0542
78	0.0718	0.0721	0.1827
79	0.0861	0.0662	0.1061
80	-0.0732	-0.0774	-0.0528
81	0.0045	-0.0422	-0.0541
82	-0.0875	-0.0622	-0.0477
83	-0.0913	-0.0544	-0.0441
84	0.0206	-0.0324	0.0540
85	-0.0932	-0.0715	-0.0530
86	-0.0090	0.0228	0.0479
87	-0.0478	0.0057	-0.0331
88	-0.0326	-0.0747	-0.0424
89	0.0476	0.0518	0.0967
90	-0.1322	-0.0150	-0.0526
91	0.0756	0.0737	0.0156
92	-0.0291	-0.0114	-0.0458
93	-0.0526	-0.0998	-0.0319
94	-0.0614	-0.0574	-0.0346
95	-0.0728	-0.0526	-0.0553
96	-0.0259	-0.0552	-0.0474
97	-0.0108	-0.0318	-0.0625
98	0.0751	0.0998	0.0140
99	-0.0478	-0.0267	-0.0663
100	-0.0086	-0.0226	0.0954
101	0.0010	-0.0044	0.0378
102	0.0033	-0.0239	-0.0592
103	-0.0133	0.0335	-0.0157
104	-0.0932	-0.0891	-0.0495
105	-0.0208	-0.0151	0.0066
106	-0.1165	-0.0624	-0.0409
107	-0.0247	-0.0076	-0.0475
108	0.0219	0.1094	-0.0394
109	-0.0818	-0.0614	-0.0510
110	-0.0476	-0.0403	-0.0387
111	0.0011	-0.0060	0.0764
112	-0.0718	-0.0600	-0.0428
113	-0.0889	-0.0587	-0.0364
114	-0.0761	-0.0811	-0.0580
115	-0.0583	-0.0443	-0.0376
116	-0.0259	0.0222	-0.0505
117	0.0564	0.0742	0.0784
118	-0.0690	-0.1025	-0.0505
119	0.0402	-0.0117	0.0013
120	-0.0112	-0.0560	-0.0676
121	0.0602	0.1527	0.1307
122	0.0561	0.0502	0.0352
123	-0.0009	-0.0649	-0.0047
124	-0.0210	-0.0100	-0.0529
125	0.0248	-0.0339	0.0475
126	0.1265	0.0379	0.0934
127	0.0030	-0.0080	-0.0518
128	-0.0258	-0.0088	-0.0400
129	-0.0366	-0.0157	0.0115
130	-0.0861	-0.0993	-0.0533
131	0.0271	0.0121	0.0394
132	0.0326	-0.0390	-0.0562
133	0.0125	-0.0472	0.1036
134	0.1213	0.1174	0.0378
135	0.0182	-0.0472	-0.0313
136	-0.0723	-0.0758	-0.0568
137	0.0116	-0.0008	0.0356
138	0.0580	0.0945	0.0955
139	-0.0316	0.0998	-0.0290
140	0.0419	-0.0217	0.0479
141	-0.0675	-0.0769	-0.0525
142	-0.0718	-0.0298	-0.0458
143	0.0188	0.0665	0.0480
144	-0.0583	-0.0438	-0.0553
145	-0.0447	-0.0262	0.0342
146	0.0661	0.0870	0.1260
147	-0.0338	-0.0263	-0.0471
148	0.0006	-0.0073	-0.0545
149	-0.0870	-0.0161	0.0086
150	0.0407	0.0456	0.0109
151	-0.0694	0.0041	-0.0137
152	-0.0190	-0.0231	-0.0588
153	0.0468	-0.0058	0.0486
154	-0.1004	-0.0568	-0.0517
155	-0.0590	-0.0173	-0.0692
156	0.0483	-0.0002	-0.0290
157	0.1108	0.0515	0.0614
158	-0.0385	-0.0822	-0.0376
159	0.0277	0.0274	-0.0007
160	-0.0647	-0.0758	-0.0504
161	-0.0259	-0.0822	-0.1160
162	-0.0559	-0.0054	-0.0615
163	-0.0043	0.0026	0.0392
164	-0.0380	-0.0520	-0.0466
165	0.0205	-0.0747	0.0490
166	-0.0604	-0.0097	-0.0617
167	0.1170	0.0731	0.1370
168	0.0671	0.1137	0.0349
169	0.1103	0.1836	0.0868
170	-0.0248	-0.0352	0.0044
171	-0.0766	-0.0574	-0.0467
172	0.0694	0.0338	0.0465
173	-0.0302	-0.0558	-0.0621
174	0.0169	0.0811	-0.0489
175	-0.0918	-0.1030	-0.0878
176	-0.0073	0.0550	0.1155
177	-0.0323	-0.0360	-0.0437
178	-0.0642	-0.0502	-0.0471
179	-0.0271	-0.0127	-0.0653
180	0.0980	0.1409	0.1021
181	-0.0273	-0.0093	0.0621
182	-0.0476	-0.0649	-0.0458
183	-0.0380	-0.0037	0.0066
184	-0.0340	-0.0167	-0.0538
185	0.1360	0.1516	0.0888
186	-0.0480	-0.0392	-0.0639
187	0.0856	0.0955	0.0757
188	0.0285	-0.0107	0.0346
189	0.1512	0.1398	0.1604
190	-0.0195	-0.0294	-0.0178
191	0.0079	-0.0216	0.0273
192	-0.0454	-0.0528	-0.0641
193	-0.0291	-0.0091	-0.0558
194	-0.0087	0.0467	-0.0331
195	-0.0423	-0.0180	-0.0504
196	0.0685	0.0400	-0.0453
197	0.0675	0.0024	-0.0165
198	-0.0161	-0.0347	-0.0512
199	-0.0018	0.0913	0.0236
200	-0.0302	-0.0606	-0.0613
201	0.0143	-0.0014	0.0349
202	-0.1089	-0.1318	-0.1103
203	-0.0086	-0.0276	-0.0661
204	0.1137	0.1094	0.1132
205	0.0889	-0.0083	0.1042
206	-0.0350	-0.0288	-0.0305
207	-0.0044	-0.0390	0.0185
208	-0.0870	-0.0259	-0.0550
209	0.0585	-0.0252	0.0242
210	-0.0007	0.0319	-0.0439
211	-0.0526	-0.0539	-0.0407
212	0.0652	0.0614	0.1337
213	0.0127	-0.0552	0.0232
214	0.0084	0.0214	0.0852
215	0.0540	0.0574	0.0204
216	-0.0799	-0.0382	-0.0634
217	-0.0200	0.0032	0.0270
218	-0.0942	-0.1537	-0.0615
219	-0.0614	-0.0432	-0.0503
220	-0.0554	-0.0438	-0.0526
221	-0.0492	0.0030	-0.0460
222	-0.0521	-0.0627	-0.0621
223	-0.0604	-0.0276	-0.0210
224	-0.0407	-0.0406	-0.0233
225	-0.0471	-0.0303	-0.0441
226	0.0499	0.1249	0.0876
227	0.1132	0.1687	0.0718
228	0.0535	0.0292	-0.0504
229	0.0704	-0.0159	-0.0581
230	-0.0528	-0.0555	-0.0439
231	0.1042	0.0111	0.1741
232	0.0307	-0.0020	-0.0503
233	-0.1313	-0.0870	-0.0694
234	0.0756	0.0085	-0.0450
235	0.0718	0.0210	0.0513
236	-0.0195	-0.0475	-0.0455
237	-0.0380	-0.0390	-0.0541
238	-0.0438	-0.0322	-0.0312
239	-0.0190	-0.0622	-0.0548
240	0.0545	-0.0199	-0.0540
241	0.0354	-0.0065	0.0087
242	-0.0894	-0.0472	-0.0781
243	-0.0842	-0.0833	-0.0681
244	-0.0029	0.0010	0.0320
245	-0.0138	-0.0475	0.0706
246	0.0537	-0.0606	-0.0429
247	-0.0661	-0.0406	-0.0446
248	-0.0685	-0.0681	-0.0606
249	-0.0099	-0.0096	-0.0406

Source: M2_RECENT_DPO_LORA_SPEAKER_EMOTION_STUDY_2026-10-02.html · SHA-256 91445a82934d6abe…

g04GermanDPO acting study

HVSAC-030 · de · targets: Pride, Confusion, Amusement

Generated TTS prediction · S3 base · C01 · 16.4 s

Die Suppe ist ausgezeichnet, obwohl der Löffel eindeutig eine fragwürdige Haltung hat. Dieser Tisch steht außerdem schief, oder vielleicht ist es die Kunst an der Wand. Bitte bringen Sie mir noch einen Kaffee, ich muss weiter urteilen.

Tiny Base · values are model estimates, not ground truth

Strongest emotions relative to training

Teasing

z +3.03 / +3.37raw 1.65 / 1.84

Fear

z +1.92 / +1.90raw 1.19 / 1.17

Contentment

z +1.64 / +1.83raw 0.84 / 0.94

Relief

z +1.74 / +1.49raw 1.22 / 1.05

Fatigue Exhaustion

z +1.35 / +1.53raw 0.75 / 0.85

Amusement

z +1.49 / +1.39raw 1.32 / 1.23

Intoxication Altered States of Consciousness

z +1.31 / +0.67raw 0.71 / 0.35

The center of each bar is the S9 teacher median. Positive z is to the right; negative z is to the left. Ranking uses z, not raw teacher units.

Strongest VoiceNet dimensions relative to training

Narrator style (S_NARR)

z +1.33 / +1.14raw 3.22 / 2.96

Content appropriateness (EXPL)

z +1.28 / +1.18raw 0.50 / 0.47

Volatility (VOLT)

z +1.17 / +1.10raw 3.62 / 3.56

Cartoonish style (S_CART)

z +1.15 / +0.99raw 3.17 / 2.95

Teacher or didactic style (S_TECH)

z +0.98 / +1.10raw 1.85 / 1.99

Vulnerability (VULN)

z +0.67 / +0.91raw 3.31 / 3.54

Perceived gender (GEND)

z +0.84 / +0.89raw 5.39 / 5.46

All 57 VoiceNet predictions, including raw units, are in the full table below. These seven are ranked by z; the top values may differ from the strongest raw dimensions.

Voice, speed and quality scores in context

Genuineness (0–6)z -0.22 / -0.15raw 1.98 / 2.08

Vocal-burst blend (0–10)z -1.71 / -1.57raw 1.99 / 2.38

Content enjoyment (CE)z +0.80 / +0.80raw 5.61 / 5.61

Production quality (PQ)z +0.81 / +0.63raw 7.75 / 7.60

Speech signal quality, calibratedz -0.35 / -0.20raw 3.32 / 3.39

Background quality, calibratedz +0.08 / +0.17raw 3.46 / 3.55

Overall quality, calibratedz +0.18 / +0.17raw 2.95 / 2.94

P.808 MOS estimatez +0.50 / +0.17raw 3.67 / 3.50

score content enjoymentz +1.10 / +0.97raw 4.84 / 4.80

score overall qualityz +0.38 / +0.25raw 2.84 / 2.78

Background Noisez -0.35 / +0.02raw 0.71 / 0.81

Tempo (TEMP)z -1.13 / -0.82raw 0.77 / 1.14

Arousal (AROU)z -1.21 / -0.95raw 0.98 / 1.27

Valence (VALN)z -0.61 / -0.49raw 1.65 / 1.78

Recording quality (RCQL)z +0.09 / -0.15raw 2.84 / 2.62

Background noise (BKGN)z +0.32 / +0.34raw 2.94 / 2.96

talking speedz -0.58 / -0.08raw 6.86 / 8.73

Characters per second (CPS): 14.29 raw · z +1.40

Orange speaker embedding reconstruction

Cosine against Orange on this same clip (higher means closer to that teacher vector):

Embedding	Tiny	Base
Timbre · 128D	0.787	0.839
Identity · 250D	0.764	0.843

Vocal-burst regions

Tiny

Base

0 s16.4 s

Verified burst intervals are unavailable for this clip.

Tiny: 1 regions, count-head estimate 1.02; Base: 1 regions, count-head estimate 0.91.

Exact predicted start and end times

Model	Region	Start (s)	End (s)	Duration (s)
Tiny	1	5.14	5.48	0.34
Base	1	5.18	5.48	0.30

All 192 score slots · raw and z values

#	Target	Tiny raw	Tiny z	Base raw	Base z	Train median	Train SD
Emotion scores Forty clip-level Empathic Insight emotion teacher outputs. Each row evaluates one named emotion score.
0	Affectionemo_Affection	0.127	+0.21	0.129	+0.21	0.007	0.570
1	Amusementemo_Amusement	1.322	+1.49	1.227	+1.39	-0.001	0.885
2	Angeremo_Anger	-0.077	-0.13	-0.022	-0.04	0.004	0.613
3	Astonishment Surpriseemo_Astonishment_Surprise	0.107	+0.18	-0.009	-0.03	0.005	0.572
4	Aweemo_Awe	0.002	+0.00	-0.021	-0.05	0.000	0.427
5	Bitternessemo_Bitterness	-0.022	-0.08	0.014	+0.00	0.013	0.415
6	Concentrationemo_Concentration	0.808	+0.23	0.953	+0.43	0.634	0.741
7	Confusionemo_Confusion	0.457	+0.85	0.297	+0.55	0.001	0.540
8	Contemplationemo_Contemplation	0.461	+0.63	0.672	+0.99	0.082	0.598
9	Contemptemo_Contempt	0.021	+0.05	0.062	+0.14	-0.000	0.464
10	Contentmentemo_Contentment	0.840	+1.64	0.941	+1.83	0.000	0.514
11	Disappointmentemo_Disappointment	-0.088	-0.13	0.005	+0.01	0.000	0.700
12	Disgustemo_Disgust	-0.008	-0.03	0.019	+0.02	0.007	0.489
13	Distressemo_Distress	0.307	+0.37	0.314	+0.38	0.000	0.821
14	Doubtemo_Doubt	0.514	+1.09	0.450	+0.95	0.006	0.466
15	Elationemo_Elation	0.227	+0.30	0.355	+0.47	0.012	0.728
16	Embarrassmentemo_Embarrassment	0.069	+0.06	0.028	-0.04	0.043	0.430
17	Emotional Numbnessemo_Emotional_Numbness	0.492	+0.53	0.667	+0.72	0.004	0.917
18	Fatigue Exhaustionemo_Fatigue_Exhaustion	0.754	+1.35	0.853	+1.53	0.028	0.539
19	Fearemo_Fear	1.187	+1.92	1.172	+1.90	0.015	0.610
20	Helplessnessemo_Helplessness	0.307	+0.45	0.163	+0.24	-0.004	0.696
21	Hope Enthusiasm Optimismemo_Hope_Enthusiasm_Optimism	0.475	+0.47	1.019	+1.19	0.117	0.760
22	Impatience and Irritabilityemo_Impatience_and_Irritability	0.140	-0.01	0.202	+0.07	0.149	0.705
23	Infatuationemo_Infatuation	0.016	+0.06	0.018	+0.06	-0.015	0.533
24	Interestemo_Interest	1.740	+0.17	1.945	+0.39	1.589	0.907
25	Intoxication Altered States of Consciousnessemo_Intoxication_Altered_States_of_Consciousness	0.709	+1.31	0.347	+0.67	-0.025	0.559
26	Jealousy and Envyemo_Jealousy_and_Envy	0.056	-0.01	0.053	-0.01	0.059	0.442
27	Longingemo_Longing	0.380	+0.46	0.568	+0.76	0.087	0.632
28	Malevolence Maliceemo_Malevolence_Malice	0.154	+0.18	0.088	+0.06	0.055	0.534
29	Painemo_Pain	0.059	+0.11	-0.003	-0.00	-0.002	0.579
30	Pleasure Ecstasyemo_Pleasure_Ecstasy	0.707	+1.12	0.772	+1.23	0.017	0.614
31	Prideemo_Pride	0.005	+0.01	-0.001	-0.01	0.002	0.509
32	Reliefemo_Relief	1.221	+1.74	1.046	+1.49	0.033	0.681
33	Sadnessemo_Sadness	0.256	+0.34	0.351	+0.46	0.000	0.759
34	Sexual Lustemo_Sexual_Lust	0.292	+0.53	0.281	+0.51	0.030	0.494
35	Shameemo_Shame	0.013	-0.00	0.022	+0.02	0.013	0.510
36	Sournessemo_Sourness	0.031	+0.08	0.007	+0.03	-0.005	0.439
37	Teasingemo_Teasing	1.653	+3.03	1.838	+3.37	0.000	0.545
38	Thankfulness Gratitudeemo_Thankfulness_Gratitude	0.151	+0.16	0.178	+0.20	0.041	0.697
39	Triumphemo_Triumph	0.045	+0.10	-0.010	-0.01	-0.007	0.521
VoiceNet dimensions Fifty-seven VoiceNet voice, delivery, style, and recording dimensions. Codes are expanded in the target column.
40	Perceived voice age (AGEV)vn_AGEV_reg	2.885	-0.08	2.526	-0.37	2.984	1.238
41	Arousal (AROU)vn_AROU_reg	0.976	-1.21	1.266	-0.95	2.359	1.147
42	Arousal shift (ARSH)vn_ARSH_reg	2.932	+0.41	2.911	+0.38	2.580	0.867
43	Vocal attack (ATCK)vn_ATCK_reg	0.771	-1.07	1.044	-0.86	2.162	1.295
44	Background noise (BKGN)vn_BKGN_reg	2.944	+0.32	2.962	+0.34	2.703	0.761
45	Brightness (BRGT)vn_BRGT_reg	1.277	-0.88	1.441	-0.68	1.991	0.813
46	Speech chunking (CHNK)vn_CHNK_reg	1.001	-0.68	1.181	-0.54	1.847	1.239
47	Articulation clarity (CLRT)vn_CLRT_reg	1.267	-0.79	1.600	-0.44	2.018	0.945
48	Cognitive load (COGL)vn_COGL_reg	2.298	+0.19	2.396	+0.29	2.094	1.061
49	Dynamic arc (DARC)vn_DARC_reg	1.480	-0.10	1.773	+0.11	1.615	1.380
50	Disfluency (DFLU)vn_DFLU_reg	3.147	+0.56	3.295	+0.68	2.488	1.184
51	Emphasis (EMPH)vn_EMPH_reg	2.813	+0.13	2.905	+0.20	2.607	1.524
52	Esthetics (ESTH)vn_ESTH_reg	2.138	-0.34	2.135	-0.34	2.402	0.782
53	Content appropriateness (EXPL)vn_EXPL_reg	0.500	+1.28	0.467	+1.18	0.086	0.322
54	Focus (FOCS)vn_FOCS_reg	1.993	-0.32	1.613	-0.66	2.344	1.102
55	Fullness (FULL)vn_FULL_reg	1.575	-0.23	1.684	-0.11	1.778	0.889
56	Perceived gender (GEND)vn_GEND_reg	5.387	+0.84	5.461	+0.89	4.055	1.588
57	Harmonicity (HARM)vn_HARM_reg	1.443	-1.24	1.738	-0.89	2.480	0.836
58	Metallic character (METL)vn_METL_reg	0.681	-0.98	0.880	-0.77	1.621	0.958
59	Pitch range (RANG)vn_RANG_reg	2.935	+0.02	3.226	+0.35	2.914	0.897
60	Recording quality (RCQL)vn_RCQL_reg	2.836	+0.09	2.621	-0.15	2.754	0.888
61	Vocal register (REGS)vn_REGS_reg	0.466	-0.58	0.780	-0.33	1.198	1.268
62	Respiration (RESP)vn_RESP_reg	3.390	+0.67	3.298	+0.59	2.680	1.056
63	Roughness (ROUG)vn_ROUG_reg	2.650	+0.70	2.250	+0.24	2.033	0.887
64	Chest resonance (R_CHST)vn_R_CHST_reg	2.582	+0.53	2.448	+0.37	2.135	0.844
65	Head resonance (R_HEAD)vn_R_HEAD_reg	1.616	-0.65	1.876	-0.33	2.148	0.822
66	Mask resonance (R_MASK)vn_R_MASK_reg	1.367	-0.54	1.640	-0.27	1.908	1.005
67	Mixed resonance (R_MIXD)vn_R_MIXD_reg	1.349	-0.10	1.257	-0.21	1.436	0.841
68	Nasal resonance (R_NASL)vn_R_NASL_reg	1.666	-1.07	2.177	-0.59	2.791	1.047
69	Oral resonance (R_ORAL)vn_R_ORAL_reg	1.574	-0.82	1.758	-0.57	2.184	0.741
70	Throat resonance (R_THRT)vn_R_THRT_reg	0.973	-1.37	1.093	-1.22	2.070	0.803
71	Smoothness (SMTH)vn_SMTH_reg	1.709	-0.40	1.299	-0.77	2.143	1.093
72	Stance (STNC)vn_STNC_reg	2.116	-0.45	2.194	-0.39	2.633	1.137
73	Speech structure (STRU)vn_STRU_reg	1.419	-0.75	1.478	-0.69	2.137	0.958
74	ASMR style (S_ASMR)vn_S_ASMR_reg	2.438	+0.76	2.082	+0.50	1.370	1.411
75	Authoritative style (S_AUTH)vn_S_AUTH_reg	1.006	-0.08	1.252	+0.16	1.088	1.043
76	Cartoonish style (S_CART)vn_S_CART_reg	3.166	+1.15	2.952	+0.99	1.560	1.401
77	Casual style (S_CASU)vn_S_CASU_reg	2.988	-0.63	3.197	-0.47	3.793	1.278
78	Conversational style (S_CONV)vn_S_CONV_reg	2.835	+0.18	3.046	+0.34	2.594	1.318
79	Dramatic style (S_DRAM)vn_S_DRAM_reg	3.220	+0.43	3.284	+0.49	2.721	1.148
80	Formal style (S_FORM)vn_S_FORM_reg	1.009	-0.18	1.098	-0.10	1.195	1.021
81	Monologue style (S_MONO)vn_S_MONO_reg	3.491	+0.52	3.357	+0.41	2.824	1.284
82	Narrator style (S_NARR)vn_S_NARR_reg	3.224	+1.33	2.955	+1.14	1.307	1.446
83	Newsreader style (S_NEWS)vn_S_NEWS_reg	0.429	+0.04	0.429	+0.04	0.408	0.568
84	Playful style (S_PLAY)vn_S_PLAY_reg	2.761	+0.31	2.954	+0.46	2.352	1.315
85	Ranting or angry style (S_RANT)vn_S_RANT_reg	1.520	+0.24	1.362	+0.12	1.213	1.289
86	Storytelling style (S_STRY)vn_S_STRY_reg	3.305	+0.60	3.039	+0.41	2.480	1.366
87	Teacher or didactic style (S_TECH)vn_S_TECH_reg	1.851	+0.98	1.994	+1.10	0.646	1.227
88	Whispered talking style (S_WHIS)vn_S_WHIS_reg	2.697	+0.68	2.363	+0.47	1.597	1.618
89	Tempo (TEMP)vn_TEMP_reg	0.774	-1.13	1.139	-0.82	2.117	1.190
90	Tension (TENS)vn_TENS_reg	2.066	+0.60	2.102	+0.64	1.559	0.852
91	Valence (VALN)vn_VALN_reg	1.645	-0.61	1.784	-0.49	2.328	1.118
92	Valence shift (VALS)vn_VALS_reg	2.050	-0.43	2.071	-0.41	2.518	1.079
93	Velocity flux (VFLX)vn_VFLX_reg	-0.084	-1.94	0.161	-1.73	2.256	1.208
94	Volatility (VOLT)vn_VOLT_reg	3.621	+1.17	3.560	+1.10	2.586	0.886
95	Vulnerability (VULN)vn_VULN_reg	3.313	+0.67	3.545	+0.91	2.648	0.984
96	Warmth (WARM)vn_WARM_reg	3.242	+0.73	2.998	+0.46	2.578	0.909
Genuineness, blend, and legacy quality Genuineness and vocal-burst blend are predicted. R_quality has Ladder training labels but no valid P3 test labels.
97	Genuineness (0–6)genuineness_0_6	1.978	-0.22	2.085	-0.15	2.332	1.621
98	Vocal-burst blend (0–10)blend_0_10	1.994	-1.71	2.376	-1.57	6.676	2.738
99	Legacy R_quality (no P3 test labels)R_quality	0.549	-1.62	0.601	-1.46	1.095	0.338
Empathic Insight Plus extra scores Nineteen additional clip-level teacher scores, including background noise and content enjoyment.
100	Ageeiv_extra:Age	2.976	-0.94	2.545	-2.41	3.250	0.293
101	Arousaleiv_extra:Arousal	1.413	+0.29	1.567	+0.64	1.289	0.435
102	Authenticityeiv_extra:Authenticity	2.717	+0.32	2.746	+0.52	2.667	0.153
103	Background Noiseeiv_extra:Background_Noise	0.714	-0.35	0.813	+0.02	0.808	0.264
104	Confident vs. Hesitanteiv_extra:Confident_vs._Hesitant	1.118	+0.26	1.220	+0.59	1.040	0.303
105	Gendereiv_extra:Gender	-0.372	+0.25	-0.207	+0.41	-0.621	0.999
106	High-Pitched vs. Low-Pitchedeiv_extra:High-Pitched_vs._Low-Pitched	1.717	-0.44	1.751	-0.31	1.827	0.250
107	Monotone vs. Expressiveeiv_extra:Monotone_vs._Expressive	1.886	+0.06	2.043	+0.39	1.859	0.470
108	Recording Qualityeiv_extra:Recording_Quality	2.195	+0.15	2.215	+0.21	2.144	0.332
109	Serious vs. Humorouseiv_extra:Serious_vs._Humorous	1.083	+0.45	1.142	+0.62	0.929	0.340
110	Soft vs. Harsheiv_extra:Soft_vs._Harsh	0.492	+0.66	0.698	+1.30	0.281	0.320
111	Submissive vs. Dominanteiv_extra:Submissive_vs._Dominant	0.277	-0.30	0.316	-0.18	0.376	0.324
112	Valenceeiv_extra:Valence	0.148	+0.38	0.477	+1.24	0.005	0.380
113	Vulnerable vs. Emotionally Detachedeiv_extra:Vulnerable_vs._Emotionally_Detached	1.482	-0.53	1.493	-0.51	1.715	0.437
114	Warm vs. Coldeiv_extra:Warm_vs._Cold	0.400	+1.16	0.484	+1.44	0.051	0.300
115	score background qualityeiv_extra:score_background_quality	3.396	+0.14	3.396	+0.14	3.301	0.693
116	score content enjoymenteiv_extra:score_content_enjoyment	4.840	+1.10	4.802	+0.97	4.507	0.303
117	score overall qualityeiv_extra:score_overall_quality	2.842	+0.38	2.777	+0.25	2.652	0.507
118	score speech qualityeiv_extra:score_speech_quality	1.721	-0.59	1.718	-0.62	1.808	0.146
Meta AudioBox Aesthetics Four AudioBox aesthetic teacher outputs. Expansions follow the official Meta model card.
119	Content enjoyment (CE)audiobox:CE	5.614	+0.80	5.614	+0.80	4.799	1.018
120	Content usefulness (CU)audiobox:CU	6.514	+0.86	6.713	+1.06	5.649	1.001
121	Production complexity (PC)audiobox:PC	2.753	+0.26	2.824	+0.30	2.331	1.617
122	Production quality (PQ)audiobox:PQ	7.754	+0.81	7.596	+0.63	7.044	0.879
Microsoft DNSMOS Seven DNSMOS teacher outputs: raw and calibrated SIG/BAK/OVRL estimates plus P.808 MOS.
123	Speech signal quality, rawdnsmos:SIG_raw	3.750	-0.22	3.781	-0.18	3.900	0.669
124	Background quality, rawdnsmos:BAK_raw	3.472	+0.23	3.643	+0.38	3.211	1.124
125	Overall quality, rawdnsmos:OVRL_raw	3.297	+0.26	3.302	+0.27	3.085	0.812
126	Speech signal quality, calibrateddnsmos:SIG	3.315	-0.35	3.388	-0.20	3.488	0.501
127	Background quality, calibrateddnsmos:BAK	3.462	+0.08	3.546	+0.17	3.389	0.928
128	Overall quality, calibrateddnsmos:OVRL	2.946	+0.18	2.943	+0.17	2.840	0.606
129	P.808 MOS estimatednsmos:P808_MOS	3.671	+0.50	3.505	+0.17	3.421	0.496
Vocal-burst count The regression target is log(1 + count). A separate table also reports count error after inverse transformation.
130	Vocal-burst count, log(1 + count)burst_count_log1p	0.705	+1.09	0.646	+1.00	0.000	0.647
VoiceCLAP attributes Sixty-one individual VoiceCLAP attribute teacher scores. The raw 768D VoiceCLAP embedding is stored in sidecars but is not a model output.
131	Affectionvoiceclap_attribute:Affection	0.779	-0.30	0.643	-0.55	0.947	0.554
132	Agevoiceclap_attribute:Age	2.491	-1.35	2.518	-1.30	3.229	0.547
133	Amusementvoiceclap_attribute:Amusement	1.276	+1.55	0.877	+0.85	0.392	0.572
134	Angervoiceclap_attribute:Anger	0.868	-0.25	0.961	-0.06	0.992	0.506
135	Arousalvoiceclap_attribute:Arousal	1.638	+0.35	1.644	+0.36	1.420	0.622
136	Astonishment Surprisevoiceclap_attribute:Astonishment_Surprise	1.216	+1.48	1.122	+1.28	0.509	0.479
137	Authenticityvoiceclap_attribute:Authenticity	2.699	-0.43	2.832	+0.37	2.770	0.167
138	Awevoiceclap_attribute:Awe	0.353	-0.72	0.416	-0.47	0.539	0.259
139	Background Noisevoiceclap_attribute:Background_Noise	0.690	+0.47	0.786	+0.83	0.567	0.264
140	Bitternessvoiceclap_attribute:Bitterness	0.492	-0.42	0.602	+0.04	0.592	0.236
141	Concentrationvoiceclap_attribute:Concentration	0.690	-0.99	0.827	-0.73	1.214	0.531
142	Confident vs. Hesitantvoiceclap_attribute:Confident_vs._Hesitant	0.914	-0.33	0.764	-0.65	1.069	0.468
143	Confusionvoiceclap_attribute:Confusion	0.963	+0.96	0.829	+0.56	0.643	0.334
144	Contemplationvoiceclap_attribute:Contemplation	0.563	-0.54	0.366	-1.02	0.780	0.406
145	Contemptvoiceclap_attribute:Contempt	0.778	+0.21	0.574	-0.40	0.709	0.339
146	Contentmentvoiceclap_attribute:Contentment	0.437	-0.49	0.639	+0.17	0.588	0.307
147	Disappointmentvoiceclap_attribute:Disappointment	0.690	-0.24	0.762	+0.01	0.760	0.291
148	Disgustvoiceclap_attribute:Disgust	0.765	+0.68	0.794	+0.82	0.625	0.207
149	Distressvoiceclap_attribute:Distress	1.000	+0.21	1.137	+0.60	0.927	0.350
150	Doubtvoiceclap_attribute:Doubt	0.484	-0.27	0.465	-0.37	0.535	0.188
151	Elationvoiceclap_attribute:Elation	0.573	+0.08	0.587	+0.12	0.539	0.397
152	Embarrassmentvoiceclap_attribute:Embarrassment	0.412	+0.34	0.221	-0.27	0.307	0.314
153	Emotional Numbnessvoiceclap_attribute:Emotional_Numbness	0.702	+0.14	0.563	-0.38	0.664	0.266
154	Fatigue Exhaustionvoiceclap_attribute:Fatigue_Exhaustion	0.471	+0.04	0.471	+0.04	0.462	0.261
155	Fearvoiceclap_attribute:Fear	1.005	+1.82	1.009	+1.84	0.618	0.212
156	Gendervoiceclap_attribute:Gender	-0.009	+0.14	0.213	+0.36	-0.151	1.005
157	Helplessnessvoiceclap_attribute:Helplessness	0.840	+0.68	0.928	+1.01	0.658	0.268
158	High-Pitched vs. Low-Pitchedvoiceclap_attribute:High-Pitched_vs._Low-Pitched	1.567	-0.73	1.553	-0.77	1.840	0.375
159	Hope Enthusiasm Optimismvoiceclap_attribute:Hope_Enthusiasm_Optimism	0.412	-0.74	0.605	-0.25	0.705	0.396
160	Impatience and Irritabilityvoiceclap_attribute:Impatience_and_Irritability	0.709	-0.63	0.796	-0.47	1.052	0.541
161	Infatuationvoiceclap_attribute:Infatuation	0.724	+0.35	0.572	-0.11	0.608	0.332
162	Interestvoiceclap_attribute:Interest	1.762	+0.37	1.686	+0.20	1.598	0.440
163	Intoxication Altered States of Consciousnessvoiceclap_attribute:Intoxication_Altered_States_of_Consciousness	1.264	+1.64	0.921	+0.90	0.502	0.463
164	Jealousy & Envyvoiceclap_attribute:Jealousy_&_Envy	0.698	+0.72	0.668	+0.59	0.523	0.245
165	Longingvoiceclap_attribute:Longing	0.398	-0.64	0.362	-0.80	0.538	0.220
166	Malevolence Malicevoiceclap_attribute:Malevolence_Malice	1.172	+0.98	1.012	+0.52	0.833	0.346
167	Monotone vs. Expressivevoiceclap_attribute:Monotone_vs._Expressive	1.583	-0.32	1.613	-0.27	1.775	0.594
168	Painvoiceclap_attribute:Pain	0.622	+1.10	0.707	+1.49	0.381	0.218
169	Pleasure Ecstasyvoiceclap_attribute:Pleasure_Ecstasy	0.652	+0.49	0.556	+0.18	0.503	0.301
170	Pridevoiceclap_attribute:Pride	0.626	-0.44	0.634	-0.42	0.780	0.349
171	Recording Qualityvoiceclap_attribute:Recording_Quality	2.203	-0.34	2.213	-0.31	2.313	0.328
172	Reliefvoiceclap_attribute:Relief	1.238	+0.52	1.456	+1.04	1.025	0.415
173	Sadnessvoiceclap_attribute:Sadness	0.660	-0.29	0.779	+0.09	0.752	0.313
174	Serious vs. Humorousvoiceclap_attribute:Serious_vs._Humorous	1.394	+1.04	1.079	+0.48	0.803	0.568
175	Sexual Lustvoiceclap_attribute:Sexual_Lust	1.136	+1.20	0.804	+0.40	0.635	0.419
176	Shamevoiceclap_attribute:Shame	0.373	-0.54	0.577	+0.18	0.526	0.283
177	Soft vs. Harshvoiceclap_attribute:Soft_vs._Harsh	0.396	+0.66	0.212	+0.15	0.160	0.360
178	Sournessvoiceclap_attribute:Sourness	0.601	-0.36	0.639	-0.23	0.706	0.291
179	Submissive vs. Dominantvoiceclap_attribute:Submissive_vs._Dominant	0.343	-0.78	0.336	-0.80	0.623	0.359
180	Teasingvoiceclap_attribute:Teasing	1.580	+2.74	1.065	+1.38	0.540	0.379
181	Thankfulness Gratitudevoiceclap_attribute:Thankfulness_Gratitude	1.241	-0.27	1.323	-0.11	1.384	0.529
182	Triumphvoiceclap_attribute:Triumph	1.068	+0.98	1.129	+1.15	0.716	0.359
183	Valencevoiceclap_attribute:Valence	0.240	+0.39	-0.024	-0.03	-0.007	0.635
184	Vulnerable vs. Emotionally Detachedvoiceclap_attribute:Vulnerable_vs._Emotionally_Detached	1.357	-0.51	1.408	-0.41	1.638	0.556
185	Warm vs. Coldvoiceclap_attribute:Warm_vs._Cold	0.152	+0.55	0.008	+0.19	-0.066	0.400
186	durationvoiceclap_attribute:duration	17.128	+0.98	17.128	+0.98	10.914	6.354
187	score background qualityvoiceclap_attribute:score_background_quality	3.456	+0.42	3.624	+0.76	3.245	0.498
188	score content enjoymentvoiceclap_attribute:score_content_enjoyment	4.907	+1.71	4.920	+1.80	4.656	0.147
189	score overall qualityvoiceclap_attribute:score_overall_quality	2.797	+0.39	2.878	+0.59	2.635	0.412
190	score speech qualityvoiceclap_attribute:score_speech_quality	1.891	-0.00	1.928	+0.53	1.891	0.069
191	talking speedvoiceclap_attribute:talking_speed	6.858	-0.58	8.727	-0.08	9.028	3.756

All Orange embedding components

The cosine above is the meaningful vector-level comparison; component values have no standalone semantic label.

Timbre — all 128 vector components

Dimension	Tiny	Base	Orange teacher
0	0.0421	0.0762	0.0727
1	-0.0208	-0.1238	-0.0892
2	0.2032	0.1903	0.0704
3	0.0231	-0.0174	0.0320
4	0.0851	0.0493	-0.0440
5	-0.0446	-0.0905	-0.1136
6	0.0842	0.1070	0.0800
7	-0.0723	-0.0674	-0.0822
8	-0.0508	0.0256	0.0238
9	-0.0387	-0.0130	0.0228
10	0.2051	0.2307	0.1564
11	-0.0677	-0.0947	-0.1050
12	0.0423	0.0151	0.0289
13	0.0063	-0.0090	-0.0141
14	0.1309	0.0720	0.0296
15	-0.1167	-0.1238	-0.0804
16	-0.0838	-0.1137	-0.1111
17	-0.0405	-0.0564	-0.0933
18	-0.0865	-0.1027	-0.0828
19	0.1337	0.0320	0.0324
20	-0.0916	-0.0985	-0.0899
21	-0.0090	-0.0082	0.0358
22	0.2124	0.1945	0.2688
23	0.0113	0.0364	0.0744
24	-0.0641	-0.0115	-0.0381
25	-0.0737	-0.0901	-0.0789
26	-0.0714	-0.0568	-0.0842
27	-0.0943	-0.0594	-0.0837
28	-0.0081	0.0249	0.0421
29	0.0462	0.0943	0.0404
30	-0.1611	-0.1044	-0.0966
31	0.0391	-0.0535	-0.0198
32	0.1730	0.2409	0.1849
33	-0.1140	-0.0893	-0.0989
34	-0.0851	-0.0392	-0.0805
35	-0.1199	-0.0459	-0.0501
36	0.0574	0.0167	0.0277
37	-0.0760	-0.1095	-0.1063
38	0.0401	-0.0392	-0.0753
39	0.0737	0.0644	0.0214
40	-0.0256	-0.0314	-0.0865
41	-0.0259	-0.0602	0.0089
42	0.0574	0.0438	0.0891
43	-0.0929	-0.0556	-0.0923
44	-0.1172	-0.0821	-0.0862
45	0.0522	0.0347	-0.0009
46	-0.0394	0.0201	-0.0142
47	0.0508	0.0745	0.0584
48	-0.0536	-0.1145	-0.0876
49	-0.0035	-0.0486	0.0267
50	-0.0165	-0.0474	-0.0199
51	0.0952	0.0821	0.0831
52	-0.0451	-0.0328	-0.1020
53	-0.0719	-0.0884	-0.0916
54	-0.1282	-0.2089	-0.1005
55	-0.0513	-0.0859	-0.0864
56	0.0046	-0.0459	-0.0784
57	-0.0829	-0.1314	-0.0984
58	0.0391	-0.0322	-0.0147
59	-0.0298	-0.0503	0.0411
60	-0.0068	-0.0023	-0.0866
61	0.0538	0.0792	0.1005
62	0.0700	0.1600	0.2194
63	-0.1511	-0.1752	-0.0853
64	-0.0008	0.0179	0.0015
65	0.1428	0.0619	0.1176
66	0.1538	0.1297	0.0141
67	0.2582	0.2190	0.2749
68	0.0140	0.0276	0.0356
69	0.1694	0.0964	0.1219
70	-0.0948	-0.0585	-0.0930
71	-0.0522	-0.0733	-0.0995
72	0.2252	0.2173	0.2263
73	0.0636	0.0072	0.0071
74	-0.0437	-0.0451	0.0326
75	0.0332	0.0045	-0.0352
76	-0.0861	-0.0994	-0.0871
77	-0.1126	-0.1086	-0.0820
78	0.0346	0.0143	-0.0202
79	-0.0038	-0.0095	-0.0385
80	0.1208	0.0552	0.1752
81	0.0199	0.0990	0.0790
82	0.0251	0.0172	-0.0233
83	0.0998	0.0897	0.1032
84	0.0645	0.0411	0.0652
85	-0.0269	-0.0058	0.0596
86	0.0396	-0.0318	-0.0259
87	-0.0700	-0.0703	-0.0908
88	0.0229	0.0101	0.0427
89	-0.0336	-0.0278	-0.0671
90	0.0774	0.0295	0.0291
91	-0.0938	-0.0851	-0.0825
92	0.2243	0.1373	0.0998
93	-0.0980	-0.1482	-0.0878
94	-0.0137	-0.0276	0.0419
95	-0.0584	-0.1322	-0.0964
96	-0.1048	-0.0888	-0.0930
97	-0.0742	-0.1048	-0.0665
98	-0.0796	-0.0872	-0.0890
99	0.0595	0.0249	0.0029
100	0.0911	0.0352	0.1849
101	0.0520	0.1023	0.0477
102	0.1483	0.1625	0.0787
103	0.1831	0.0931	0.1012
104	0.0256	0.0615	0.0914
105	0.0373	-0.0085	0.0792
106	0.0330	0.0042	0.0053
107	0.0403	-0.0149	0.0002
108	0.0256	0.0436	0.0921
109	-0.0314	-0.0779	-0.0030
110	0.0449	0.0728	-0.0704
111	0.0673	0.0476	-0.0072
112	-0.0251	-0.0260	-0.0885
113	-0.0481	-0.0079	-0.0064
114	0.0120	0.1583	0.0180
115	-0.0227	-0.0206	-0.0851
116	-0.0341	-0.0678	-0.0770
117	-0.0336	0.1112	0.1434
118	-0.0012	-0.0585	-0.0874
119	-0.1131	-0.0952	-0.0868
120	0.0526	0.0716	0.1052
121	-0.0057	-0.0297	0.0162
122	-0.0151	-0.0202	-0.0462
123	-0.0506	-0.0257	0.0481
124	0.0221	-0.0472	-0.0908
125	-0.1172	-0.0539	-0.0895
126	-0.0323	-0.0227	-0.0774
127	-0.1566	-0.1347	-0.0953

Identity — all 250 vector components

Dimension	Tiny	Base	Orange teacher
0	-0.0266	-0.0530	-0.0444
1	-0.0803	-0.0484	-0.0390
2	-0.0126	0.0204	-0.0293
3	0.0522	-0.0463	-0.0314
4	-0.1000	-0.0766	-0.0367
5	-0.0613	-0.0168	0.0486
6	-0.0017	0.0791	0.0067
7	0.1926	0.1257	0.1378
8	0.0704	0.0638	0.0704
9	0.0051	0.0193	-0.0013
10	-0.0012	0.0748	0.0497
11	-0.0624	-0.0494	-0.0546
12	-0.1043	-0.0635	-0.0441
13	0.1394	0.1085	0.0728
14	-0.0482	-0.0846	-0.0575
15	0.2583	0.1913	0.1976
16	0.0653	0.0650	0.0530
17	-0.0270	0.0118	-0.0484
18	0.0992	0.0181	0.0919
19	-0.0916	-0.0745	-0.0640
20	0.0018	-0.0512	-0.0404
21	-0.0496	-0.0330	-0.0374
22	0.0146	-0.0101	-0.0113
23	-0.0012	-0.0466	-0.0390
24	-0.0405	-0.0277	-0.0344
25	-0.0522	-0.0182	0.0068
26	-0.0123	0.0840	0.0611
27	-0.0281	-0.0583	-0.0328
28	-0.0077	-0.0075	-0.0436
29	-0.0312	-0.0570	-0.0388
30	-0.0401	-0.0521	-0.0351
31	0.0452	-0.0616	-0.0507
32	0.0334	0.0714	0.0203
33	0.0697	0.1717	0.1608
34	-0.1065	-0.0589	-0.0482
35	0.0001	-0.0320	-0.0519
36	-0.0327	-0.0277	-0.0426
37	-0.0093	-0.0018	-0.0279
38	-0.0660	-0.0684	-0.0559
39	-0.0201	-0.0671	-0.0193
40	-0.0544	-0.0423	-0.0467
41	-0.0023	0.0162	-0.0463
42	0.0323	0.0405	0.0412
43	0.0352	0.0342	0.0252
44	-0.0023	0.0322	-0.0133
45	0.0085	-0.0319	-0.0463
46	-0.0500	-0.0576	-0.0592
47	-0.0379	-0.0302	-0.0487
48	-0.0241	-0.0126	-0.0430
49	-0.0719	0.0241	0.0178
50	0.0544	0.0671	0.0775
51	-0.0303	0.0760	0.0250
52	-0.0558	-0.0702	-0.0398
53	0.0598	0.0665	0.0221
54	0.0024	0.0205	0.0217
55	0.0843	0.0708	0.0488
56	0.0164	-0.0100	0.0681
57	-0.0365	0.0057	-0.0018
58	0.0330	-0.0111	-0.0387
59	0.0985	0.0497	0.0618
60	0.1022	0.1042	0.1578
61	0.0642	0.0558	0.0305
62	-0.0398	0.0092	-0.0354
63	0.0097	0.0153	0.0528
64	0.0016	0.0221	-0.0449
65	-0.0985	-0.0714	-0.0492
66	0.0704	0.0622	0.0383
67	-0.0081	0.0379	-0.0017
68	0.0283	0.0224	0.0194
69	0.0872	0.0610	0.0734
70	-0.0452	-0.0742	-0.0585
71	-0.0409	-0.0822	-0.0422
72	-0.0500	-0.0675	-0.0447
73	-0.0367	-0.0288	-0.0720
74	-0.0432	-0.0435	-0.0435
75	-0.0254	-0.0180	0.0017
76	-0.0396	-0.0733	-0.0384
77	0.0077	-0.0549	-0.0221
78	-0.0071	0.0242	0.0311
79	0.0949	0.0478	0.0365
80	-0.0471	-0.0668	-0.0428
81	0.0978	0.1055	0.0378
82	0.1335	0.1049	0.1763
83	-0.0345	-0.0320	-0.0358
84	0.0675	0.0297	0.0407
85	-0.0396	-0.0441	-0.0066
86	-0.0821	-0.0561	-0.0385
87	0.0098	-0.0274	-0.0344
88	0.0901	0.1079	0.0659
89	0.0595	0.0671	0.0216
90	0.0317	0.0877	0.0425
91	0.0056	-0.0199	-0.0356
92	-0.0432	-0.0696	-0.0372
93	-0.0460	0.0091	-0.0489
94	0.0001	-0.0084	0.0222
95	0.1824	0.1705	0.0784
96	0.0485	0.0576	0.0273
97	-0.0337	-0.0227	-0.0176
98	0.1233	0.0981	0.0295
99	-0.0139	-0.0475	-0.0539
100	0.0770	0.0950	0.1249
101	0.0613	0.0506	-0.0228
102	0.0058	-0.0032	0.0152
103	-0.0142	-0.0244	-0.0712
104	-0.0002	-0.0366	-0.0437
105	-0.0722	-0.0763	-0.0560
106	-0.0503	-0.0503	-0.0332
107	0.0719	0.0262	-0.0131
108	-0.0518	-0.0273	-0.0320
109	0.0883	0.1680	0.1503
110	-0.0573	-0.0414	-0.0513
111	0.0058	-0.0035	-0.0200
112	-0.0272	-0.0238	-0.0348
113	-0.0766	-0.0742	-0.0648
114	0.0436	0.0595	0.1107
115	0.0401	-0.0035	-0.0305
116	0.0178	0.0248	-0.0412
117	-0.0144	-0.0058	-0.0339
118	-0.1167	-0.1049	-0.0562
119	0.0555	0.1337	0.1693
120	-0.0109	0.0247	-0.0376
121	-0.0171	-0.0466	-0.0367
122	0.0135	-0.0027	-0.0406
123	0.0963	0.1128	0.1555
124	-0.0156	-0.0451	-0.0429
125	-0.1306	-0.0675	-0.0418
126	-0.0392	-0.0231	-0.0429
127	-0.0562	-0.0834	-0.0443
128	-0.0199	0.0103	0.0283
129	-0.0317	-0.0487	-0.0457
130	-0.0208	0.0205	-0.0432
131	-0.0500	-0.0385	-0.0377
132	-0.0281	-0.0284	-0.0457
133	-0.0296	0.0177	0.0328
134	-0.0266	0.0239	0.0494
135	-0.0029	0.0647	0.0347
136	-0.0015	0.0126	-0.0461
137	-0.0522	-0.0213	-0.0400
138	-0.0744	-0.0675	-0.0380
139	0.0496	0.0176	-0.0164
140	0.0129	0.0132	0.1018
141	-0.0212	-0.0227	-0.0426
142	-0.0390	-0.0328	-0.0372
143	-0.1036	-0.0586	-0.0587
144	-0.0204	-0.0327	-0.0449
145	-0.0682	-0.0524	-0.0547
146	-0.0576	0.0299	-0.0022
147	-0.0100	-0.0146	-0.0016
148	0.0213	0.0328	-0.0474
149	0.0828	0.1404	0.1710
150	0.0188	-0.0071	-0.0424
151	0.0806	0.0619	0.0782
152	0.0412	0.0093	-0.0423
153	0.0565	0.0757	0.0718
154	0.0595	0.0803	0.0978
155	0.0440	0.0247	-0.0533
156	0.0135	-0.0136	-0.0431
157	0.0034	0.0589	-0.0137
158	-0.0440	-0.0108	-0.0388
159	-0.0660	-0.0858	-0.0504
160	0.0558	0.1275	0.2253
161	-0.0941	-0.0322	-0.0277
162	-0.0055	-0.0368	-0.0500
163	-0.0664	-0.0714	-0.0479
164	0.0341	0.0026	-0.0378
165	-0.0387	-0.0198	-0.0277
166	0.0348	0.0926	-0.0107
167	0.0843	-0.0182	-0.0288
168	-0.0522	-0.0629	-0.0609
169	-0.0887	-0.0021	-0.0491
170	-0.0279	-0.0262	-0.0403
171	0.0104	0.0399	-0.0049
172	-0.0642	-0.0215	-0.0499
173	0.0263	0.0641	0.0217
174	-0.0482	-0.0926	-0.0442
175	-0.0956	-0.1036	-0.0713
176	-0.0624	-0.0644	-0.0366
177	-0.0376	-0.0333	-0.0355
178	0.1569	0.1729	0.1722
179	0.1043	0.1036	0.0551
180	-0.0343	0.0014	-0.0022
181	-0.0223	0.0013	0.0347
182	0.0303	0.0478	0.0084
183	-0.0098	-0.0478	-0.0338
184	-0.0182	-0.0213	-0.0437
185	-0.0540	-0.0299	-0.0515
186	-0.0653	-0.0552	-0.0519
187	-0.0113	0.0033	-0.0144
188	0.0021	0.0616	0.0786
189	0.0059	0.0494	0.0336
190	0.0638	0.0950	0.0682
191	-0.0190	-0.0330	-0.0132
192	-0.0503	-0.0445	-0.0521
193	0.1547	0.1110	0.1465
194	-0.0257	-0.0451	-0.0558
195	-0.0248	-0.0009	-0.0191
196	0.0431	0.0293	-0.0279
197	-0.0781	0.0012	-0.0432
198	-0.0272	-0.0130	-0.0358
199	-0.0573	-0.0363	0.0047
200	-0.0770	-0.0647	-0.0497
201	0.0737	0.0733	0.0622
202	-0.0078	-0.0082	-0.0891
203	0.0010	-0.0051	0.0096
204	0.0792	0.1141	0.1306
205	0.1087	0.0987	0.1039
206	0.0405	0.0463	-0.0118
207	0.0693	-0.0009	0.0309
208	-0.0259	0.0037	0.0031
209	-0.0172	0.0216	0.0027
210	0.1313	0.2293	0.1411
211	-0.0131	-0.0134	-0.0331
212	0.0934	0.0527	0.0502
213	0.1160	0.1122	0.0950
214	0.1321	0.1367	0.1581
215	-0.0169	0.0041	-0.0362
216	0.0970	0.1680	0.1172
217	0.0350	0.0089	-0.0232
218	0.1058	0.0607	0.1316
219	-0.0872	-0.0684	-0.0560
220	-0.0693	-0.0653	-0.0475
221	-0.0533	-0.0173	-0.0373
222	-0.0151	0.0007	0.0559
223	-0.0443	0.0104	-0.0044
224	0.0547	0.0264	0.0224
225	0.0202	0.0650	0.0152
226	0.1321	0.0828	0.1364
227	-0.0598	-0.0690	-0.0569
228	-0.1116	-0.0757	-0.0696
229	0.0200	0.0733	0.0019
230	-0.0096	-0.0001	-0.0438
231	-0.0529	-0.0311	-0.0595
232	-0.0235	-0.0742	-0.0591
233	-0.0237	-0.0256	-0.0613
234	-0.0288	-0.0402	-0.0365
235	0.1022	0.1055	0.1379
236	-0.0142	0.0063	0.0052
237	-0.0122	-0.0095	-0.0439
238	0.0055	0.0270	0.0217
239	-0.0361	-0.0299	-0.0445
240	-0.0434	-0.0540	-0.0439
241	0.0409	0.0797	0.1390
242	-0.0540	-0.0396	-0.0634
243	-0.0544	-0.0319	-0.0553
244	0.0339	-0.0043	-0.0457
245	0.1532	0.1036	0.1313
246	-0.0576	-0.0840	-0.0349
247	-0.0100	-0.0189	-0.0362
248	-0.0462	-0.0647	-0.0492
249	0.1022	0.0221	0.0276

Source: M2_RECENT_DPO_LORA_SPEAKER_EMOTION_STUDY_2026-10-02.html · SHA-256 b4f234db7c315319…

g05EnglishMediathek voice study

mediathek_0047 · en · 1/50

Generated TTS prediction · Rank 2 qkvo · 7.6 s

We really need to make these legal ideas about getting along more solid. It is crucial to get concrete about these principles of coexistence.

Tiny Base · values are model estimates, not ground truth

Strongest emotions relative to training

Concentration

z +1.67 / +1.90raw 1.87 / 2.05

Contemplation

z +1.82 / +1.43raw 1.17 / 0.94

Contempt

z +1.63 / +1.22raw 0.76 / 0.56

Sourness

z +1.47 / +1.32raw 0.64 / 0.57

Impatience and Irritability

z +1.39 / +1.33raw 1.13 / 1.09

Disgust

z +1.27 / +0.55raw 0.63 / 0.28

Anger

z +1.23 / +1.10raw 0.75 / 0.68

The center of each bar is the S9 teacher median. Positive z is to the right; negative z is to the left. Ranking uses z, not raw teacher units.

Strongest VoiceNet dimensions relative to training

Newsreader style (S_NEWS)

z +2.46 / +3.05raw 1.80 / 2.14

Authoritative style (S_AUTH)

z +1.73 / +1.77raw 2.89 / 2.93

Content appropriateness (EXPL)

z +1.29 / +1.37raw 0.50 / 0.53

Speech chunking (CHNK)

z +1.14 / +1.11raw 3.26 / 3.23

Tempo (TEMP)

z +1.10 / +1.05raw 3.43 / 3.37

Metallic character (METL)

z +0.98 / +0.86raw 2.56 / 2.45

Speech structure (STRU)

z +0.78 / +0.96raw 2.88 / 3.06

All 57 VoiceNet predictions, including raw units, are in the full table below. These seven are ranked by z; the top values may differ from the strongest raw dimensions.

Voice, speed and quality scores in context

Genuineness (0–6)z +0.04 / -0.30raw 2.40 / 1.85

Vocal-burst blend (0–10)z -0.87 / -1.03raw 4.29 / 3.86

Content enjoyment (CE)z +0.71 / +0.96raw 5.53 / 5.78

Production quality (PQ)z +0.28 / +0.08raw 7.29 / 7.12

Speech signal quality, calibratedz +0.19 / +0.15raw 3.59 / 3.57

Background quality, calibratedz +0.57 / +0.65raw 3.92 / 3.99

Overall quality, calibratedz +0.61 / +0.63raw 3.21 / 3.22

P.808 MOS estimatez +0.84 / +0.76raw 3.84 / 3.80

score content enjoymentz +0.62 / +1.00raw 4.69 / 4.81

score overall qualityz +0.55 / +0.63raw 2.93 / 2.97

Background Noisez -1.34 / -2.03raw 0.45 / 0.27

Tempo (TEMP)z +1.10 / +1.05raw 3.43 / 3.37

Arousal (AROU)z +0.36 / +0.29raw 2.77 / 2.69

Valence (VALN)z +0.33 / +0.09raw 2.70 / 2.43

Recording quality (RCQL)z -0.53 / -0.43raw 2.28 / 2.37

Background noise (BKGN)z +0.04 / -0.01raw 2.74 / 2.70

talking speedz +3.18 / +3.38raw 20.97 / 21.74

Characters per second (CPS): 18.47 raw · z +2.52

Orange speaker embedding reconstruction

Cosine against Orange on this same clip (higher means closer to that teacher vector):

Embedding	Tiny	Base
Timbre · 128D	0.883	0.897
Identity · 250D	0.683	0.707

Vocal-burst regions

Tiny

Base

0 s7.6 s

Verified burst intervals are unavailable for this clip.

Tiny: 0 regions, count-head estimate 0.01; Base: 0 regions, count-head estimate 0.00.

Exact predicted start and end times

Model	Region	Start (s)	End (s)	Duration (s)

All 192 score slots · raw and z values

#	Target	Tiny raw	Tiny z	Base raw	Base z	Train median	Train SD
Emotion scores Forty clip-level Empathic Insight emotion teacher outputs. Each row evaluates one named emotion score.
0	Affectionemo_Affection	0.032	+0.04	0.049	+0.07	0.007	0.570
1	Amusementemo_Amusement	-0.014	-0.01	-0.034	-0.04	-0.001	0.885
2	Angeremo_Anger	0.755	+1.23	0.680	+1.10	0.004	0.613
3	Astonishment Surpriseemo_Astonishment_Surprise	0.004	-0.00	0.052	+0.08	0.005	0.572
4	Aweemo_Awe	0.043	+0.10	0.037	+0.09	0.000	0.427
5	Bitternessemo_Bitterness	0.288	+0.66	0.272	+0.62	0.013	0.415
6	Concentrationemo_Concentration	1.875	+1.67	2.046	+1.90	0.634	0.741
7	Confusionemo_Confusion	-0.016	-0.03	-0.005	-0.01	0.001	0.540
8	Contemplationemo_Contemplation	1.173	+1.82	0.938	+1.43	0.082	0.598
9	Contemptemo_Contempt	0.755	+1.63	0.565	+1.22	-0.000	0.464
10	Contentmentemo_Contentment	0.020	+0.04	0.096	+0.19	0.000	0.514
11	Disappointmentemo_Disappointment	0.246	+0.35	0.131	+0.19	0.000	0.700
12	Disgustemo_Disgust	0.628	+1.27	0.277	+0.55	0.007	0.489
13	Distressemo_Distress	0.117	+0.14	-0.014	-0.02	0.000	0.821
14	Doubtemo_Doubt	0.188	+0.39	0.048	+0.09	0.006	0.466
15	Elationemo_Elation	0.125	+0.15	0.173	+0.22	0.012	0.728
16	Embarrassmentemo_Embarrassment	-0.010	-0.12	-0.036	-0.18	0.043	0.430
17	Emotional Numbnessemo_Emotional_Numbness	0.327	+0.35	0.224	+0.24	0.004	0.917
18	Fatigue Exhaustionemo_Fatigue_Exhaustion	0.158	+0.24	0.117	+0.16	0.028	0.539
19	Fearemo_Fear	0.145	+0.21	-0.032	-0.08	0.015	0.610
20	Helplessnessemo_Helplessness	0.084	+0.13	-0.006	-0.00	-0.004	0.696
21	Hope Enthusiasm Optimismemo_Hope_Enthusiasm_Optimism	0.773	+0.86	0.883	+1.01	0.117	0.760
22	Impatience and Irritabilityemo_Impatience_and_Irritability	1.126	+1.39	1.089	+1.33	0.149	0.705
23	Infatuationemo_Infatuation	-0.027	-0.02	-0.015	-0.00	-0.015	0.533
24	Interestemo_Interest	2.174	+0.65	2.220	+0.70	1.589	0.907
25	Intoxication Altered States of Consciousnessemo_Intoxication_Altered_States_of_Consciousness	-0.053	-0.05	-0.064	-0.07	-0.025	0.559
26	Jealousy and Envyemo_Jealousy_and_Envy	0.071	+0.03	0.095	+0.08	0.059	0.442
27	Longingemo_Longing	0.168	+0.13	0.143	+0.09	0.087	0.632
28	Malevolence Maliceemo_Malevolence_Malice	0.361	+0.57	0.190	+0.25	0.055	0.534
29	Painemo_Pain	0.013	+0.03	-0.019	-0.03	-0.002	0.579
30	Pleasure Ecstasyemo_Pleasure_Ecstasy	0.016	-0.00	-0.032	-0.08	0.017	0.614
31	Prideemo_Pride	0.134	+0.26	0.376	+0.74	0.002	0.509
32	Reliefemo_Relief	0.052	+0.03	0.031	-0.00	0.033	0.681
33	Sadnessemo_Sadness	0.023	+0.03	-0.067	-0.09	0.000	0.759
34	Sexual Lustemo_Sexual_Lust	0.090	+0.12	0.019	-0.02	0.030	0.494
35	Shameemo_Shame	0.034	+0.04	0.018	+0.01	0.013	0.510
36	Sournessemo_Sourness	0.641	+1.47	0.575	+1.32	-0.005	0.439
37	Teasingemo_Teasing	0.142	+0.26	0.159	+0.29	0.000	0.545
38	Thankfulness Gratitudeemo_Thankfulness_Gratitude	0.058	+0.02	0.014	-0.04	0.041	0.697
39	Triumphemo_Triumph	0.033	+0.08	0.005	+0.02	-0.007	0.521
VoiceNet dimensions Fifty-seven VoiceNet voice, delivery, style, and recording dimensions. Codes are expanded in the target column.
40	Perceived voice age (AGEV)vn_AGEV_reg	3.499	+0.42	3.092	+0.09	2.984	1.238
41	Arousal (AROU)vn_AROU_reg	2.773	+0.36	2.686	+0.29	2.359	1.147
42	Arousal shift (ARSH)vn_ARSH_reg	3.166	+0.68	2.952	+0.43	2.580	0.867
43	Vocal attack (ATCK)vn_ATCK_reg	2.901	+0.57	2.571	+0.32	2.162	1.295
44	Background noise (BKGN)vn_BKGN_reg	2.736	+0.04	2.697	-0.01	2.703	0.761
45	Brightness (BRGT)vn_BRGT_reg	1.838	-0.19	1.669	-0.40	1.991	0.813
46	Speech chunking (CHNK)vn_CHNK_reg	3.255	+1.14	3.226	+1.11	1.847	1.239
47	Articulation clarity (CLRT)vn_CLRT_reg	2.281	+0.28	2.089	+0.08	2.018	0.945
48	Cognitive load (COGL)vn_COGL_reg	2.341	+0.23	2.253	+0.15	2.094	1.061
49	Dynamic arc (DARC)vn_DARC_reg	1.825	+0.15	1.941	+0.24	1.615	1.380
50	Disfluency (DFLU)vn_DFLU_reg	2.027	-0.39	1.911	-0.49	2.488	1.184
51	Emphasis (EMPH)vn_EMPH_reg	3.154	+0.36	3.154	+0.36	2.607	1.524
52	Esthetics (ESTH)vn_ESTH_reg	2.438	+0.04	2.317	-0.11	2.402	0.782
53	Content appropriateness (EXPL)vn_EXPL_reg	0.502	+1.29	0.528	+1.37	0.086	0.322
54	Focus (FOCS)vn_FOCS_reg	2.727	+0.35	2.500	+0.14	2.344	1.102
55	Fullness (FULL)vn_FULL_reg	1.126	-0.73	1.140	-0.72	1.778	0.889
56	Perceived gender (GEND)vn_GEND_reg	4.790	+0.46	4.727	+0.42	4.055	1.588
57	Harmonicity (HARM)vn_HARM_reg	2.405	-0.09	2.499	+0.02	2.480	0.836
58	Metallic character (METL)vn_METL_reg	2.559	+0.98	2.447	+0.86	1.621	0.958
59	Pitch range (RANG)vn_RANG_reg	2.616	-0.33	2.453	-0.51	2.914	0.897
60	Recording quality (RCQL)vn_RCQL_reg	2.280	-0.53	2.368	-0.43	2.754	0.888
61	Vocal register (REGS)vn_REGS_reg	0.157	-0.82	0.225	-0.77	1.198	1.268
62	Respiration (RESP)vn_RESP_reg	1.965	-0.68	1.877	-0.76	2.680	1.056
63	Roughness (ROUG)vn_ROUG_reg	2.836	+0.90	2.836	+0.90	2.033	0.887
64	Chest resonance (R_CHST)vn_R_CHST_reg	2.870	+0.87	2.671	+0.64	2.135	0.844
65	Head resonance (R_HEAD)vn_R_HEAD_reg	2.125	-0.03	2.113	-0.04	2.148	0.822
66	Mask resonance (R_MASK)vn_R_MASK_reg	1.558	-0.35	1.512	-0.39	1.908	1.005
67	Mixed resonance (R_MIXD)vn_R_MIXD_reg	1.929	+0.59	1.863	+0.51	1.436	0.841
68	Nasal resonance (R_NASL)vn_R_NASL_reg	3.683	+0.85	3.588	+0.76	2.791	1.047
69	Oral resonance (R_ORAL)vn_R_ORAL_reg	2.271	+0.12	2.179	-0.01	2.184	0.741
70	Throat resonance (R_THRT)vn_R_THRT_reg	2.584	+0.64	2.408	+0.42	2.070	0.803
71	Smoothness (SMTH)vn_SMTH_reg	2.757	+0.56	2.835	+0.63	2.143	1.093
72	Stance (STNC)vn_STNC_reg	3.641	+0.89	3.464	+0.73	2.633	1.137
73	Speech structure (STRU)vn_STRU_reg	2.884	+0.78	3.061	+0.96	2.137	0.958
74	ASMR style (S_ASMR)vn_S_ASMR_reg	-0.083	-1.03	-0.158	-1.08	1.370	1.411
75	Authoritative style (S_AUTH)vn_S_AUTH_reg	2.892	+1.73	2.932	+1.77	1.088	1.043
76	Cartoonish style (S_CART)vn_S_CART_reg	1.796	+0.17	2.019	+0.33	1.560	1.401
77	Casual style (S_CASU)vn_S_CASU_reg	3.861	+0.05	3.763	-0.02	3.793	1.278
78	Conversational style (S_CONV)vn_S_CONV_reg	1.687	-0.69	1.340	-0.95	2.594	1.318
79	Dramatic style (S_DRAM)vn_S_DRAM_reg	3.036	+0.27	2.856	+0.12	2.721	1.148
80	Formal style (S_FORM)vn_S_FORM_reg	1.809	+0.60	2.073	+0.86	1.195	1.021
81	Monologue style (S_MONO)vn_S_MONO_reg	3.243	+0.33	3.014	+0.15	2.824	1.284
82	Narrator style (S_NARR)vn_S_NARR_reg	2.282	+0.67	2.579	+0.88	1.307	1.446
83	Newsreader style (S_NEWS)vn_S_NEWS_reg	1.805	+2.46	2.140	+3.05	0.408	0.568
84	Playful style (S_PLAY)vn_S_PLAY_reg	2.437	+0.07	2.275	-0.06	2.352	1.315
85	Ranting or angry style (S_RANT)vn_S_RANT_reg	2.331	+0.87	1.828	+0.48	1.213	1.289
86	Storytelling style (S_STRY)vn_S_STRY_reg	3.632	+0.84	3.360	+0.64	2.480	1.366
87	Teacher or didactic style (S_TECH)vn_S_TECH_reg	-0.765	-1.15	-0.566	-0.99	0.646	1.227
88	Whispered talking style (S_WHIS)vn_S_WHIS_reg	1.061	-0.33	0.755	-0.52	1.597	1.618
89	Tempo (TEMP)vn_TEMP_reg	3.428	+1.10	3.372	+1.05	2.117	1.190
90	Tension (TENS)vn_TENS_reg	1.871	+0.37	1.877	+0.37	1.559	0.852
91	Valence (VALN)vn_VALN_reg	2.698	+0.33	2.426	+0.09	2.328	1.118
92	Valence shift (VALS)vn_VALS_reg	3.034	+0.48	2.654	+0.13	2.518	1.079
93	Velocity flux (VFLX)vn_VFLX_reg	2.452	+0.16	2.450	+0.16	2.256	1.208
94	Volatility (VOLT)vn_VOLT_reg	1.826	-0.86	1.667	-1.04	2.586	0.886
95	Vulnerability (VULN)vn_VULN_reg	1.069	-1.61	1.107	-1.57	2.648	0.984
96	Warmth (WARM)vn_WARM_reg	2.570	-0.01	2.181	-0.44	2.578	0.909
Genuineness, blend, and legacy quality Genuineness and vocal-burst blend are predicted. R_quality has Ladder training labels but no valid P3 test labels.
97	Genuineness (0–6)genuineness_0_6	2.402	+0.04	1.853	-0.30	2.332	1.621
98	Vocal-burst blend (0–10)blend_0_10	4.287	-0.87	3.862	-1.03	6.676	2.738
99	Legacy R_quality (no P3 test labels)R_quality	0.840	-0.75	0.705	-1.16	1.095	0.338
Empathic Insight Plus extra scores Nineteen additional clip-level teacher scores, including background noise and content enjoyment.
100	Ageeiv_extra:Age	3.313	+0.21	3.356	+0.36	3.250	0.293
101	Arousaleiv_extra:Arousal	1.528	+0.55	1.644	+0.82	1.289	0.435
102	Authenticityeiv_extra:Authenticity	2.742	+0.49	2.698	+0.20	2.667	0.153
103	Background Noiseeiv_extra:Background_Noise	0.453	-1.34	0.272	-2.03	0.808	0.264
104	Confident vs. Hesitanteiv_extra:Confident_vs._Hesitant	1.154	+0.38	1.107	+0.22	1.040	0.303
105	Gendereiv_extra:Gender	-1.106	-0.49	-1.130	-0.51	-0.621	0.999
106	High-Pitched vs. Low-Pitchedeiv_extra:High-Pitched_vs._Low-Pitched	2.153	+1.30	2.171	+1.37	1.827	0.250
107	Monotone vs. Expressiveeiv_extra:Monotone_vs._Expressive	2.028	+0.36	2.060	+0.43	1.859	0.470
108	Recording Qualityeiv_extra:Recording_Quality	2.433	+0.87	2.486	+1.03	2.144	0.332
109	Serious vs. Humorouseiv_extra:Serious_vs._Humorous	0.865	-0.19	1.002	+0.21	0.929	0.340
110	Soft vs. Harsheiv_extra:Soft_vs._Harsh	0.129	-0.48	0.192	-0.28	0.281	0.320
111	Submissive vs. Dominanteiv_extra:Submissive_vs._Dominant	0.803	+1.32	0.914	+1.66	0.376	0.324
112	Valenceeiv_extra:Valence	-0.077	-0.22	0.026	+0.06	0.005	0.380
113	Vulnerable vs. Emotionally Detachedeiv_extra:Vulnerable_vs._Emotionally_Detached	2.074	+0.82	2.144	+0.98	1.715	0.437
114	Warm vs. Coldeiv_extra:Warm_vs._Cold	-0.034	-0.28	0.087	+0.12	0.051	0.300
115	score background qualityeiv_extra:score_background_quality	3.602	+0.43	3.675	+0.54	3.301	0.693
116	score content enjoymenteiv_extra:score_content_enjoyment	4.694	+0.62	4.809	+1.00	4.507	0.303
117	score overall qualityeiv_extra:score_overall_quality	2.933	+0.55	2.973	+0.63	2.652	0.507
118	score speech qualityeiv_extra:score_speech_quality	1.975	+1.15	1.995	+1.28	1.808	0.146
Meta AudioBox Aesthetics Four AudioBox aesthetic teacher outputs. Expansions follow the official Meta model card.
119	Content enjoyment (CE)audiobox:CE	5.526	+0.71	5.776	+0.96	4.799	1.018
120	Content usefulness (CU)audiobox:CU	6.226	+0.58	6.044	+0.40	5.649	1.001
121	Production complexity (PC)audiobox:PC	1.498	-0.51	1.505	-0.51	2.331	1.617
122	Production quality (PQ)audiobox:PQ	7.289	+0.28	7.117	+0.08	7.044	0.879
Microsoft DNSMOS Seven DNSMOS teacher outputs: raw and calibrated SIG/BAK/OVRL estimates plus P.808 MOS.
123	Speech signal quality, rawdnsmos:SIG_raw	4.061	+0.24	4.033	+0.20	3.900	0.669
124	Background quality, rawdnsmos:BAK_raw	4.043	+0.74	4.113	+0.80	3.211	1.124
125	Overall quality, rawdnsmos:OVRL_raw	3.643	+0.69	3.669	+0.72	3.085	0.812
126	Speech signal quality, calibrateddnsmos:SIG	3.585	+0.19	3.565	+0.15	3.488	0.501
127	Background quality, calibrateddnsmos:BAK	3.919	+0.57	3.988	+0.65	3.389	0.928
128	Overall quality, calibrateddnsmos:OVRL	3.207	+0.61	3.224	+0.63	2.840	0.606
129	P.808 MOS estimatednsmos:P808_MOS	3.837	+0.84	3.799	+0.76	3.421	0.496
Vocal-burst count The regression target is log(1 + count). A separate table also reports count error after inverse transformation.
130	Vocal-burst count, log(1 + count)burst_count_log1p	0.005	+0.01	-0.008	-0.01	0.000	0.647
VoiceCLAP attributes Sixty-one individual VoiceCLAP attribute teacher scores. The raw 768D VoiceCLAP embedding is stored in sidecars but is not a model output.
131	Affectionvoiceclap_attribute:Affection	0.671	-0.50	0.494	-0.82	0.947	0.554
132	Agevoiceclap_attribute:Age	3.248	+0.04	3.290	+0.11	3.229	0.547
133	Amusementvoiceclap_attribute:Amusement	0.544	+0.27	0.427	+0.06	0.392	0.572
134	Angervoiceclap_attribute:Anger	1.635	+1.27	1.588	+1.18	0.992	0.506
135	Arousalvoiceclap_attribute:Arousal	2.075	+1.05	2.077	+1.06	1.420	0.622
136	Astonishment Surprisevoiceclap_attribute:Astonishment_Surprise	0.511	+0.01	0.714	+0.43	0.509	0.479
137	Authenticityvoiceclap_attribute:Authenticity	2.786	+0.10	2.705	-0.39	2.770	0.167
138	Awevoiceclap_attribute:Awe	0.761	+0.86	0.757	+0.84	0.539	0.259
139	Background Noisevoiceclap_attribute:Background_Noise	0.421	-0.55	0.501	-0.25	0.567	0.264
140	Bitternessvoiceclap_attribute:Bitterness	0.840	+1.05	0.762	+0.72	0.592	0.236
141	Concentrationvoiceclap_attribute:Concentration	1.245	+0.06	1.453	+0.45	1.214	0.531
142	Confident vs. Hesitantvoiceclap_attribute:Confident_vs._Hesitant	1.075	+0.01	0.957	-0.24	1.069	0.468
143	Confusionvoiceclap_attribute:Confusion	0.612	-0.09	0.501	-0.43	0.643	0.334
144	Contemplationvoiceclap_attribute:Contemplation	0.610	-0.42	0.530	-0.62	0.780	0.406
145	Contemptvoiceclap_attribute:Contempt	1.290	+1.72	1.118	+1.21	0.709	0.339
146	Contentmentvoiceclap_attribute:Contentment	0.436	-0.50	0.432	-0.51	0.588	0.307
147	Disappointmentvoiceclap_attribute:Disappointment	0.977	+0.75	1.048	+0.99	0.760	0.291
148	Disgustvoiceclap_attribute:Disgust	0.937	+1.51	0.953	+1.58	0.625	0.207
149	Distressvoiceclap_attribute:Distress	1.182	+0.73	1.161	+0.67	0.927	0.350
150	Doubtvoiceclap_attribute:Doubt	0.318	-1.15	0.287	-1.32	0.535	0.188
151	Elationvoiceclap_attribute:Elation	0.795	+0.64	0.695	+0.39	0.539	0.397
152	Embarrassmentvoiceclap_attribute:Embarrassment	0.216	-0.29	0.060	-0.79	0.307	0.314
153	Emotional Numbnessvoiceclap_attribute:Emotional_Numbness	0.627	-0.14	0.667	+0.01	0.664	0.266
154	Fatigue Exhaustionvoiceclap_attribute:Fatigue_Exhaustion	0.421	-0.16	0.340	-0.47	0.462	0.261
155	Fearvoiceclap_attribute:Fear	0.827	+0.99	0.833	+1.01	0.618	0.212
156	Gendervoiceclap_attribute:Gender	-1.501	-1.34	-1.619	-1.46	-0.151	1.005
157	Helplessnessvoiceclap_attribute:Helplessness	0.647	-0.04	0.729	+0.26	0.658	0.268
158	High-Pitched vs. Low-Pitchedvoiceclap_attribute:High-Pitched_vs._Low-Pitched	2.324	+1.29	2.406	+1.51	1.840	0.375
159	Hope Enthusiasm Optimismvoiceclap_attribute:Hope_Enthusiasm_Optimism	1.056	+0.89	1.000	+0.75	0.705	0.396
160	Impatience and Irritabilityvoiceclap_attribute:Impatience_and_Irritability	1.810	+1.40	2.001	+1.75	1.052	0.541
161	Infatuationvoiceclap_attribute:Infatuation	0.605	-0.01	0.573	-0.11	0.608	0.332
162	Interestvoiceclap_attribute:Interest	1.770	+0.39	1.594	-0.01	1.598	0.440
163	Intoxication Altered States of Consciousnessvoiceclap_attribute:Intoxication_Altered_States_of_Consciousness	0.590	+0.19	0.802	+0.65	0.502	0.463
164	Jealousy & Envyvoiceclap_attribute:Jealousy_&_Envy	0.813	+1.18	0.848	+1.33	0.523	0.245
165	Longingvoiceclap_attribute:Longing	0.591	+0.24	0.549	+0.05	0.538	0.220
166	Malevolence Malicevoiceclap_attribute:Malevolence_Malice	1.252	+1.21	1.184	+1.02	0.833	0.346
167	Monotone vs. Expressivevoiceclap_attribute:Monotone_vs._Expressive	2.016	+0.41	1.885	+0.19	1.775	0.594
168	Painvoiceclap_attribute:Pain	0.406	+0.11	0.486	+0.48	0.381	0.218
169	Pleasure Ecstasyvoiceclap_attribute:Pleasure_Ecstasy	0.565	+0.21	0.396	-0.36	0.503	0.301
170	Pridevoiceclap_attribute:Pride	1.007	+0.65	1.049	+0.77	0.780	0.349
171	Recording Qualityvoiceclap_attribute:Recording_Quality	2.368	+0.17	2.314	+0.00	2.313	0.328
172	Reliefvoiceclap_attribute:Relief	0.945	-0.19	0.842	-0.44	1.025	0.415
173	Sadnessvoiceclap_attribute:Sadness	0.802	+0.16	0.841	+0.28	0.752	0.313
174	Serious vs. Humorousvoiceclap_attribute:Serious_vs._Humorous	0.679	-0.22	0.552	-0.44	0.803	0.568
175	Sexual Lustvoiceclap_attribute:Sexual_Lust	0.882	+0.59	0.934	+0.71	0.635	0.419
176	Shamevoiceclap_attribute:Shame	0.589	+0.22	0.685	+0.56	0.526	0.283
177	Soft vs. Harshvoiceclap_attribute:Soft_vs._Harsh	-0.330	-1.36	-0.555	-1.98	0.160	0.360
178	Sournessvoiceclap_attribute:Sourness	1.104	+1.37	1.061	+1.22	0.706	0.291
179	Submissive vs. Dominantvoiceclap_attribute:Submissive_vs._Dominant	1.201	+1.61	1.344	+2.01	0.623	0.359
180	Teasingvoiceclap_attribute:Teasing	0.430	-0.29	0.247	-0.78	0.540	0.379
181	Thankfulness Gratitudevoiceclap_attribute:Thankfulness_Gratitude	1.789	+0.76	1.764	+0.72	1.384	0.529
182	Triumphvoiceclap_attribute:Triumph	0.949	+0.65	1.044	+0.91	0.716	0.359
183	Valencevoiceclap_attribute:Valence	-1.017	-1.59	-1.225	-1.92	-0.007	0.635
184	Vulnerable vs. Emotionally Detachedvoiceclap_attribute:Vulnerable_vs._Emotionally_Detached	2.222	+1.05	2.387	+1.35	1.638	0.556
185	Warm vs. Coldvoiceclap_attribute:Warm_vs._Cold	-0.402	-0.84	-0.659	-1.48	-0.066	0.400
186	durationvoiceclap_attribute:duration	8.345	-0.40	9.396	-0.24	10.914	6.354
187	score background qualityvoiceclap_attribute:score_background_quality	3.453	+0.42	3.638	+0.79	3.245	0.498
188	score content enjoymentvoiceclap_attribute:score_content_enjoyment	4.748	+0.62	4.795	+0.95	4.656	0.147
189	score overall qualityvoiceclap_attribute:score_overall_quality	2.795	+0.39	2.903	+0.65	2.635	0.412
190	score speech qualityvoiceclap_attribute:score_speech_quality	1.979	+1.27	1.988	+1.41	1.891	0.069
191	talking speedvoiceclap_attribute:talking_speed	20.973	+3.18	21.735	+3.38	9.028	3.756

All Orange embedding components

The cosine above is the meaningful vector-level comparison; component values have no standalone semantic label.

Timbre — all 128 vector components

Dimension	Tiny	Base	Orange teacher
0	-0.0053	0.0095	-0.0006
1	0.0510	0.0151	-0.0880
2	-0.0665	-0.0690	-0.0868
3	-0.0245	-0.0849	-0.0897
4	-0.0828	-0.1156	-0.0832
5	-0.1336	-0.1074	-0.1120
6	-0.0465	-0.0308	-0.0802
7	0.1016	0.0783	0.1226
8	0.0041	-0.0320	0.0806
9	-0.1016	-0.1025	-0.0501
10	0.0615	0.0449	0.0770
11	-0.0903	-0.1079	-0.0530
12	-0.0585	-0.0229	-0.0491
13	-0.0930	-0.0877	-0.0873
14	-0.0812	-0.1030	-0.0922
15	-0.0775	-0.0811	-0.0793
16	-0.1096	-0.0707	-0.0521
17	-0.1165	-0.0959	-0.0763
18	-0.0604	-0.0219	-0.0586
19	-0.0577	-0.0707	-0.0837
20	0.1871	0.1512	0.1221
21	-0.0309	0.0112	-0.0290
22	-0.0893	-0.0844	-0.0833
23	-0.0226	-0.0381	0.0846
24	-0.0877	-0.0838	-0.0714
25	-0.0013	-0.0575	-0.0353
26	0.0008	0.0107	-0.0765
27	-0.0526	-0.0200	0.0544
28	-0.0420	-0.0405	-0.0170
29	-0.0037	0.0515	0.0568
30	0.1277	0.1896	0.1793
31	0.0484	0.0570	-0.0394
32	-0.1058	-0.0915	-0.0853
33	-0.1219	-0.1134	-0.0975
34	-0.1053	-0.1161	-0.0793
35	0.2010	0.2619	0.2231
36	-0.0855	-0.1041	-0.0951
37	-0.1133	-0.0920	-0.1048
38	-0.0484	-0.0762	-0.0668
39	-0.0930	-0.0992	-0.0893
40	-0.0727	-0.0573	-0.0367
41	-0.1293	-0.1019	-0.1272
42	0.0775	0.0772	0.0728
43	0.0871	0.0562	0.0746
44	0.1689	0.2476	0.1925
45	0.1625	0.1698	0.1665
46	-0.0941	-0.0542	-0.0345
47	-0.0973	-0.0915	-0.0895
48	-0.0183	-0.0597	-0.0864
49	0.0652	0.0592	0.0450
50	0.0363	0.0416	0.0361
51	-0.0327	-0.0600	-0.0885
52	-0.0187	-0.0186	0.0176
53	0.0839	0.1041	0.0886
54	-0.1251	-0.0871	-0.0991
55	0.2459	0.1896	0.1434
56	-0.0126	-0.0194	-0.0839
57	-0.1144	-0.1479	-0.0970
58	0.0388	0.0129	0.0584
59	0.1176	0.1063	0.1075
60	-0.0668	-0.0816	-0.0853
61	0.3399	0.2487	0.2576
62	-0.0748	-0.0904	-0.0828
63	-0.0334	-0.0575	-0.0583
64	-0.0060	0.0493	0.0522
65	-0.0909	-0.0937	-0.0722
66	0.0791	0.0992	0.0529
67	-0.0834	-0.0751	-0.0853
68	-0.0727	-0.1068	-0.0936
69	-0.0791	-0.0866	-0.0811
70	0.0569	0.0411	0.0436
71	-0.0146	-0.0051	-0.0109
72	-0.0684	-0.0641	-0.0856
73	0.0295	0.0262	0.0368
74	-0.0941	-0.0751	-0.0967
75	-0.0076	0.0003	0.0810
76	0.0353	0.0168	0.0243
77	-0.0460	-0.0292	-0.0808
78	0.0524	0.0264	-0.0215
79	-0.0572	-0.0767	-0.0768
80	-0.0317	0.0263	-0.0481
81	0.0909	0.0844	0.0305
82	-0.0802	-0.1052	-0.0847
83	-0.0882	-0.1068	-0.0906
84	0.0877	0.1244	0.1295
85	-0.0092	0.0496	0.0451
86	-0.0681	-0.0696	-0.0632
87	-0.0914	-0.0668	-0.0551
88	0.0313	0.0305	0.0292
89	-0.0227	-0.0221	-0.0812
90	-0.0791	-0.1052	-0.0959
91	0.1860	0.1315	0.1504
92	-0.1090	-0.0937	-0.0859
93	0.0919	0.0844	0.1229
94	0.0957	0.0899	0.1160
95	-0.0521	-0.0197	-0.0535
96	-0.0770	-0.0756	-0.0510
97	0.0031	-0.0059	0.0567
98	0.0855	0.0789	0.1327
99	0.0125	-0.0222	0.0599
100	0.0839	0.1364	0.0795
101	0.1176	0.1090	0.0682
102	-0.0473	-0.0499	-0.0565
103	-0.1005	-0.0937	-0.0934
104	-0.0665	-0.0603	-0.0763
105	-0.0492	-0.0690	-0.0236
106	-0.0251	-0.0425	-0.0548
107	0.0334	0.0284	-0.0204
108	-0.0042	0.0064	-0.0374
109	-0.0577	-0.0866	-0.0868
110	0.0015	-0.0132	-0.0205
111	-0.0919	-0.0904	-0.1027
112	-0.0855	-0.0986	-0.0872
113	0.0823	0.0751	0.0681
114	-0.0732	-0.0616	-0.0551
115	0.0711	0.0849	0.1692
116	0.0478	0.0208	-0.0102
117	0.0764	0.1249	0.1534
118	-0.1358	-0.1205	-0.0862
119	0.1203	0.1512	0.0608
120	-0.0834	-0.0679	-0.0910
121	0.0625	0.0534	0.1449
122	-0.0951	-0.0663	-0.0909
123	-0.0575	-0.0161	-0.0329
124	-0.0295	-0.0241	-0.0872
125	0.0122	0.0362	0.0454
126	-0.0310	-0.0644	-0.0032
127	0.0126	0.0086	0.0963

Identity — all 250 vector components

Dimension	Tiny	Base	Orange teacher
0	0.0360	0.0310	0.1121
1	0.0028	0.0033	0.0621
2	0.0157	0.0064	0.0616
3	-0.0151	-0.0070	-0.0348
4	-0.0313	0.0208	-0.0427
5	-0.1054	-0.0713	-0.0490
6	-0.0145	0.0510	0.0202
7	0.0442	0.0358	-0.0475
8	0.0019	0.0595	0.0087
9	0.0442	0.0068	0.0229
10	0.0772	0.0832	0.0803
11	-0.0388	-0.0613	0.0465
12	-0.0459	-0.0722	-0.0513
13	-0.0408	-0.0179	-0.0414
14	-0.0564	-0.0431	0.0609
15	0.0554	0.0777	0.1038
16	0.0979	0.0886	0.0659
17	0.0023	-0.0042	0.0259
18	-0.0918	-0.0372	-0.0477
19	-0.0218	-0.0172	-0.0052
20	0.0142	0.0343	0.0117
21	-0.0561	-0.0650	-0.0435
22	-0.0202	-0.0367	-0.0486
23	-0.0945	-0.0722	-0.0453
24	0.0287	0.0449	0.0153
25	-0.0287	0.0616	-0.0804
26	0.0161	0.0083	-0.0251
27	0.0309	0.0537	0.1073
28	0.0212	0.0200	-0.0079
29	-0.0445	-0.0589	-0.0451
30	0.1027	0.0628	0.0035
31	0.1142	0.0977	0.1494
32	-0.0196	0.0156	-0.0482
33	0.1101	0.0662	0.0439
34	0.0003	-0.0012	-0.0476
35	0.0014	-0.0001	-0.0440
36	-0.0010	-0.0373	0.0139
37	0.0275	0.0337	-0.0324
38	0.0513	0.0656	-0.0036
39	-0.0578	-0.0431	-0.0196
40	-0.0615	-0.0692	-0.0543
41	0.0799	0.0562	0.0492
42	-0.0260	-0.0231	-0.0466
43	0.0191	0.0771	-0.0554
44	0.0551	0.0722	-0.0050
45	-0.0541	-0.0054	0.0227
46	-0.0272	-0.0665	-0.0287
47	-0.0326	-0.0467	-0.0499
48	0.0070	-0.0184	-0.0500
49	-0.0435	-0.0707	-0.0460
50	-0.0272	-0.0212	-0.0649
51	0.1115	0.0856	0.0244
52	0.0313	0.0540	-0.0300
53	-0.0169	0.0043	0.0180
54	0.0296	0.0929	0.0596
55	0.0476	0.0504	0.0651
56	0.0530	0.0838	0.1099
57	0.0136	-0.0214	-0.0429
58	0.0000	0.0150	0.0061
59	0.0248	0.0449	0.0641
60	0.0178	0.0440	0.0110
61	-0.0476	-0.0510	-0.0435
62	0.0036	-0.0217	-0.0412
63	-0.0127	-0.0137	-0.0510
64	0.0022	-0.0410	-0.0450
65	0.0544	0.0577	0.0431
66	0.0076	-0.0331	-0.0591
67	0.0243	-0.0106	-0.0493
68	-0.0490	-0.0474	-0.0505
69	0.0308	0.0826	-0.0194
70	-0.0643	-0.0710	-0.0680
71	-0.0106	0.0061	-0.0059
72	-0.0405	-0.0070	-0.0265
73	0.0972	0.0501	-0.0028
74	-0.0195	0.0077	-0.0506
75	0.1142	0.1111	0.0797
76	-0.0173	0.0410	-0.0140
77	-0.0816	-0.0604	-0.0274
78	-0.0109	-0.0413	0.0009
79	-0.0029	0.0187	0.0190
80	-0.1081	-0.1069	-0.0498
81	-0.0059	0.0110	-0.0562
82	-0.0308	-0.0443	-0.0450
83	-0.0670	-0.0477	-0.0416
84	0.0462	0.0308	0.1108
85	0.0347	0.0443	0.0987
86	-0.0442	-0.0062	-0.0447
87	-0.0238	-0.0178	0.1187
88	0.0795	0.0801	0.0365
89	0.0311	0.0073	-0.0453
90	-0.0466	-0.0299	-0.0496
91	-0.0925	-0.0844	-0.0589
92	0.0016	-0.0054	-0.0120
93	0.0165	0.0595	-0.0530
94	-0.0500	-0.0543	-0.0753
95	-0.0551	-0.0320	-0.0522
96	-0.0091	0.0343	0.0045
97	-0.0571	-0.0586	-0.0590
98	0.0214	0.0431	-0.0529
99	-0.0202	0.0387	0.0098
100	-0.0396	-0.0389	-0.0308
101	-0.0350	-0.0149	-0.0473
102	0.0301	0.0231	-0.0096
103	-0.0040	0.0345	0.0292
104	-0.1149	-0.1050	-0.0652
105	-0.0433	-0.0546	0.0252
106	-0.0823	-0.0653	-0.0386
107	-0.0772	-0.0437	-0.0449
108	0.1945	0.2149	0.2477
109	-0.0178	0.0144	0.0565
110	-0.0792	-0.0698	-0.0596
111	-0.1163	-0.0677	-0.0413
112	-0.0449	-0.0552	-0.0404
113	0.0785	0.0707	0.0152
114	-0.0274	-0.0091	-0.0225
115	0.0275	0.0363	-0.0281
116	-0.0311	-0.0501	0.0144
117	0.0064	-0.0244	-0.0629
118	-0.0860	-0.0513	-0.0123
119	-0.0326	-0.0340	-0.0515
120	0.0031	-0.0322	-0.0350
121	-0.0466	-0.0285	-0.0538
122	-0.0809	-0.0929	-0.0473
123	0.0483	0.0264	0.1212
124	0.0476	0.0128	-0.0171
125	-0.0986	-0.1062	-0.0487
126	0.1142	0.1299	0.2008
127	-0.0184	-0.0250	-0.0515
128	0.0041	0.0034	-0.0201
129	0.1074	0.1032	0.1058
130	-0.0282	-0.0583	-0.0503
131	0.0476	0.0232	-0.0435
132	-0.0173	0.0410	-0.0251
133	0.0812	0.0366	0.1243
134	0.0517	0.0437	0.0644
135	-0.0115	-0.0063	-0.0504
136	-0.0371	-0.0543	-0.0299
137	0.0687	0.0223	0.0356
138	0.0082	0.0323	-0.0253
139	0.0396	0.0574	-0.0512
140	-0.0277	-0.0165	-0.0092
141	-0.0062	0.0413	-0.0219
142	-0.0598	-0.0322	-0.0433
143	0.0435	0.0216	0.0036
144	-0.1074	-0.1014	-0.0522
145	0.0052	0.0074	-0.0023
146	0.1305	0.1639	0.0696
147	-0.0087	-0.0197	0.0011
148	0.0931	0.0856	0.0641
149	0.1278	0.1311	0.1825
150	0.1285	0.0984	0.0220
151	0.0134	0.0180	0.0264
152	-0.0108	-0.0098	-0.0555
153	0.0877	0.0296	0.0548
154	0.0231	0.0211	0.0120
155	0.0711	-0.0182	-0.0151
156	0.0121	-0.0036	-0.0170
157	0.0598	0.0625	0.0134
158	-0.0001	-0.0296	-0.0623
159	0.0406	0.0671	0.0080
160	0.0704	0.0765	0.1307
161	0.0112	-0.0149	-0.0703
162	-0.0840	-0.0461	-0.0324
163	-0.0918	-0.0668	-0.0557
164	-0.0999	-0.0386	-0.0440
165	0.0207	0.0308	0.0189
166	0.0107	0.0556	-0.0392
167	-0.1537	-0.1366	-0.0464
168	0.0952	0.0923	0.0891
169	0.0945	0.0522	-0.0511
170	-0.0051	-0.0276	-0.0469
171	-0.0331	-0.0540	-0.0440
172	0.0993	0.1190	0.0351
173	0.0214	0.0659	0.1326
174	-0.0636	-0.0419	-0.0514
175	-0.0775	-0.0856	-0.0829
176	0.0517	0.0389	0.1128
177	-0.0352	-0.0269	-0.0413
178	0.0416	0.0304	-0.0439
179	0.1115	0.1232	0.0486
180	0.1713	0.1894	0.1168
181	-0.0133	0.0038	0.0148
182	-0.0578	-0.0683	-0.0432
183	-0.1027	-0.0768	-0.0767
184	0.0260	0.0759	0.0411
185	0.0646	0.0637	0.0135
186	-0.0731	-0.0777	-0.0604
187	0.1027	0.1251	0.0756
188	0.0721	0.0504	0.0840
189	0.0581	0.0640	0.0453
190	-0.0420	0.0073	0.0312
191	0.0510	0.0446	0.0766
192	0.0918	0.1354	0.0782
193	0.0442	0.0650	0.0864
194	0.0062	0.0168	0.0020
195	0.0131	0.0217	-0.0014
196	0.0027	0.0200	0.0414
197	0.1387	0.1202	0.1052
198	-0.0008	-0.0165	-0.0484
199	0.0318	0.0407	-0.0339
200	-0.0140	-0.0205	-0.0579
201	0.1101	0.1354	0.0426
202	-0.0643	-0.0838	-0.1041
203	0.1265	0.0923	0.0235
204	0.1101	0.0704	0.1121
205	-0.0064	-0.0103	0.0591
206	0.0206	0.0326	0.0404
207	-0.0262	0.0168	0.0458
208	-0.0189	-0.0619	-0.0519
209	-0.0060	0.0067	-0.0122
210	0.1149	0.0874	0.1063
211	0.0102	-0.0243	0.0223
212	-0.0064	0.0695	0.1444
213	0.0362	0.0249	0.0977
214	0.2597	0.2926	0.2761
215	-0.0362	-0.0370	-0.0421
216	-0.0287	-0.0501	-0.0599
217	-0.0537	-0.0282	0.0110
218	-0.0030	-0.0483	0.0520
219	-0.0211	0.0087	-0.0481
220	-0.0595	-0.0789	-0.0553
221	-0.0071	-0.0083	-0.0158
222	0.0088	0.0263	0.0431
223	-0.0602	-0.0381	-0.0401
224	-0.0213	0.0073	0.0799
225	0.0292	0.0241	0.0587
226	-0.0316	-0.0119	0.0065
227	0.0592	0.1178	0.0442
228	0.0039	0.0125	-0.0696
229	0.0592	0.0098	-0.0549
230	0.0325	0.0516	0.0892
231	0.0626	0.0398	0.0690
232	-0.0168	0.0023	-0.0005
233	-0.0350	-0.0577	-0.0809
234	0.1666	0.1257	0.0206
235	0.1577	0.1311	0.0696
236	-0.0001	-0.0114	-0.0430
237	-0.0120	0.0059	-0.0511
238	0.0636	0.0360	0.1029
239	-0.0139	-0.0211	0.0218
240	0.0717	0.1020	0.1371
241	0.0054	0.0288	0.0710
242	-0.0325	-0.0384	-0.0737
243	-0.0860	-0.0971	-0.0643
244	-0.0690	-0.0695	-0.0532
245	-0.0843	-0.0571	-0.0476
246	-0.0165	0.0610	-0.0405
247	-0.0728	-0.0923	-0.0421
248	-0.0724	-0.0744	-0.0572
249	-0.0609	-0.0392	-0.0345

Source: HUMANENESS_SMALL_VOICE_IDENTITY_R1_R2_2026-10-02_mediathek_0047.html · SHA-256 8abb604125492b46…

g06EnglishMediathek voice study

mediathek_0047 · en · 13/50

Generated TTS prediction · Rank 1 qv · 12.0 s

For folks constantly on the move, trying to gather all that intel about a search subject by hand is just too much work. (normal breathing) That's where online tools like People Finder really shine, you know?

Tiny Base · values are model estimates, not ground truth

Strongest emotions relative to training

Impatience and Irritability

z +2.16 / +1.66raw 1.67 / 1.32

Hope Enthusiasm Optimism

z +1.07 / +1.74raw 0.93 / 1.44

Anger

z +1.56 / +1.42raw 0.96 / 0.87

Sourness

z +1.32 / +1.34raw 0.57 / 0.58

Contemplation

z +1.03 / +1.33raw 0.70 / 0.88

Pride

z +0.59 / +1.27raw 0.30 / 0.65

Concentration

z +1.13 / +1.17raw 1.47 / 1.50

The center of each bar is the S9 teacher median. Positive z is to the right; negative z is to the left. Ranking uses z, not raw teacher units.

Strongest VoiceNet dimensions relative to training

Authoritative style (S_AUTH)

z +1.95 / +1.75raw 3.12 / 2.92

Ranting or angry style (S_RANT)

z +1.84 / +1.77raw 3.59 / 3.50

Stance (STNC)

z +1.82 / +1.81raw 4.70 / 4.69

Nasal resonance (R_NASL)

z +1.75 / +1.78raw 4.62 / 4.66

Tempo (TEMP)

z +1.50 / +1.61raw 3.91 / 4.03

Roughness (ROUG)

z +1.31 / +1.53raw 3.19 / 3.39

Tension (TENS)

z +1.48 / +1.39raw 2.82 / 2.75

All 57 VoiceNet predictions, including raw units, are in the full table below. These seven are ranked by z; the top values may differ from the strongest raw dimensions.

Voice, speed and quality scores in context

Genuineness (0–6)z +0.55 / +0.44raw 3.22 / 3.05

Vocal-burst blend (0–10)z +0.05 / +0.10raw 6.82 / 6.96

Content enjoyment (CE)z +0.64 / +0.47raw 5.45 / 5.28

Production quality (PQ)z +0.32 / +0.23raw 7.33 / 7.25

Speech signal quality, calibratedz +0.14 / +0.19raw 3.56 / 3.59

Background quality, calibratedz +0.69 / +0.63raw 4.03 / 3.98

Overall quality, calibratedz +0.73 / +0.65raw 3.29 / 3.24

P.808 MOS estimatez +0.55 / +0.51raw 3.70 / 3.67

score content enjoymentz +0.74 / +1.10raw 4.73 / 4.84

score overall qualityz +0.86 / +0.91raw 3.09 / 3.11

Background Noisez -0.41 / -0.98raw 0.70 / 0.55

Tempo (TEMP)z +1.50 / +1.61raw 3.91 / 4.03

Arousal (AROU)z +1.45 / +1.39raw 4.02 / 3.95

Valence (VALN)z +0.52 / +0.41raw 2.91 / 2.78

Recording quality (RCQL)z -0.76 / -0.91raw 2.08 / 1.95

Background noise (BKGN)z -0.62 / -0.58raw 2.23 / 2.26

talking speedz +2.38 / +2.79raw 17.98 / 19.51

Characters per second (CPS): 17.32 raw · z +2.21

Orange speaker embedding reconstruction

Cosine against Orange on this same clip (higher means closer to that teacher vector):

Embedding	Tiny	Base
Timbre · 128D	0.907	0.886
Identity · 250D	0.683	0.673

Vocal-burst regions

Tiny

Base

0 s12.0 s

Verified burst intervals are unavailable for this clip.

Tiny: 0 regions, count-head estimate 0.00; Base: 0 regions, count-head estimate 0.00.

Exact predicted start and end times

Model	Region	Start (s)	End (s)	Duration (s)

All 192 score slots · raw and z values

#	Target	Tiny raw	Tiny z	Base raw	Base z	Train median	Train SD
Emotion scores Forty clip-level Empathic Insight emotion teacher outputs. Each row evaluates one named emotion score.
0	Affectionemo_Affection	0.094	+0.15	0.215	+0.37	0.007	0.570
1	Amusementemo_Amusement	0.066	+0.08	0.171	+0.19	-0.001	0.885
2	Angeremo_Anger	0.959	+1.56	0.873	+1.42	0.004	0.613
3	Astonishment Surpriseemo_Astonishment_Surprise	0.036	+0.05	0.029	+0.04	0.005	0.572
4	Aweemo_Awe	-0.002	-0.01	-0.012	-0.03	0.000	0.427
5	Bitternessemo_Bitterness	0.382	+0.89	0.325	+0.75	0.013	0.415
6	Concentrationemo_Concentration	1.470	+1.13	1.498	+1.17	0.634	0.741
7	Confusionemo_Confusion	0.067	+0.12	0.011	+0.02	0.001	0.540
8	Contemplationemo_Contemplation	0.695	+1.03	0.878	+1.33	0.082	0.598
9	Contemptemo_Contempt	0.365	+0.79	0.496	+1.07	-0.000	0.464
10	Contentmentemo_Contentment	0.235	+0.46	0.527	+1.03	0.000	0.514
11	Disappointmentemo_Disappointment	0.571	+0.82	0.260	+0.37	0.000	0.700
12	Disgustemo_Disgust	0.147	+0.29	0.089	+0.17	0.007	0.489
13	Distressemo_Distress	0.224	+0.27	0.061	+0.07	0.000	0.821
14	Doubtemo_Doubt	0.139	+0.29	0.150	+0.31	0.006	0.466
15	Elationemo_Elation	0.243	+0.32	0.372	+0.49	0.012	0.728
16	Embarrassmentemo_Embarrassment	-0.027	-0.16	-0.007	-0.12	0.043	0.430
17	Emotional Numbnessemo_Emotional_Numbness	0.113	+0.12	0.037	+0.04	0.004	0.917
18	Fatigue Exhaustionemo_Fatigue_Exhaustion	0.427	+0.74	0.054	+0.05	0.028	0.539
19	Fearemo_Fear	-0.008	-0.04	-0.015	-0.05	0.015	0.610
20	Helplessnessemo_Helplessness	0.168	+0.25	0.060	+0.09	-0.004	0.696
21	Hope Enthusiasm Optimismemo_Hope_Enthusiasm_Optimism	0.930	+1.07	1.440	+1.74	0.117	0.760
22	Impatience and Irritabilityemo_Impatience_and_Irritability	1.669	+2.16	1.321	+1.66	0.149	0.705
23	Infatuationemo_Infatuation	-0.016	-0.00	0.003	+0.03	-0.015	0.533
24	Interestemo_Interest	2.149	+0.62	2.392	+0.89	1.589	0.907
25	Intoxication Altered States of Consciousnessemo_Intoxication_Altered_States_of_Consciousness	-0.040	-0.03	-0.022	+0.01	-0.025	0.559
26	Jealousy and Envyemo_Jealousy_and_Envy	0.377	+0.72	0.419	+0.81	0.059	0.442
27	Longingemo_Longing	0.158	+0.11	0.035	-0.08	0.087	0.632
28	Malevolence Maliceemo_Malevolence_Malice	0.057	+0.00	0.092	+0.07	0.055	0.534
29	Painemo_Pain	-0.029	-0.05	-0.031	-0.05	-0.002	0.579
30	Pleasure Ecstasyemo_Pleasure_Ecstasy	0.018	+0.00	0.143	+0.21	0.017	0.614
31	Prideemo_Pride	0.301	+0.59	0.647	+1.27	0.002	0.509
32	Reliefemo_Relief	0.040	+0.01	0.035	+0.00	0.033	0.681
33	Sadnessemo_Sadness	0.110	+0.14	-0.037	-0.05	0.000	0.759
34	Sexual Lustemo_Sexual_Lust	-0.033	-0.13	0.018	-0.02	0.030	0.494
35	Shameemo_Shame	0.005	-0.01	0.010	-0.01	0.013	0.510
36	Sournessemo_Sourness	0.575	+1.32	0.582	+1.34	-0.005	0.439
37	Teasingemo_Teasing	0.124	+0.23	0.205	+0.38	0.000	0.545
38	Thankfulness Gratitudeemo_Thankfulness_Gratitude	0.146	+0.15	0.362	+0.46	0.041	0.697
39	Triumphemo_Triumph	0.015	+0.04	0.088	+0.18	-0.007	0.521
VoiceNet dimensions Fifty-seven VoiceNet voice, delivery, style, and recording dimensions. Codes are expanded in the target column.
40	Perceived voice age (AGEV)vn_AGEV_reg	3.341	+0.29	3.031	+0.04	2.984	1.238
41	Arousal (AROU)vn_AROU_reg	4.021	+1.45	3.950	+1.39	2.359	1.147
42	Arousal shift (ARSH)vn_ARSH_reg	3.690	+1.28	3.717	+1.31	2.580	0.867
43	Vocal attack (ATCK)vn_ATCK_reg	3.363	+0.93	3.343	+0.91	2.162	1.295
44	Background noise (BKGN)vn_BKGN_reg	2.232	-0.62	2.265	-0.58	2.703	0.761
45	Brightness (BRGT)vn_BRGT_reg	2.733	+0.91	2.812	+1.01	1.991	0.813
46	Speech chunking (CHNK)vn_CHNK_reg	3.313	+1.18	3.167	+1.07	1.847	1.239
47	Articulation clarity (CLRT)vn_CLRT_reg	2.983	+1.02	3.103	+1.15	2.018	0.945
48	Cognitive load (COGL)vn_COGL_reg	1.702	-0.37	1.579	-0.49	2.094	1.061
49	Dynamic arc (DARC)vn_DARC_reg	3.368	+1.27	3.379	+1.28	1.615	1.380
50	Disfluency (DFLU)vn_DFLU_reg	2.725	+0.20	2.718	+0.19	2.488	1.184
51	Emphasis (EMPH)vn_EMPH_reg	4.289	+1.10	4.350	+1.14	2.607	1.524
52	Esthetics (ESTH)vn_ESTH_reg	2.169	-0.30	2.158	-0.31	2.402	0.782
53	Content appropriateness (EXPL)vn_EXPL_reg	0.419	+1.03	0.456	+1.15	0.086	0.322
54	Focus (FOCS)vn_FOCS_reg	3.464	+1.02	3.507	+1.06	2.344	1.102
55	Fullness (FULL)vn_FULL_reg	1.078	-0.79	1.029	-0.84	1.778	0.889
56	Perceived gender (GEND)vn_GEND_reg	4.808	+0.47	4.653	+0.38	4.055	1.588
57	Harmonicity (HARM)vn_HARM_reg	2.665	+0.22	2.779	+0.36	2.480	0.836
58	Metallic character (METL)vn_METL_reg	2.642	+1.06	2.443	+0.86	1.621	0.958
59	Pitch range (RANG)vn_RANG_reg	3.588	+0.75	3.483	+0.63	2.914	0.897
60	Recording quality (RCQL)vn_RCQL_reg	2.080	-0.76	1.950	-0.91	2.754	0.888
61	Vocal register (REGS)vn_REGS_reg	0.844	-0.28	0.883	-0.25	1.198	1.268
62	Respiration (RESP)vn_RESP_reg	3.248	+0.54	3.440	+0.72	2.680	1.056
63	Roughness (ROUG)vn_ROUG_reg	3.194	+1.31	3.387	+1.53	2.033	0.887
64	Chest resonance (R_CHST)vn_R_CHST_reg	2.728	+0.70	2.479	+0.41	2.135	0.844
65	Head resonance (R_HEAD)vn_R_HEAD_reg	2.459	+0.38	2.558	+0.50	2.148	0.822
66	Mask resonance (R_MASK)vn_R_MASK_reg	2.235	+0.32	2.411	+0.50	1.908	1.005
67	Mixed resonance (R_MIXD)vn_R_MIXD_reg	1.144	-0.35	1.053	-0.46	1.436	0.841
68	Nasal resonance (R_NASL)vn_R_NASL_reg	4.624	+1.75	4.657	+1.78	2.791	1.047
69	Oral resonance (R_ORAL)vn_R_ORAL_reg	2.992	+1.09	3.027	+1.14	2.184	0.741
70	Throat resonance (R_THRT)vn_R_THRT_reg	1.888	-0.23	1.669	-0.50	2.070	0.803
71	Smoothness (SMTH)vn_SMTH_reg	2.623	+0.44	2.662	+0.48	2.143	1.093
72	Stance (STNC)vn_STNC_reg	4.700	+1.82	4.691	+1.81	2.633	1.137
73	Speech structure (STRU)vn_STRU_reg	2.391	+0.27	2.434	+0.31	2.137	0.958
74	ASMR style (S_ASMR)vn_S_ASMR_reg	0.187	-0.84	0.036	-0.95	1.370	1.411
75	Authoritative style (S_AUTH)vn_S_AUTH_reg	3.119	+1.95	2.916	+1.75	1.088	1.043
76	Cartoonish style (S_CART)vn_S_CART_reg	2.952	+0.99	3.006	+1.03	1.560	1.401
77	Casual style (S_CASU)vn_S_CASU_reg	4.717	+0.72	4.882	+0.85	3.793	1.278
78	Conversational style (S_CONV)vn_S_CONV_reg	1.947	-0.49	1.860	-0.56	2.594	1.318
79	Dramatic style (S_DRAM)vn_S_DRAM_reg	4.284	+1.36	4.070	+1.17	2.721	1.148
80	Formal style (S_FORM)vn_S_FORM_reg	0.769	-0.42	0.816	-0.37	1.195	1.021
81	Monologue style (S_MONO)vn_S_MONO_reg	2.824	+0.00	3.121	+0.23	2.824	1.284
82	Narrator style (S_NARR)vn_S_NARR_reg	0.499	-0.56	0.471	-0.58	1.307	1.446
83	Newsreader style (S_NEWS)vn_S_NEWS_reg	0.529	+0.21	0.494	+0.15	0.408	0.568
84	Playful style (S_PLAY)vn_S_PLAY_reg	3.335	+0.75	3.157	+0.61	2.352	1.315
85	Ranting or angry style (S_RANT)vn_S_RANT_reg	3.587	+1.84	3.498	+1.77	1.213	1.289
86	Storytelling style (S_STRY)vn_S_STRY_reg	3.823	+0.98	3.725	+0.91	2.480	1.366
87	Teacher or didactic style (S_TECH)vn_S_TECH_reg	0.511	-0.11	0.763	+0.09	0.646	1.227
88	Whispered talking style (S_WHIS)vn_S_WHIS_reg	0.187	-0.87	0.462	-0.70	1.597	1.618
89	Tempo (TEMP)vn_TEMP_reg	3.907	+1.50	4.029	+1.61	2.117	1.190
90	Tension (TENS)vn_TENS_reg	2.817	+1.48	2.745	+1.39	1.559	0.852
91	Valence (VALN)vn_VALN_reg	2.906	+0.52	2.782	+0.41	2.328	1.118
92	Valence shift (VALS)vn_VALS_reg	2.558	+0.04	2.385	-0.12	2.518	1.079
93	Velocity flux (VFLX)vn_VFLX_reg	2.839	+0.48	2.891	+0.53	2.256	1.208
94	Volatility (VOLT)vn_VOLT_reg	2.889	+0.34	2.874	+0.32	2.586	0.886
95	Vulnerability (VULN)vn_VULN_reg	1.107	-1.57	1.138	-1.53	2.648	0.984
96	Warmth (WARM)vn_WARM_reg	2.222	-0.39	2.086	-0.54	2.578	0.909
Genuineness, blend, and legacy quality Genuineness and vocal-burst blend are predicted. R_quality has Ladder training labels but no valid P3 test labels.
97	Genuineness (0–6)genuineness_0_6	3.216	+0.55	3.051	+0.44	2.332	1.621
98	Vocal-burst blend (0–10)blend_0_10	6.817	+0.05	6.961	+0.10	6.676	2.738
99	Legacy R_quality (no P3 test labels)R_quality	1.222	+0.38	1.206	+0.33	1.095	0.338
Empathic Insight Plus extra scores Nineteen additional clip-level teacher scores, including background noise and content enjoyment.
100	Ageeiv_extra:Age	3.317	+0.23	3.225	-0.09	3.250	0.293
101	Arousaleiv_extra:Arousal	1.762	+1.09	1.872	+1.34	1.289	0.435
102	Authenticityeiv_extra:Authenticity	2.726	+0.38	2.746	+0.52	2.667	0.153
103	Background Noiseeiv_extra:Background_Noise	0.698	-0.41	0.549	-0.98	0.808	0.264
104	Confident vs. Hesitanteiv_extra:Confident_vs._Hesitant	1.211	+0.56	1.110	+0.23	1.040	0.303
105	Gendereiv_extra:Gender	-1.048	-0.43	-0.947	-0.33	-0.621	0.999
106	High-Pitched vs. Low-Pitchedeiv_extra:High-Pitched_vs._Low-Pitched	2.067	+0.96	2.039	+0.85	1.827	0.250
107	Monotone vs. Expressiveeiv_extra:Monotone_vs._Expressive	2.414	+1.18	2.440	+1.24	1.859	0.470
108	Recording Qualityeiv_extra:Recording_Quality	2.165	+0.06	2.277	+0.40	2.144	0.332
109	Serious vs. Humorouseiv_extra:Serious_vs._Humorous	0.955	+0.08	1.053	+0.36	0.929	0.340
110	Soft vs. Harsheiv_extra:Soft_vs._Harsh	0.011	-0.84	0.232	-0.15	0.281	0.320
111	Submissive vs. Dominanteiv_extra:Submissive_vs._Dominant	1.010	+1.96	0.836	+1.42	0.376	0.324
112	Valenceeiv_extra:Valence	-0.155	-0.42	-0.011	-0.04	0.005	0.380
113	Vulnerable vs. Emotionally Detachedeiv_extra:Vulnerable_vs._Emotionally_Detached	1.819	+0.24	1.752	+0.09	1.715	0.437
114	Warm vs. Coldeiv_extra:Warm_vs._Cold	-0.177	-0.76	0.119	+0.23	0.051	0.300
115	score background qualityeiv_extra:score_background_quality	3.678	+0.54	3.740	+0.63	3.301	0.693
116	score content enjoymenteiv_extra:score_content_enjoyment	4.732	+0.74	4.840	+1.10	4.507	0.303
117	score overall qualityeiv_extra:score_overall_quality	3.088	+0.86	3.111	+0.91	2.652	0.507
118	score speech qualityeiv_extra:score_speech_quality	1.945	+0.94	1.962	+1.06	1.808	0.146
Meta AudioBox Aesthetics Four AudioBox aesthetic teacher outputs. Expansions follow the official Meta model card.
119	Content enjoyment (CE)audiobox:CE	5.447	+0.64	5.276	+0.47	4.799	1.018
120	Content usefulness (CU)audiobox:CU	6.058	+0.41	6.128	+0.48	5.649	1.001
121	Production complexity (PC)audiobox:PC	1.972	-0.22	1.744	-0.36	2.331	1.617
122	Production quality (PQ)audiobox:PQ	7.328	+0.32	7.248	+0.23	7.044	0.879
Microsoft DNSMOS Seven DNSMOS teacher outputs: raw and calibrated SIG/BAK/OVRL estimates plus P.808 MOS.
123	Speech signal quality, rawdnsmos:SIG_raw	4.048	+0.22	4.053	+0.23	3.900	0.669
124	Background quality, rawdnsmos:BAK_raw	4.250	+0.92	4.149	+0.83	3.211	1.124
125	Overall quality, rawdnsmos:OVRL_raw	3.770	+0.84	3.691	+0.75	3.085	0.812
126	Speech signal quality, calibrateddnsmos:SIG	3.560	+0.14	3.585	+0.19	3.488	0.501
127	Background quality, calibrateddnsmos:BAK	4.028	+0.69	3.977	+0.63	3.389	0.928
128	Overall quality, calibrateddnsmos:OVRL	3.285	+0.73	3.236	+0.65	2.840	0.606
129	P.808 MOS estimatednsmos:P808_MOS	3.696	+0.55	3.674	+0.51	3.421	0.496
Vocal-burst count The regression target is log(1 + count). A separate table also reports count error after inverse transformation.
130	Vocal-burst count, log(1 + count)burst_count_log1p	0.002	+0.00	0.002	+0.00	0.000	0.647
VoiceCLAP attributes Sixty-one individual VoiceCLAP attribute teacher scores. The raw 768D VoiceCLAP embedding is stored in sidecars but is not a model output.
131	Affectionvoiceclap_attribute:Affection	1.060	+0.20	1.086	+0.25	0.947	0.554
132	Agevoiceclap_attribute:Age	3.357	+0.24	3.306	+0.14	3.229	0.547
133	Amusementvoiceclap_attribute:Amusement	0.798	+0.71	0.701	+0.54	0.392	0.572
134	Angervoiceclap_attribute:Anger	2.246	+2.48	2.198	+2.38	0.992	0.506
135	Arousalvoiceclap_attribute:Arousal	2.666	+2.00	2.680	+2.03	1.420	0.622
136	Astonishment Surprisevoiceclap_attribute:Astonishment_Surprise	0.656	+0.31	0.967	+0.96	0.509	0.479
137	Authenticityvoiceclap_attribute:Authenticity	2.921	+0.90	2.943	+1.04	2.770	0.167
138	Awevoiceclap_attribute:Awe	0.580	+0.16	0.780	+0.93	0.539	0.259
139	Background Noisevoiceclap_attribute:Background_Noise	0.637	+0.26	0.626	+0.22	0.567	0.264
140	Bitternessvoiceclap_attribute:Bitterness	1.061	+1.99	1.044	+1.91	0.592	0.236
141	Concentrationvoiceclap_attribute:Concentration	1.012	-0.38	1.312	+0.18	1.214	0.531
142	Confident vs. Hesitantvoiceclap_attribute:Confident_vs._Hesitant	1.079	+0.02	1.263	+0.41	1.069	0.468
143	Confusionvoiceclap_attribute:Confusion	0.640	-0.01	0.836	+0.58	0.643	0.334
144	Contemplationvoiceclap_attribute:Contemplation	0.447	-0.82	0.493	-0.71	0.780	0.406
145	Contemptvoiceclap_attribute:Contempt	1.378	+1.98	1.314	+1.79	0.709	0.339
146	Contentmentvoiceclap_attribute:Contentment	0.543	-0.15	0.464	-0.41	0.588	0.307
147	Disappointmentvoiceclap_attribute:Disappointment	1.369	+2.09	1.446	+2.36	0.760	0.291
148	Disgustvoiceclap_attribute:Disgust	1.072	+2.16	1.031	+1.96	0.625	0.207
149	Distressvoiceclap_attribute:Distress	1.481	+1.59	1.615	+1.97	0.927	0.350
150	Doubtvoiceclap_attribute:Doubt	0.338	-1.05	0.455	-0.42	0.535	0.188
151	Elationvoiceclap_attribute:Elation	1.034	+1.25	0.947	+1.03	0.539	0.397
152	Embarrassmentvoiceclap_attribute:Embarrassment	0.221	-0.27	0.361	+0.17	0.307	0.314
153	Emotional Numbnessvoiceclap_attribute:Emotional_Numbness	0.405	-0.97	0.427	-0.89	0.664	0.266
154	Fatigue Exhaustionvoiceclap_attribute:Fatigue_Exhaustion	0.543	+0.31	0.449	-0.05	0.462	0.261
155	Fearvoiceclap_attribute:Fear	0.807	+0.89	0.834	+1.02	0.618	0.212
156	Gendervoiceclap_attribute:Gender	-1.414	-1.26	-1.312	-1.16	-0.151	1.005
157	Helplessnessvoiceclap_attribute:Helplessness	0.778	+0.45	0.954	+1.10	0.658	0.268
158	High-Pitched vs. Low-Pitchedvoiceclap_attribute:High-Pitched_vs._Low-Pitched	2.266	+1.14	2.284	+1.18	1.840	0.375
159	Hope Enthusiasm Optimismvoiceclap_attribute:Hope_Enthusiasm_Optimism	1.451	+1.88	1.519	+2.06	0.705	0.396
160	Impatience and Irritabilityvoiceclap_attribute:Impatience_and_Irritability	2.518	+2.71	2.848	+3.32	1.052	0.541
161	Infatuationvoiceclap_attribute:Infatuation	0.352	-0.77	0.543	-0.19	0.608	0.332
162	Interestvoiceclap_attribute:Interest	1.799	+0.46	1.806	+0.47	1.598	0.440
163	Intoxication Altered States of Consciousnessvoiceclap_attribute:Intoxication_Altered_States_of_Consciousness	0.717	+0.46	0.921	+0.90	0.502	0.463
164	Jealousy & Envyvoiceclap_attribute:Jealousy_&_Envy	0.912	+1.59	1.160	+2.60	0.523	0.245
165	Longingvoiceclap_attribute:Longing	0.516	-0.10	0.525	-0.06	0.538	0.220
166	Malevolence Malicevoiceclap_attribute:Malevolence_Malice	1.479	+1.87	1.525	+2.00	0.833	0.346
167	Monotone vs. Expressivevoiceclap_attribute:Monotone_vs._Expressive	2.846	+1.80	2.921	+1.93	1.775	0.594
168	Painvoiceclap_attribute:Pain	0.441	+0.27	0.633	+1.15	0.381	0.218
169	Pleasure Ecstasyvoiceclap_attribute:Pleasure_Ecstasy	0.734	+0.77	0.692	+0.63	0.503	0.301
170	Pridevoiceclap_attribute:Pride	1.284	+1.44	1.224	+1.27	0.780	0.349
171	Recording Qualityvoiceclap_attribute:Recording_Quality	2.185	-0.39	2.091	-0.68	2.313	0.328
172	Reliefvoiceclap_attribute:Relief	0.854	-0.41	0.793	-0.56	1.025	0.415
173	Sadnessvoiceclap_attribute:Sadness	0.906	+0.49	0.997	+0.78	0.752	0.313
174	Serious vs. Humorousvoiceclap_attribute:Serious_vs._Humorous	0.790	-0.02	0.783	-0.04	0.803	0.568
175	Sexual Lustvoiceclap_attribute:Sexual_Lust	0.464	-0.41	0.718	+0.20	0.635	0.419
176	Shamevoiceclap_attribute:Shame	0.794	+0.94	0.929	+1.42	0.526	0.283
177	Soft vs. Harshvoiceclap_attribute:Soft_vs._Harsh	-0.543	-1.95	-0.600	-2.11	0.160	0.360
178	Sournessvoiceclap_attribute:Sourness	1.186	+1.65	1.225	+1.79	0.706	0.291
179	Submissive vs. Dominantvoiceclap_attribute:Submissive_vs._Dominant	1.613	+2.76	1.372	+2.09	0.623	0.359
180	Teasingvoiceclap_attribute:Teasing	0.638	+0.26	0.336	-0.54	0.540	0.379
181	Thankfulness Gratitudevoiceclap_attribute:Thankfulness_Gratitude	2.086	+1.33	2.074	+1.30	1.384	0.529
182	Triumphvoiceclap_attribute:Triumph	1.213	+1.38	1.132	+1.16	0.716	0.359
183	Valencevoiceclap_attribute:Valence	-1.592	-2.50	-2.067	-3.25	-0.007	0.635
184	Vulnerable vs. Emotionally Detachedvoiceclap_attribute:Vulnerable_vs._Emotionally_Detached	1.533	-0.19	1.420	-0.39	1.638	0.556
185	Warm vs. Coldvoiceclap_attribute:Warm_vs._Cold	-0.618	-1.38	-0.774	-1.77	-0.066	0.400
186	durationvoiceclap_attribute:duration	11.289	+0.06	11.646	+0.12	10.914	6.354
187	score background qualityvoiceclap_attribute:score_background_quality	3.509	+0.53	3.653	+0.82	3.245	0.498
188	score content enjoymentvoiceclap_attribute:score_content_enjoyment	4.720	+0.44	4.675	+0.13	4.656	0.147
189	score overall qualityvoiceclap_attribute:score_overall_quality	2.923	+0.70	2.973	+0.82	2.635	0.412
190	score speech qualityvoiceclap_attribute:score_speech_quality	1.970	+1.14	1.959	+0.98	1.891	0.069
191	talking speedvoiceclap_attribute:talking_speed	17.983	+2.38	19.507	+2.79	9.028	3.756

All Orange embedding components

The cosine above is the meaningful vector-level comparison; component values have no standalone semantic label.

Timbre — all 128 vector components

Dimension	Tiny	Base	Orange teacher
0	0.0471	0.0198	0.0130
1	-0.0234	0.0204	-0.0855
2	-0.0651	-0.0565	-0.0844
3	-0.0471	-0.1118	-0.0872
4	-0.1090	-0.1182	-0.0809
5	-0.1303	-0.1177	-0.1089
6	-0.0322	-0.0229	-0.0780
7	0.0428	0.0926	0.1024
8	0.0527	-0.0319	0.0675
9	-0.0719	-0.0781	-0.0079
10	0.0680	0.0472	0.0956
11	-0.0556	-0.0903	-0.0572
12	-0.0223	-0.0192	-0.0074
13	-0.0892	-0.0746	-0.0849
14	-0.0605	-0.0897	-0.0846
15	-0.0906	-0.0920	-0.0771
16	-0.0697	-0.0390	-0.0649
17	-0.0690	-0.1124	-0.0406
18	-0.0033	-0.0213	-0.0356
19	-0.0811	-0.0600	-0.0814
20	0.1232	0.1316	0.1124
21	-0.0026	-0.0069	-0.0238
22	-0.0800	-0.0743	-0.0809
23	-0.0434	-0.0574	0.0479
24	-0.0779	-0.0652	-0.0695
25	-0.0418	-0.0620	-0.0623
26	-0.0150	0.0130	-0.0807
27	-0.0085	0.0022	0.0948
28	-0.0239	-0.0513	-0.0203
29	0.0032	0.1153	0.0784
30	0.2237	0.1910	0.1646
31	0.0025	-0.0460	-0.0720
32	-0.0927	-0.0868	-0.0829
33	-0.1048	-0.0984	-0.0948
34	-0.0271	-0.0571	-0.0771
35	0.2520	0.3192	0.2593
36	-0.0814	-0.0856	-0.0925
37	-0.0843	-0.1008	-0.0808
38	-0.0556	-0.0786	-0.0806
39	-0.1041	-0.1037	-0.0868
40	-0.0556	-0.0571	-0.0417
41	-0.1416	-0.1182	-0.1237
42	0.0573	0.0603	0.0535
43	0.0327	0.0472	0.0161
44	0.3087	0.2621	0.2137
45	0.0754	0.1235	0.1271
46	-0.1012	-0.0804	-0.0553
47	-0.0867	-0.0914	-0.0870
48	-0.0135	-0.0373	-0.0781
49	0.0450	0.0390	0.0533
50	0.0612	0.0798	0.0515
51	-0.1062	-0.0880	-0.0860
52	0.0404	0.0044	0.0434
53	0.0747	0.0716	0.0800
54	-0.1062	-0.1194	-0.0963
55	0.1912	0.2109	0.1543
56	-0.0151	-0.0469	-0.0816
57	-0.1175	-0.1444	-0.0944
58	0.0166	0.0067	0.0556
59	0.0280	0.0319	0.0718
60	-0.0437	-0.0454	-0.0830
61	0.2393	0.2132	0.2498
62	-0.0913	-0.0626	-0.0804
63	-0.0250	-0.0728	-0.0817
64	0.0347	0.0728	0.0214
65	-0.0935	-0.0821	-0.0702
66	0.1168	0.1223	0.0883
67	-0.0977	-0.0705	-0.0830
68	-0.1260	-0.1002	-0.0909
69	-0.0835	-0.0850	-0.0789
70	0.1076	0.0996	0.0889
71	-0.0207	0.0013	-0.0190
72	-0.0775	-0.0533	-0.0833
73	0.0389	0.0577	0.0536
74	-0.1189	-0.0702	-0.0940
75	0.0366	0.0513	0.1032
76	0.0087	0.0347	0.0209
77	-0.0221	-0.0092	-0.0694
78	0.0388	-0.0161	-0.0061
79	-0.0811	-0.0719	-0.0746
80	-0.0942	-0.0218	-0.0779
81	0.0464	0.0833	-0.0023
82	-0.0814	-0.0996	-0.0823
83	-0.1133	-0.1025	-0.0881
84	0.0690	0.0792	0.1362
85	0.0335	0.0431	0.0212
86	-0.0906	-0.0880	-0.0359
87	-0.0789	-0.0909	-0.0541
88	-0.0230	-0.0530	-0.0518
89	-0.0619	-0.0518	-0.0790
90	-0.1041	-0.1182	-0.0933
91	0.1494	0.1264	0.1476
92	-0.1005	-0.0647	-0.0836
93	0.1791	0.1462	0.1476
94	0.0864	0.0746	0.0850
95	-0.0023	-0.0119	-0.0616
96	-0.1019	-0.0632	-0.0864
97	-0.0102	0.0098	0.0358
98	0.0485	0.0365	0.0994
99	0.0715	0.0002	0.1017
100	0.0687	0.1072	0.0753
101	0.0634	0.1078	0.0679
102	-0.0368	-0.0513	-0.0375
103	-0.1069	-0.0714	-0.0908
104	-0.0489	-0.0536	-0.0775
105	-0.0605	-0.0708	0.0001
106	-0.0765	-0.0664	-0.1035
107	0.0180	0.0396	-0.0022
108	-0.0004	0.0181	-0.0317
109	-0.0704	-0.0850	-0.0844
110	0.0142	-0.0316	-0.0179
111	-0.0761	-0.0786	-0.0999
112	-0.0935	-0.0845	-0.0848
113	0.1409	0.1340	0.1059
114	-0.0448	-0.0367	0.0175
115	0.0782	0.0909	0.1707
116	-0.0489	-0.0052	-0.0458
117	0.1175	0.1025	0.1576
118	-0.1196	-0.1165	-0.0838
119	0.1090	0.1334	0.0360
120	-0.0761	-0.0661	-0.0717
121	0.0517	0.0349	0.1310
122	-0.0726	-0.0734	-0.0884
123	-0.1232	-0.0454	-0.0801
124	-0.0036	-0.0119	-0.0724
125	0.0322	0.0249	0.0513
126	-0.0271	-0.0743	0.0001
127	0.0365	-0.0050	0.1081

Identity — all 250 vector components

Dimension	Tiny	Base	Orange teacher
0	0.0250	0.0224	0.0592
1	-0.0012	-0.0097	0.0052
2	0.0474	0.0265	0.0562
3	-0.0277	0.0137	-0.0368
4	0.0105	0.0061	-0.0422
5	-0.0489	-0.0624	-0.0485
6	0.0222	0.0540	-0.0089
7	0.0017	0.0117	-0.0470
8	-0.0115	0.0475	-0.0105
9	0.0235	-0.0018	0.0372
10	0.0315	0.0225	0.0583
11	-0.0241	-0.0550	-0.0040
12	-0.0543	-0.0453	-0.0508
13	-0.0565	-0.0369	-0.0410
14	-0.0481	-0.0301	-0.0085
15	0.0335	0.0770	0.1059
16	0.0926	0.0963	0.0428
17	-0.0481	-0.0244	0.0083
18	-0.0609	-0.0312	-0.0314
19	0.0112	-0.0040	-0.0174
20	0.1196	0.0745	0.0646
21	-0.0645	-0.0708	-0.0430
22	-0.0343	-0.0289	-0.0482
23	-0.1072	-0.0863	-0.0449
24	0.0439	0.0584	0.0143
25	0.0048	0.0447	-0.0853
26	0.0653	-0.0102	0.0039
27	0.0317	0.0175	0.0878
28	0.0503	0.0761	0.0321
29	-0.0853	-0.0869	-0.0446
30	0.0441	0.0487	-0.0237
31	0.1327	0.1099	0.1776
32	0.0609	0.0782	-0.0478
33	0.0315	0.0125	0.0258
34	0.0252	0.0164	-0.0475
35	-0.0070	0.0070	-0.0598
36	0.0383	0.0048	0.0440
37	0.0202	0.0077	-0.0321
38	0.0359	0.0222	-0.0344
39	-0.0882	-0.1012	-0.0605
40	-0.0467	-0.0404	-0.0537
41	0.0664	0.0574	0.0258
42	-0.0284	-0.0039	-0.0461
43	0.0740	0.1273	-0.0548
44	0.0857	0.0975	0.0192
45	-0.0489	-0.0255	0.0164
46	-0.0463	-0.0646	-0.0275
47	-0.0062	0.0067	-0.0593
48	0.0034	-0.0227	-0.0495
49	-0.0459	-0.0602	-0.0170
50	-0.0456	-0.0689	-0.0867
51	0.0407	0.0382	0.0020
52	0.0540	0.0857	-0.0066
53	0.0134	0.0211	0.0256
54	0.0882	0.1192	0.0942
55	0.0405	0.0251	0.0477
56	0.0272	0.0422	0.1199
57	-0.0525	-0.0711	-0.0542
58	-0.0277	-0.0283	-0.0207
59	0.0165	0.0133	0.0559
60	-0.0155	0.0171	-0.0124
61	-0.0514	-0.0612	-0.0431
62	-0.0407	-0.0494	-0.0408
63	-0.0323	-0.0290	-0.0504
64	-0.0225	-0.0003	-0.0517
65	0.0268	0.0193	0.0376
66	-0.0292	-0.0247	-0.0585
67	-0.0131	-0.0167	-0.0488
68	-0.0478	-0.0315	-0.0500
69	0.0059	0.0696	-0.0043
70	-0.0872	-0.0727	-0.0673
71	0.0061	0.0025	0.0018
72	-0.0335	0.0000	-0.0185
73	0.1203	0.1118	0.0608
74	0.0215	0.0151	-0.0501
75	0.0682	0.0913	0.0815
76	0.0261	0.0506	0.0094
77	-0.0799	-0.0612	-0.0370
78	-0.0283	-0.0460	0.0085
79	0.0500	0.0351	0.0417
80	-0.1437	-0.1217	-0.0493
81	0.0111	0.0238	-0.0556
82	-0.0496	-0.0714	-0.0446
83	-0.0627	-0.0259	-0.0412
84	-0.0009	0.0460	0.1010
85	0.0070	0.0139	0.0889
86	0.0165	0.0404	-0.0443
87	-0.0281	-0.0245	0.0309
88	0.0465	0.0438	0.0684
89	0.0292	0.0258	-0.0409
90	-0.0780	-0.0652	-0.0491
91	-0.0999	-0.1466	-0.0583
92	0.0248	0.0253	0.0226
93	0.0583	0.0543	-0.0562
94	-0.0441	-0.0696	-0.0660
95	-0.0773	-0.0621	-0.0517
96	0.0044	0.0290	0.0353
97	-0.0496	-0.0362	-0.0584
98	-0.0015	0.0158	-0.0358
99	-0.0478	-0.0060	0.0156
100	-0.0511	-0.0328	-0.0221
101	-0.0368	-0.0088	-0.0468
102	0.0150	0.0435	-0.0297
103	0.0012	0.0419	-0.0095
104	-0.1130	-0.0888	-0.0646
105	-0.0624	-0.0779	0.0257
106	-0.0729	-0.0717	-0.0382
107	-0.0660	-0.0312	-0.0444
108	0.1167	0.1714	0.2168
109	-0.0067	-0.0095	0.0401
110	-0.0664	-0.0674	-0.0590
111	-0.0726	-0.0126	-0.0408
112	-0.0303	-0.0216	-0.0400
113	0.0853	0.0987	0.0452
114	-0.0784	-0.0596	-0.0572
115	-0.0383	-0.0030	-0.0351
116	-0.0129	-0.0042	0.0243
117	-0.0078	-0.0587	-0.0629
118	-0.0376	-0.0404	0.0024
119	-0.0454	-0.0404	-0.0510
120	-0.0184	-0.0416	-0.0416
121	0.0177	0.0185	-0.0269
122	-0.0948	-0.1037	-0.0468
123	-0.0142	-0.0250	0.0867
124	0.0602	0.0491	0.0327
125	-0.0707	-0.0723	-0.0482
126	0.1357	0.1335	0.1098
127	-0.0195	-0.0134	-0.0510
128	0.0039	0.0029	0.0009
129	0.0762	0.1099	0.0913
130	-0.0341	-0.0609	-0.0498
131	0.0470	0.0143	-0.0303
132	0.0511	0.0503	-0.0523
133	0.0018	-0.0390	0.0325
134	0.0839	0.0593	0.0210
135	-0.0202	-0.0008	-0.0499
136	-0.0222	-0.0120	-0.0523
137	0.0718	-0.0109	-0.0065
138	0.0232	0.0312	-0.0092
139	0.0474	0.0550	-0.0354
140	-0.0335	-0.0182	-0.0584
141	0.0474	0.1025	-0.0265
142	-0.0642	-0.0500	-0.0428
143	0.0394	0.0227	0.0031
144	-0.0955	-0.0919	-0.0516
145	0.0308	0.0245	0.0881
146	0.1692	0.1838	0.1093
147	-0.0148	-0.0208	0.0197
148	0.1050	0.1366	0.0919
149	0.0704	0.0562	0.1973
150	0.1218	0.1118	-0.0040
151	-0.0532	-0.0404	0.0200
152	-0.0388	-0.0156	-0.0550
153	0.0110	0.0168	0.0242
154	0.0121	0.0224	0.0438
155	-0.0230	-0.0366	-0.0646
156	0.0328	-0.0036	-0.0050
157	0.0886	0.0671	0.0351
158	-0.0235	0.0087	-0.0617
159	0.0766	0.0618	0.0346
160	0.0292	0.0450	0.1216
161	0.0261	0.0022	-0.0600
162	-0.0842	-0.0671	-0.0575
163	-0.0806	-0.0581	-0.0552
164	-0.0485	-0.0120	-0.0435
165	-0.0094	-0.0200	0.0002
166	0.0078	0.0349	-0.0261
167	-0.1371	-0.1397	-0.0628
168	0.0605	0.0633	0.0880
169	0.1160	0.0807	-0.0152
170	-0.0250	-0.0135	-0.0464
171	-0.0257	-0.0531	-0.0436
172	0.0788	0.0969	0.0356
173	0.0201	0.0711	0.0969
174	-0.0190	-0.0167	-0.0509
175	-0.0653	-0.0826	-0.0821
176	0.0740	0.0584	0.1090
177	-0.0562	-0.0295	-0.0408
178	-0.0059	-0.0230	-0.0440
179	0.0777	0.0826	0.0853
180	0.1940	0.1875	0.1345
181	-0.0711	-0.0394	-0.0252
182	-0.0613	-0.0696	-0.0428
183	-0.0853	-0.0463	-0.0919
184	-0.0041	0.0441	-0.0105
185	0.0872	0.0528	-0.0031
186	-0.0616	-0.0481	-0.0598
187	0.0868	0.0432	0.0818
188	0.0252	0.0145	0.0748
189	0.0613	0.0374	0.0684
190	0.0097	0.0251	0.0212
191	0.0418	0.0332	0.0512
192	0.1291	0.1348	0.0683
193	0.0465	0.0683	0.0425
194	0.0237	0.0286	-0.0050
195	-0.0052	-0.0137	-0.0238
196	0.0396	0.0845	0.0920
197	0.1575	0.1223	0.1163
198	-0.0228	-0.0174	-0.0479
199	0.0536	0.0692	-0.0267
200	-0.0299	-0.0416	-0.0573
201	0.0150	0.0391	-0.0025
202	-0.0624	-0.0699	-0.1030
203	0.0744	0.0717	0.0454
204	0.0667	0.0149	0.1277
205	-0.0635	-0.0668	0.0496
206	0.0192	0.0562	0.0168
207	-0.0304	0.0031	0.0507
208	-0.0376	-0.0671	-0.0514
209	-0.0418	-0.0158	0.0122
210	0.1641	0.1074	0.1705
211	-0.0182	-0.0447	0.0153
212	0.0591	0.0770	0.1877
213	-0.0217	-0.0047	0.0842
214	0.2567	0.2621	0.2839
215	-0.0266	-0.0245	-0.0416
216	-0.0439	-0.0463	-0.0593
217	-0.0879	-0.0338	-0.0464
218	-0.0227	-0.0882	-0.0280
219	-0.0346	0.0002	-0.0591
220	-0.0817	-0.0689	-0.0547
221	0.0390	0.0022	0.0295
222	-0.0403	0.0037	0.0509
223	-0.0704	-0.0475	-0.0397
224	0.0001	0.0092	0.0677
225	0.0507	0.0334	0.0769
226	-0.0507	-0.0206	0.0230
227	0.0343	0.1031	0.0678
228	-0.0150	-0.0314	-0.0787
229	0.0049	0.0038	-0.0543
230	0.0620	0.0500	0.0845
231	0.0430	0.0621	0.0327
232	-0.0410	0.0161	0.0312
233	-0.0264	-0.0571	-0.0684
234	0.1823	0.1851	0.0175
235	0.2028	0.1801	0.0648
236	-0.0241	-0.0306	-0.0425
237	-0.0197	-0.0328	-0.0506
238	0.0410	0.0298	0.0779
239	-0.0052	0.0179	0.0057
240	0.0915	0.1031	0.1859
241	-0.0081	0.0144	0.0920
242	-0.0432	-0.0371	-0.0491
243	-0.0605	-0.0730	-0.0637
244	-0.0470	-0.0708	-0.0526
245	-0.0780	-0.0377	-0.0471
246	-0.0126	-0.0270	-0.0401
247	-0.0562	-0.0807	-0.0417
248	-0.0642	-0.0609	-0.0566
249	-0.0828	-0.0590	-0.0712

Source: HUMANENESS_SMALL_VOICE_IDENTITY_R1_R2_2026-10-02_mediathek_0047.html · SHA-256 c9330d9714011f2b…

g07GermanMediathek voice study

mediathek_0047 · de · 26/50

Generated TTS prediction · Rank 1 qkvo · 10.5 s

Dieser kleine Knoten auf meinem Schädel, das ist mehr als nur eine kleine lästige Sache. (soft hum) Glauben Sie mir, Dinge, die harmlos aussehen, können überraschend ernst sein.

Tiny Base · values are model estimates, not ground truth

Strongest emotions relative to training

Contempt

z +2.79 / +2.81raw 1.29 / 1.30

Sourness

z +2.56 / +2.62raw 1.12 / 1.15

Disgust

z +2.13 / +2.34raw 1.05 / 1.15

Bitterness

z +2.33 / +2.16raw 0.98 / 0.91

Anger

z +2.09 / +2.14raw 1.29 / 1.32

Disappointment

z +1.74 / +1.94raw 1.22 / 1.36

Impatience and Irritability

z +1.76 / +1.94raw 1.39 / 1.52

The center of each bar is the S9 teacher median. Positive z is to the right; negative z is to the left. Ranking uses z, not raw teacher units.

Strongest VoiceNet dimensions relative to training

Authoritative style (S_AUTH)

z +2.73 / +2.59raw 3.94 / 3.79

Newsreader style (S_NEWS)

z +2.72 / +2.49raw 1.95 / 1.82

Cartoonish style (S_CART)

z +2.35 / +2.57raw 4.85 / 5.17

Tension (TENS)

z +2.35 / +2.38raw 3.56 / 3.58

Nasal resonance (R_NASL)

z +1.91 / +1.81raw 4.79 / 4.69

Metallic character (METL)

z +1.72 / +1.69raw 3.27 / 3.24

Ranting or angry style (S_RANT)

z +1.69 / +1.63raw 3.40 / 3.32

All 57 VoiceNet predictions, including raw units, are in the full table below. These seven are ranked by z; the top values may differ from the strongest raw dimensions.

Voice, speed and quality scores in context

Genuineness (0–6)z -0.55 / -0.65raw 1.44 / 1.28

Vocal-burst blend (0–10)z -1.39 / -1.43raw 2.86 / 2.76

Content enjoyment (CE)z +0.37 / +0.49raw 5.18 / 5.30

Production quality (PQ)z +0.19 / +0.29raw 7.21 / 7.30

Speech signal quality, calibratedz +0.03 / +0.27raw 3.50 / 3.62

Background quality, calibratedz +0.52 / +0.57raw 3.87 / 3.92

Overall quality, calibratedz +0.49 / +0.68raw 3.14 / 3.25

P.808 MOS estimatez +0.87 / +0.80raw 3.85 / 3.82

score content enjoymentz +0.72 / +0.79raw 4.72 / 4.75

score overall qualityz +0.53 / +0.86raw 2.92 / 3.09

Background Noisez -0.63 / -0.22raw 0.64 / 0.75

Tempo (TEMP)z +0.20 / +0.21raw 2.36 / 2.37

Arousal (AROU)z +1.36 / +1.29raw 3.92 / 3.84

Valence (VALN)z +0.30 / +0.20raw 2.66 / 2.55

Recording quality (RCQL)z -0.69 / -0.67raw 2.14 / 2.16

Background noise (BKGN)z -0.02 / -0.09raw 2.69 / 2.63

talking speedz +1.19 / +0.87raw 13.50 / 12.30

Characters per second (CPS): 16.84 raw · z +2.08

Orange speaker embedding reconstruction

Cosine against Orange on this same clip (higher means closer to that teacher vector):

Embedding	Tiny	Base
Timbre · 128D	0.860	0.869
Identity · 250D	0.796	0.777

Vocal-burst regions

Tiny

Base

0 s10.5 s

Verified burst intervals are unavailable for this clip.

Tiny: 0 regions, count-head estimate 0.00; Base: 0 regions, count-head estimate 0.00.

Exact predicted start and end times

Model	Region	Start (s)	End (s)	Duration (s)

All 192 score slots · raw and z values

#	Target	Tiny raw	Tiny z	Base raw	Base z	Train median	Train SD
Emotion scores Forty clip-level Empathic Insight emotion teacher outputs. Each row evaluates one named emotion score.
0	Affectionemo_Affection	0.059	+0.09	0.032	+0.04	0.007	0.570
1	Amusementemo_Amusement	0.426	+0.48	0.378	+0.43	-0.001	0.885
2	Angeremo_Anger	1.285	+2.09	1.317	+2.14	0.004	0.613
3	Astonishment Surpriseemo_Astonishment_Surprise	0.118	+0.20	0.048	+0.07	0.005	0.572
4	Aweemo_Awe	0.021	+0.05	-0.004	-0.01	0.000	0.427
5	Bitternessemo_Bitterness	0.982	+2.33	0.913	+2.16	0.013	0.415
6	Concentrationemo_Concentration	1.079	+0.60	1.067	+0.58	0.634	0.741
7	Confusionemo_Confusion	0.182	+0.34	0.099	+0.18	0.001	0.540
8	Contemplationemo_Contemplation	0.842	+1.27	0.774	+1.16	0.082	0.598
9	Contemptemo_Contempt	1.294	+2.79	1.301	+2.81	-0.000	0.464
10	Contentmentemo_Contentment	-0.031	-0.06	-0.041	-0.08	0.000	0.514
11	Disappointmentemo_Disappointment	1.218	+1.74	1.361	+1.94	0.000	0.700
12	Disgustemo_Disgust	1.050	+2.13	1.153	+2.34	0.007	0.489
13	Distressemo_Distress	1.295	+1.58	1.372	+1.67	0.000	0.821
14	Doubtemo_Doubt	0.248	+0.52	0.223	+0.47	0.006	0.466
15	Elationemo_Elation	-0.050	-0.09	-0.056	-0.09	0.012	0.728
16	Embarrassmentemo_Embarrassment	-0.003	-0.11	-0.001	-0.10	0.043	0.430
17	Emotional Numbnessemo_Emotional_Numbness	0.528	+0.57	0.312	+0.34	0.004	0.917
18	Fatigue Exhaustionemo_Fatigue_Exhaustion	0.132	+0.19	0.120	+0.17	0.028	0.539
19	Fearemo_Fear	0.845	+1.36	0.809	+1.30	0.015	0.610
20	Helplessnessemo_Helplessness	0.771	+1.11	0.724	+1.05	-0.004	0.696
21	Hope Enthusiasm Optimismemo_Hope_Enthusiasm_Optimism	0.018	-0.13	0.036	-0.11	0.117	0.760
22	Impatience and Irritabilityemo_Impatience_and_Irritability	1.391	+1.76	1.519	+1.94	0.149	0.705
23	Infatuationemo_Infatuation	0.003	+0.03	-0.025	-0.02	-0.015	0.533
24	Interestemo_Interest	1.713	+0.14	1.430	-0.18	1.589	0.907
25	Intoxication Altered States of Consciousnessemo_Intoxication_Altered_States_of_Consciousness	-0.042	-0.03	-0.032	-0.01	-0.025	0.559
26	Jealousy and Envyemo_Jealousy_and_Envy	0.354	+0.67	0.516	+1.03	0.059	0.442
27	Longingemo_Longing	0.927	+1.33	0.982	+1.42	0.087	0.632
28	Malevolence Maliceemo_Malevolence_Malice	0.845	+1.48	0.947	+1.67	0.055	0.534
29	Painemo_Pain	0.281	+0.49	0.145	+0.25	-0.002	0.579
30	Pleasure Ecstasyemo_Pleasure_Ecstasy	-0.020	-0.06	-0.023	-0.06	0.017	0.614
31	Prideemo_Pride	0.288	+0.56	0.608	+1.19	0.002	0.509
32	Reliefemo_Relief	0.148	+0.17	0.130	+0.14	0.033	0.681
33	Sadnessemo_Sadness	1.157	+1.53	1.125	+1.48	0.000	0.759
34	Sexual Lustemo_Sexual_Lust	0.022	-0.02	0.014	-0.03	0.030	0.494
35	Shameemo_Shame	0.128	+0.23	0.341	+0.64	0.013	0.510
36	Sournessemo_Sourness	1.120	+2.56	1.147	+2.62	-0.005	0.439
37	Teasingemo_Teasing	0.625	+1.15	0.606	+1.11	0.000	0.545
38	Thankfulness Gratitudeemo_Thankfulness_Gratitude	0.345	+0.44	0.295	+0.36	0.041	0.697
39	Triumphemo_Triumph	0.136	+0.27	0.320	+0.63	-0.007	0.521
VoiceNet dimensions Fifty-seven VoiceNet voice, delivery, style, and recording dimensions. Codes are expanded in the target column.
40	Perceived voice age (AGEV)vn_AGEV_reg	4.089	+0.89	3.932	+0.77	2.984	1.238
41	Arousal (AROU)vn_AROU_reg	3.915	+1.36	3.845	+1.29	2.359	1.147
42	Arousal shift (ARSH)vn_ARSH_reg	3.252	+0.77	3.180	+0.69	2.580	0.867
43	Vocal attack (ATCK)vn_ATCK_reg	4.341	+1.68	4.258	+1.62	2.162	1.295
44	Background noise (BKGN)vn_BKGN_reg	2.686	-0.02	2.632	-0.09	2.703	0.761
45	Brightness (BRGT)vn_BRGT_reg	1.960	-0.04	1.749	-0.30	1.991	0.813
46	Speech chunking (CHNK)vn_CHNK_reg	2.040	+0.16	2.030	+0.15	1.847	1.239
47	Articulation clarity (CLRT)vn_CLRT_reg	3.118	+1.16	3.283	+1.34	2.018	0.945
48	Cognitive load (COGL)vn_COGL_reg	2.417	+0.30	2.363	+0.25	2.094	1.061
49	Dynamic arc (DARC)vn_DARC_reg	3.507	+1.37	3.592	+1.43	1.615	1.380
50	Disfluency (DFLU)vn_DFLU_reg	1.862	-0.53	1.964	-0.44	2.488	1.184
51	Emphasis (EMPH)vn_EMPH_reg	4.252	+1.08	4.399	+1.18	2.607	1.524
52	Esthetics (ESTH)vn_ESTH_reg	1.942	-0.59	1.753	-0.83	2.402	0.782
53	Content appropriateness (EXPL)vn_EXPL_reg	-0.001	-0.27	0.044	-0.13	0.086	0.322
54	Focus (FOCS)vn_FOCS_reg	2.679	+0.30	2.753	+0.37	2.344	1.102
55	Fullness (FULL)vn_FULL_reg	1.123	-0.74	1.009	-0.87	1.778	0.889
56	Perceived gender (GEND)vn_GEND_reg	5.026	+0.61	5.101	+0.66	4.055	1.588
57	Harmonicity (HARM)vn_HARM_reg	3.128	+0.77	3.209	+0.87	2.480	0.836
58	Metallic character (METL)vn_METL_reg	3.270	+1.72	3.240	+1.69	1.621	0.958
59	Pitch range (RANG)vn_RANG_reg	3.759	+0.94	3.804	+0.99	2.914	0.897
60	Recording quality (RCQL)vn_RCQL_reg	2.143	-0.69	2.157	-0.67	2.754	0.888
61	Vocal register (REGS)vn_REGS_reg	0.206	-0.78	0.485	-0.56	1.198	1.268
62	Respiration (RESP)vn_RESP_reg	2.740	+0.06	2.780	+0.09	2.680	1.056
63	Roughness (ROUG)vn_ROUG_reg	3.097	+1.20	3.077	+1.18	2.033	0.887
64	Chest resonance (R_CHST)vn_R_CHST_reg	3.401	+1.50	3.202	+1.26	2.135	0.844
65	Head resonance (R_HEAD)vn_R_HEAD_reg	1.938	-0.26	1.994	-0.19	2.148	0.822
66	Mask resonance (R_MASK)vn_R_MASK_reg	1.607	-0.30	1.636	-0.27	1.908	1.005
67	Mixed resonance (R_MIXD)vn_R_MIXD_reg	0.945	-0.58	0.817	-0.74	1.436	0.841
68	Nasal resonance (R_NASL)vn_R_NASL_reg	4.789	+1.91	4.690	+1.81	2.791	1.047
69	Oral resonance (R_ORAL)vn_R_ORAL_reg	2.734	+0.74	2.658	+0.64	2.184	0.741
70	Throat resonance (R_THRT)vn_R_THRT_reg	3.345	+1.59	3.100	+1.28	2.070	0.803
71	Smoothness (SMTH)vn_SMTH_reg	2.445	+0.28	2.295	+0.14	2.143	1.093
72	Stance (STNC)vn_STNC_reg	4.309	+1.47	4.024	+1.22	2.633	1.137
73	Speech structure (STRU)vn_STRU_reg	2.930	+0.83	3.092	+1.00	2.137	0.958
74	ASMR style (S_ASMR)vn_S_ASMR_reg	-0.115	-1.05	-0.018	-0.98	1.370	1.411
75	Authoritative style (S_AUTH)vn_S_AUTH_reg	3.939	+2.73	3.792	+2.59	1.088	1.043
76	Cartoonish style (S_CART)vn_S_CART_reg	4.846	+2.35	5.167	+2.57	1.560	1.401
77	Casual style (S_CASU)vn_S_CASU_reg	1.428	-1.85	1.438	-1.84	3.793	1.278
78	Conversational style (S_CONV)vn_S_CONV_reg	-0.118	-2.06	-0.159	-2.09	2.594	1.318
79	Dramatic style (S_DRAM)vn_S_DRAM_reg	4.132	+1.23	4.123	+1.22	2.721	1.148
80	Formal style (S_FORM)vn_S_FORM_reg	1.927	+0.72	1.990	+0.78	1.195	1.021
81	Monologue style (S_MONO)vn_S_MONO_reg	3.126	+0.23	2.957	+0.10	2.824	1.284
82	Narrator style (S_NARR)vn_S_NARR_reg	2.579	+0.88	2.546	+0.86	1.307	1.446
83	Newsreader style (S_NEWS)vn_S_NEWS_reg	1.951	+2.72	1.822	+2.49	0.408	0.568
84	Playful style (S_PLAY)vn_S_PLAY_reg	1.834	-0.39	1.998	-0.27	2.352	1.315
85	Ranting or angry style (S_RANT)vn_S_RANT_reg	3.398	+1.69	3.318	+1.63	1.213	1.289
86	Storytelling style (S_STRY)vn_S_STRY_reg	4.487	+1.47	4.182	+1.25	2.480	1.366
87	Teacher or didactic style (S_TECH)vn_S_TECH_reg	-0.746	-1.14	-0.665	-1.07	0.646	1.227
88	Whispered talking style (S_WHIS)vn_S_WHIS_reg	0.930	-0.41	1.099	-0.31	1.597	1.618
89	Tempo (TEMP)vn_TEMP_reg	2.355	+0.20	2.369	+0.21	2.117	1.190
90	Tension (TENS)vn_TENS_reg	3.558	+2.35	3.584	+2.38	1.559	0.852
91	Valence (VALN)vn_VALN_reg	2.663	+0.30	2.552	+0.20	2.328	1.118
92	Valence shift (VALS)vn_VALS_reg	2.127	-0.36	1.841	-0.63	2.518	1.079
93	Velocity flux (VFLX)vn_VFLX_reg	2.102	-0.13	1.846	-0.34	2.256	1.208
94	Volatility (VOLT)vn_VOLT_reg	2.601	+0.02	2.701	+0.13	2.586	0.886
95	Vulnerability (VULN)vn_VULN_reg	1.146	-1.53	0.852	-1.83	2.648	0.984
96	Warmth (WARM)vn_WARM_reg	1.941	-0.70	1.814	-0.84	2.578	0.909
Genuineness, blend, and legacy quality Genuineness and vocal-burst blend are predicted. R_quality has Ladder training labels but no valid P3 test labels.
97	Genuineness (0–6)genuineness_0_6	1.438	-0.55	1.281	-0.65	2.332	1.621
98	Vocal-burst blend (0–10)blend_0_10	2.864	-1.39	2.758	-1.43	6.676	2.738
99	Legacy R_quality (no P3 test labels)R_quality	0.536	-1.65	0.495	-1.78	1.095	0.338
Empathic Insight Plus extra scores Nineteen additional clip-level teacher scores, including background noise and content enjoyment.
100	Ageeiv_extra:Age	3.233	-0.06	3.198	-0.18	3.250	0.293
101	Arousaleiv_extra:Arousal	1.722	+1.00	1.896	+1.40	1.289	0.435
102	Authenticityeiv_extra:Authenticity	2.705	+0.25	2.659	-0.05	2.667	0.153
103	Background Noiseeiv_extra:Background_Noise	0.640	-0.63	0.749	-0.22	0.808	0.264
104	Confident vs. Hesitanteiv_extra:Confident_vs._Hesitant	1.040	+0.00	1.134	+0.31	1.040	0.303
105	Gendereiv_extra:Gender	-1.192	-0.57	-0.989	-0.37	-0.621	0.999
106	High-Pitched vs. Low-Pitchedeiv_extra:High-Pitched_vs._Low-Pitched	2.151	+1.29	2.153	+1.30	1.827	0.250
107	Monotone vs. Expressiveeiv_extra:Monotone_vs._Expressive	2.298	+0.93	2.421	+1.20	1.859	0.470
108	Recording Qualityeiv_extra:Recording_Quality	2.077	-0.20	2.043	-0.30	2.144	0.332
109	Serious vs. Humorouseiv_extra:Serious_vs._Humorous	0.805	-0.36	0.951	+0.06	0.929	0.340
110	Soft vs. Harsheiv_extra:Soft_vs._Harsh	0.205	-0.24	0.040	-0.75	0.281	0.320
111	Submissive vs. Dominanteiv_extra:Submissive_vs._Dominant	0.853	+1.48	0.919	+1.68	0.376	0.324
112	Valenceeiv_extra:Valence	-0.740	-1.96	-1.014	-2.68	0.005	0.380
113	Vulnerable vs. Emotionally Detachedeiv_extra:Vulnerable_vs._Emotionally_Detached	1.606	-0.25	1.439	-0.63	1.715	0.437
114	Warm vs. Coldeiv_extra:Warm_vs._Cold	-0.317	-1.23	-0.338	-1.30	0.051	0.300
115	score background qualityeiv_extra:score_background_quality	3.583	+0.41	3.713	+0.59	3.301	0.693
116	score content enjoymenteiv_extra:score_content_enjoyment	4.724	+0.72	4.745	+0.79	4.507	0.303
117	score overall qualityeiv_extra:score_overall_quality	2.921	+0.53	3.088	+0.86	2.652	0.507
118	score speech qualityeiv_extra:score_speech_quality	1.921	+0.78	1.944	+0.94	1.808	0.146
Meta AudioBox Aesthetics Four AudioBox aesthetic teacher outputs. Expansions follow the official Meta model card.
119	Content enjoyment (CE)audiobox:CE	5.181	+0.37	5.296	+0.49	4.799	1.018
120	Content usefulness (CU)audiobox:CU	5.768	+0.12	5.906	+0.26	5.649	1.001
121	Production complexity (PC)audiobox:PC	1.473	-0.53	1.662	-0.41	2.331	1.617
122	Production quality (PQ)audiobox:PQ	7.212	+0.19	7.296	+0.29	7.044	0.879
Microsoft DNSMOS Seven DNSMOS teacher outputs: raw and calibrated SIG/BAK/OVRL estimates plus P.808 MOS.
123	Speech signal quality, rawdnsmos:SIG_raw	3.933	+0.05	4.131	+0.35	3.900	0.669
124	Background quality, rawdnsmos:BAK_raw	4.021	+0.72	4.052	+0.75	3.211	1.124
125	Overall quality, rawdnsmos:OVRL_raw	3.561	+0.59	3.723	+0.79	3.085	0.812
126	Speech signal quality, calibrateddnsmos:SIG	3.504	+0.03	3.624	+0.27	3.488	0.501
127	Background quality, calibrateddnsmos:BAK	3.872	+0.52	3.919	+0.57	3.389	0.928
128	Overall quality, calibrateddnsmos:OVRL	3.136	+0.49	3.252	+0.68	2.840	0.606
129	P.808 MOS estimatednsmos:P808_MOS	3.855	+0.87	3.820	+0.80	3.421	0.496
Vocal-burst count The regression target is log(1 + count). A separate table also reports count error after inverse transformation.
130	Vocal-burst count, log(1 + count)burst_count_log1p	0.002	+0.00	-0.005	-0.01	0.000	0.647
VoiceCLAP attributes Sixty-one individual VoiceCLAP attribute teacher scores. The raw 768D VoiceCLAP embedding is stored in sidecars but is not a model output.
131	Affectionvoiceclap_attribute:Affection	0.859	-0.16	0.730	-0.39	0.947	0.554
132	Agevoiceclap_attribute:Age	3.202	-0.05	3.280	+0.09	3.229	0.547
133	Amusementvoiceclap_attribute:Amusement	0.148	-0.43	0.101	-0.51	0.392	0.572
134	Angervoiceclap_attribute:Anger	1.929	+1.85	1.905	+1.80	0.992	0.506
135	Arousalvoiceclap_attribute:Arousal	2.432	+1.63	2.252	+1.34	1.420	0.622
136	Astonishment Surprisevoiceclap_attribute:Astonishment_Surprise	0.524	+0.03	0.407	-0.21	0.509	0.479
137	Authenticityvoiceclap_attribute:Authenticity	2.667	-0.62	2.664	-0.64	2.770	0.167
138	Awevoiceclap_attribute:Awe	0.796	+0.99	0.687	+0.57	0.539	0.259
139	Background Noisevoiceclap_attribute:Background_Noise	0.590	+0.09	0.683	+0.44	0.567	0.264
140	Bitternessvoiceclap_attribute:Bitterness	1.063	+2.00	1.010	+1.77	0.592	0.236
141	Concentrationvoiceclap_attribute:Concentration	1.355	+0.27	1.441	+0.43	1.214	0.531
142	Confident vs. Hesitantvoiceclap_attribute:Confident_vs._Hesitant	1.027	-0.09	0.925	-0.31	1.069	0.468
143	Confusionvoiceclap_attribute:Confusion	0.736	+0.28	0.577	-0.20	0.643	0.334
144	Contemplationvoiceclap_attribute:Contemplation	0.677	-0.25	0.575	-0.50	0.780	0.406
145	Contemptvoiceclap_attribute:Contempt	1.327	+1.83	1.213	+1.49	0.709	0.339
146	Contentmentvoiceclap_attribute:Contentment	0.321	-0.87	0.465	-0.40	0.588	0.307
147	Disappointmentvoiceclap_attribute:Disappointment	1.287	+1.81	1.289	+1.82	0.760	0.291
148	Disgustvoiceclap_attribute:Disgust	1.066	+2.13	1.029	+1.95	0.625	0.207
149	Distressvoiceclap_attribute:Distress	1.446	+1.48	1.473	+1.56	0.927	0.350
150	Doubtvoiceclap_attribute:Doubt	0.398	-0.73	0.352	-0.97	0.535	0.188
151	Elationvoiceclap_attribute:Elation	0.517	-0.06	0.565	+0.06	0.539	0.397
152	Embarrassmentvoiceclap_attribute:Embarrassment	0.141	-0.53	0.082	-0.72	0.307	0.314
153	Emotional Numbnessvoiceclap_attribute:Emotional_Numbness	0.561	-0.39	0.698	+0.13	0.664	0.266
154	Fatigue Exhaustionvoiceclap_attribute:Fatigue_Exhaustion	0.418	-0.17	0.540	+0.30	0.462	0.261
155	Fearvoiceclap_attribute:Fear	0.857	+1.13	0.925	+1.45	0.618	0.212
156	Gendervoiceclap_attribute:Gender	-1.658	-1.50	-1.226	-1.07	-0.151	1.005
157	Helplessnessvoiceclap_attribute:Helplessness	0.944	+1.06	0.957	+1.11	0.658	0.268
158	High-Pitched vs. Low-Pitchedvoiceclap_attribute:High-Pitched_vs._Low-Pitched	2.418	+1.54	2.301	+1.23	1.840	0.375
159	Hope Enthusiasm Optimismvoiceclap_attribute:Hope_Enthusiasm_Optimism	0.917	+0.53	0.980	+0.70	0.705	0.396
160	Impatience and Irritabilityvoiceclap_attribute:Impatience_and_Irritability	2.323	+2.35	2.221	+2.16	1.052	0.541
161	Infatuationvoiceclap_attribute:Infatuation	0.570	-0.11	0.645	+0.11	0.608	0.332
162	Interestvoiceclap_attribute:Interest	1.496	-0.23	1.482	-0.26	1.598	0.440
163	Intoxication Altered States of Consciousnessvoiceclap_attribute:Intoxication_Altered_States_of_Consciousness	0.549	+0.10	0.572	+0.15	0.502	0.463
164	Jealousy & Envyvoiceclap_attribute:Jealousy_&_Envy	0.904	+1.56	0.932	+1.67	0.523	0.245
165	Longingvoiceclap_attribute:Longing	0.708	+0.77	0.719	+0.83	0.538	0.220
166	Malevolence Malicevoiceclap_attribute:Malevolence_Malice	1.571	+2.13	1.533	+2.02	0.833	0.346
167	Monotone vs. Expressivevoiceclap_attribute:Monotone_vs._Expressive	2.159	+0.65	2.120	+0.58	1.775	0.594
168	Painvoiceclap_attribute:Pain	0.726	+1.58	0.763	+1.75	0.381	0.218
169	Pleasure Ecstasyvoiceclap_attribute:Pleasure_Ecstasy	0.393	-0.37	0.382	-0.40	0.503	0.301
170	Pridevoiceclap_attribute:Pride	1.185	+1.16	1.207	+1.22	0.780	0.349
171	Recording Qualityvoiceclap_attribute:Recording_Quality	1.988	-0.99	2.073	-0.73	2.313	0.328
172	Reliefvoiceclap_attribute:Relief	0.892	-0.32	0.875	-0.36	1.025	0.415
173	Sadnessvoiceclap_attribute:Sadness	1.052	+0.96	1.058	+0.98	0.752	0.313
174	Serious vs. Humorousvoiceclap_attribute:Serious_vs._Humorous	0.376	-0.75	0.269	-0.94	0.803	0.568
175	Sexual Lustvoiceclap_attribute:Sexual_Lust	0.545	-0.21	0.588	-0.11	0.635	0.419
176	Shamevoiceclap_attribute:Shame	0.607	+0.28	0.745	+0.77	0.526	0.283
177	Soft vs. Harshvoiceclap_attribute:Soft_vs._Harsh	-0.282	-1.23	-0.375	-1.48	0.160	0.360
178	Sournessvoiceclap_attribute:Sourness	1.225	+1.79	1.168	+1.59	0.706	0.291
179	Submissive vs. Dominantvoiceclap_attribute:Submissive_vs._Dominant	1.206	+1.63	1.285	+1.84	0.623	0.359
180	Teasingvoiceclap_attribute:Teasing	0.232	-0.81	0.226	-0.83	0.540	0.379
181	Thankfulness Gratitudevoiceclap_attribute:Thankfulness_Gratitude	1.811	+0.81	2.082	+1.32	1.384	0.529
182	Triumphvoiceclap_attribute:Triumph	1.118	+1.12	1.239	+1.45	0.716	0.359
183	Valencevoiceclap_attribute:Valence	-1.790	-2.81	-1.701	-2.67	-0.007	0.635
184	Vulnerable vs. Emotionally Detachedvoiceclap_attribute:Vulnerable_vs._Emotionally_Detached	1.715	+0.14	1.776	+0.25	1.638	0.556
185	Warm vs. Coldvoiceclap_attribute:Warm_vs._Cold	-0.618	-1.38	-0.725	-1.65	-0.066	0.400
186	durationvoiceclap_attribute:duration	10.952	+0.01	11.619	+0.11	10.914	6.354
187	score background qualityvoiceclap_attribute:score_background_quality	3.445	+0.40	3.620	+0.75	3.245	0.498
188	score content enjoymentvoiceclap_attribute:score_content_enjoyment	4.669	+0.09	4.678	+0.15	4.656	0.147
189	score overall qualityvoiceclap_attribute:score_overall_quality	2.919	+0.69	3.029	+0.95	2.635	0.412
190	score speech qualityvoiceclap_attribute:score_speech_quality	1.961	+1.01	1.941	+0.72	1.891	0.069
191	talking speedvoiceclap_attribute:talking_speed	13.498	+1.19	12.296	+0.87	9.028	3.756

All Orange embedding components

The cosine above is the meaningful vector-level comparison; component values have no standalone semantic label.

Timbre — all 128 vector components

Dimension	Tiny	Base	Orange teacher
0	0.0498	0.0071	0.0383
1	-0.0002	0.0171	-0.0816
2	-0.0720	-0.0464	-0.0806
3	-0.0343	-0.1012	-0.0833
4	-0.0620	-0.1214	-0.0772
5	-0.1469	-0.1326	-0.1039
6	-0.0327	-0.0408	-0.0745
7	0.0763	0.0509	0.1173
8	0.0297	-0.0239	0.1211
9	-0.1201	-0.0923	-0.0672
10	0.0555	0.0281	0.0937
11	-0.0544	-0.0590	-0.0406
12	-0.0561	-0.0271	-0.0191
13	-0.0894	-0.0856	-0.0811
14	-0.0769	-0.0766	-0.0799
15	-0.1110	-0.1029	-0.0736
16	-0.0831	-0.0727	-0.0872
17	-0.0911	-0.0996	-0.0413
18	-0.0272	-0.0092	-0.0629
19	-0.0677	-0.0565	-0.0777
20	0.1685	0.1521	0.0917
21	-0.0236	-0.0139	-0.0155
22	-0.0911	-0.0805	-0.0772
23	-0.0292	-0.0722	0.0719
24	-0.0854	-0.0710	-0.0663
25	-0.0379	-0.0621	-0.0518
26	-0.0223	-0.0082	-0.0656
27	-0.0364	-0.0004	0.1190
28	-0.0265	-0.0130	0.0341
29	0.0058	0.1180	0.1088
30	0.1594	0.1398	0.1671
31	0.0330	-0.0162	-0.0688
32	-0.0677	-0.0794	-0.0791
33	-0.1435	-0.1063	-0.0905
34	-0.0797	-0.0593	-0.0736
35	0.2106	0.2730	0.2346
36	-0.0865	-0.0940	-0.0883
37	-0.1104	-0.1175	-0.0972
38	-0.0527	-0.0621	-0.0519
39	-0.1173	-0.0889	-0.0828
40	-0.0888	-0.0386	-0.0151
41	-0.1275	-0.0934	-0.1180
42	0.1298	0.1068	0.0573
43	0.0527	0.0568	0.0630
44	0.2425	0.2953	0.1798
45	0.0985	0.1303	0.1481
46	-0.0905	-0.0668	-0.0635
47	-0.0786	-0.0817	-0.0830
48	-0.0370	-0.0512	-0.0749
49	0.0843	0.1018	0.0543
50	0.0672	0.0473	0.0645
51	-0.0905	-0.0945	-0.0821
52	0.0040	0.0192	0.0083
53	0.0831	0.1426	0.0891
54	-0.1287	-0.1063	-0.0919
55	0.1696	0.1689	0.1279
56	0.0356	-0.0150	-0.0762
57	-0.1315	-0.1555	-0.0901
58	0.0660	0.0149	0.0702
59	0.0922	0.0501	0.0775
60	-0.0769	-0.0722	-0.0792
61	0.2687	0.2014	0.2468
62	-0.0996	-0.0699	-0.0768
63	-0.0310	-0.0828	-0.0780
64	0.0017	0.0249	0.0606
65	-0.0996	-0.0856	-0.0670
66	0.0734	0.0934	0.0624
67	-0.0865	-0.0850	-0.0792
68	-0.1053	-0.1096	-0.0868
69	-0.0820	-0.0811	-0.0753
70	0.0740	0.0984	0.1000
71	-0.0106	-0.0248	-0.0171
72	-0.0734	-0.0439	-0.0795
73	0.1013	0.0646	0.1074
74	-0.1361	-0.0557	-0.0897
75	0.0467	0.0414	0.1395
76	-0.0272	-0.0005	0.0095
77	-0.0272	-0.0266	-0.0750
78	0.0584	-0.0200	-0.0185
79	-0.0808	-0.0744	-0.0712
80	-0.0292	-0.0200	-0.0585
81	0.0572	0.0694	0.0006
82	-0.0882	-0.1158	-0.0786
83	-0.0951	-0.1018	-0.0841
84	0.0956	0.1600	0.1237
85	0.0379	0.0777	0.0580
86	-0.0985	-0.1091	-0.0751
87	-0.0586	-0.0590	-0.0576
88	-0.0048	-0.0450	-0.0311
89	-0.0905	-0.0805	-0.0754
90	-0.1030	-0.1113	-0.0891
91	0.1093	0.0817	0.1553
92	-0.1087	-0.1001	-0.0798
93	0.1480	0.1644	0.1699
94	0.1429	0.0805	0.0975
95	0.0295	0.0545	-0.0818
96	-0.0601	-0.0540	-0.0734
97	0.0031	0.0214	0.0243
98	0.1042	0.0951	0.1093
99	0.0444	-0.0043	0.0981
100	0.1292	0.1270	0.0787
101	0.0729	0.0766	0.0853
102	-0.0178	-0.0281	-0.0364
103	-0.1076	-0.0951	-0.0867
104	-0.0376	-0.0192	-0.0803
105	-0.0319	-0.0375	-0.0357
106	-0.0549	-0.0475	-0.0959
107	0.0095	0.0298	-0.0210
108	0.0286	0.0142	-0.0374
109	-0.0549	-0.0940	-0.0806
110	0.0324	-0.0179	-0.0271
111	-0.1053	-0.0750	-0.0953
112	-0.0854	-0.0833	-0.0809
113	0.0418	0.0828	0.0481
114	-0.0917	-0.0554	-0.0030
115	0.0433	0.0917	0.1879
116	-0.0085	-0.0011	-0.0704
117	0.0751	0.0755	0.1299
118	-0.1053	-0.1124	-0.0800
119	0.0584	0.1286	0.0688
120	-0.1036	-0.0917	-0.0845
121	0.1076	0.1035	0.1042
122	-0.0566	-0.0403	-0.0844
123	-0.1116	-0.0543	-0.0695
124	0.0515	-0.0022	-0.0596
125	0.0208	0.0710	0.0840
126	-0.0467	-0.0559	-0.0033
127	0.0106	0.0162	0.0614

Identity — all 250 vector components

Dimension	Tiny	Base	Orange teacher
0	-0.0317	-0.0287	-0.0478
1	-0.0453	-0.0265	-0.0421
2	0.0301	0.0159	0.0653
3	-0.0090	0.0066	0.0638
4	0.0215	0.0422	-0.0395
5	-0.0683	-0.0369	-0.0454
6	0.0017	0.0076	0.0047
7	0.0111	0.0374	-0.0440
8	0.0185	0.0262	-0.0207
9	0.0338	0.0158	0.0231
10	0.0516	0.0580	0.0140
11	-0.0531	-0.0577	-0.0234
12	-0.0534	-0.0619	-0.0475
13	-0.0631	-0.0237	-0.0384
14	-0.0559	-0.0527	-0.0112
15	0.0622	0.0540	0.1014
16	0.0677	0.0606	0.0463
17	-0.0370	-0.0482	-0.0340
18	-0.0447	-0.0348	-0.0442
19	0.0037	-0.0179	-0.0423
20	0.0912	0.0785	0.0520
21	-0.0620	-0.0651	-0.0403
22	-0.0280	-0.0461	-0.0451
23	-0.0998	-0.0654	-0.0420
24	0.0367	0.0680	0.0601
25	-0.0178	0.0216	-0.0799
26	0.0703	0.0212	0.0520
27	0.0906	0.0456	0.0311
28	0.0482	0.0535	0.0812
29	-0.0792	-0.0775	-0.0418
30	0.0261	0.0519	-0.0187
31	0.0468	0.0712	0.0295
32	0.0683	0.0859	-0.0404
33	0.0565	0.0155	0.0334
34	-0.0513	-0.0238	-0.0482
35	-0.0181	-0.0369	-0.0560
36	0.0280	0.0094	0.0763
37	0.0331	0.0398	0.0815
38	0.0295	0.0775	0.0651
39	-0.0562	-0.0324	-0.0317
40	-0.0740	-0.0590	-0.0503
41	0.1285	0.0975	0.0320
42	-0.0597	-0.0237	-0.0432
43	0.0708	0.1181	-0.0219
44	0.0769	0.0661	-0.0079
45	-0.0502	-0.0351	-0.0142
46	-0.0597	-0.0656	-0.0418
47	0.0238	-0.0242	-0.0174
48	0.0260	0.0123	-0.0464
49	-0.0361	-0.0453	-0.0693
50	-0.0238	-0.0336	-0.0786
51	0.0706	0.0540	0.0656
52	-0.0093	0.0312	-0.0356
53	0.0330	0.0543	0.0541
54	0.0404	0.0577	0.0339
55	0.0562	0.0411	0.1316
56	0.0499	0.0885	0.1090
57	0.0250	-0.0235	-0.0113
58	0.0130	0.0119	-0.0384
59	-0.0153	-0.0145	0.0470
60	0.0645	0.0833	0.0616
61	-0.0485	-0.0461	-0.0403
62	-0.0516	-0.0408	-0.0382
63	0.0318	-0.0219	0.0282
64	-0.0191	-0.0215	-0.0362
65	0.0222	-0.0206	-0.0058
66	0.0271	0.0121	-0.0473
67	-0.0121	-0.0177	0.0775
68	-0.0568	-0.0387	-0.0468
69	-0.0134	0.0875	0.0262
70	-0.0611	-0.0672	-0.0630
71	-0.0490	-0.0300	-0.0421
72	0.0241	0.0232	0.0095
73	0.1044	0.0622	0.0975
74	-0.0568	-0.0310	-0.0469
75	0.0324	0.0754	0.0534
76	0.0505	0.0933	0.0421
77	-0.0473	-0.0622	-0.0443
78	-0.0228	-0.0503	-0.0627
79	0.0185	0.0262	0.0665
80	-0.0786	-0.0875	-0.0461
81	0.0188	0.0453	-0.0152
82	-0.0148	-0.0527	-0.0295
83	-0.0599	-0.0325	-0.0386
84	0.0459	0.0448	0.0440
85	0.0714	0.0796	0.1219
86	0.0205	0.0047	-0.0414
87	-0.0410	-0.0506	0.0122
88	0.1165	0.0843	0.1407
89	0.0103	0.0451	0.0146
90	-0.0222	-0.0385	0.0137
91	-0.0680	-0.0743	-0.0546
92	-0.0132	-0.0198	0.0359
93	0.0115	0.0406	-0.0454
94	-0.0161	-0.0211	-0.0475
95	-0.0611	-0.0073	-0.0484
96	-0.0131	0.0358	0.0255
97	-0.0513	-0.0488	-0.0547
98	-0.0070	0.0345	0.0098
99	-0.0077	0.0285	0.0202
100	-0.0447	-0.0427	0.0343
101	-0.0023	0.0160	-0.0430
102	0.0410	0.0598	0.0354
103	-0.0120	0.0152	-0.0544
104	-0.0496	-0.0632	-0.0605
105	-0.0519	-0.0585	-0.0388
106	-0.0815	-0.0564	-0.0357
107	-0.0706	-0.0453	-0.0416
108	0.1973	0.2129	0.2717
109	0.0029	0.0052	-0.0138
110	-0.0413	-0.0393	-0.0552
111	-0.0752	-0.0269	-0.0382
112	-0.0399	-0.0366	-0.0374
113	0.0594	0.0625	0.0984
114	-0.0769	-0.0543	-0.0647
115	-0.0059	0.0072	0.0304
116	0.0018	-0.0282	-0.0051
117	-0.0078	-0.0215	0.0574
118	-0.0465	-0.0459	-0.0453
119	-0.0565	-0.0419	-0.0477
120	0.0005	-0.0096	-0.0176
121	-0.0084	-0.0036	0.0092
122	-0.0998	-0.1086	-0.0438
123	0.0089	0.0129	0.0374
124	0.1308	0.0696	0.0042
125	-0.0992	-0.1117	-0.0451
126	0.0924	0.0975	0.1187
127	-0.0294	-0.0358	-0.0477
128	0.0173	0.0267	0.0277
129	0.0947	0.0933	0.0917
130	-0.0354	-0.0073	-0.0466
131	0.0244	-0.0055	-0.0305
132	0.0634	0.0630	-0.0096
133	0.0147	-0.0295	0.0378
134	0.0413	0.0274	0.0496
135	-0.0222	0.0034	-0.0421
136	0.0020	-0.0199	0.0196
137	0.0599	-0.0080	0.0341
138	0.0511	0.0273	-0.0409
139	0.0241	0.0480	0.0370
140	-0.0227	0.0055	-0.0412
141	0.0832	0.1123	0.0371
142	-0.0459	-0.0157	-0.0401
143	0.0588	0.0117	0.0148
144	-0.0929	-0.0864	-0.0483
145	0.0396	0.0192	0.0301
146	0.1348	0.1782	0.0879
147	-0.0328	-0.0252	-0.0121
148	0.1457	0.1602	0.1742
149	0.1394	0.1270	0.1294
150	0.1038	0.1012	0.0920
151	0.0074	0.0037	0.0456
152	0.0116	0.0171	0.0159
153	-0.0073	0.0258	0.0338
154	0.0677	0.0490	0.0985
155	0.0131	-0.0482	0.0006
156	0.0151	-0.0128	-0.0387
157	0.0219	0.0459	0.0249
158	0.0479	0.0596	0.0577
159	-0.0003	0.0115	-0.0508
160	0.0577	0.0524	0.1270
161	-0.0217	-0.0145	-0.0610
162	-0.1090	-0.0817	-0.0538
163	-0.0640	-0.0556	-0.0516
164	-0.0174	0.0090	-0.0407
165	-0.0536	-0.0076	-0.0118
166	0.0462	0.0970	0.0298
167	-0.1400	-0.1803	-0.0588
168	-0.0083	0.0295	0.0829
169	0.0883	0.0474	0.0219
170	-0.0054	-0.0190	0.0156
171	-0.0202	-0.0343	-0.0408
172	0.0711	0.0864	0.0555
173	0.0861	0.1107	0.0707
174	-0.0482	-0.0472	-0.0476
175	-0.0508	-0.0493	-0.0694
176	0.0889	0.0253	0.0812
177	-0.0513	-0.0372	-0.0382
178	0.0303	0.0042	-0.0204
179	0.0975	0.1507	0.1061
180	0.2088	0.1708	0.1488
181	-0.0668	-0.0358	0.0191
182	-0.0470	-0.0480	-0.0400
183	-0.0651	-0.0596	-0.0680
184	-0.0280	0.0366	0.0135
185	0.0505	0.0196	0.0726
186	-0.0479	-0.0340	-0.0559
187	0.0763	0.0727	0.0708
188	0.0548	0.0408	0.0748
189	0.0579	0.0145	0.0713
190	0.0399	0.0260	0.0800
191	-0.0205	-0.0048	0.0857
192	0.0516	0.0917	0.1123
193	0.0291	0.0632	0.1193
194	0.0482	0.0459	-0.0066
195	-0.0142	-0.0139	-0.0441
196	0.0640	0.1017	0.0850
197	0.1411	0.1276	0.0864
198	-0.0202	-0.0169	-0.0341
199	0.0516	0.0743	0.0350
200	-0.0591	-0.0614	-0.0536
201	0.0605	0.0722	0.0598
202	-0.0479	-0.0459	-0.0965
203	0.1394	0.1001	0.0313
204	0.0686	0.0480	0.1166
205	-0.0425	-0.0329	-0.0047
206	0.0209	0.0406	0.0328
207	-0.0307	-0.0203	-0.0383
208	-0.0166	-0.0177	-0.0299
209	-0.0447	-0.0199	0.0224
210	0.2123	0.1718	0.2505
211	0.0229	-0.0256	-0.0356
212	0.0453	0.0604	0.0547
213	0.0654	0.0422	0.0781
214	0.2731	0.2825	0.2739
215	-0.0272	-0.0366	-0.0390
216	0.0140	-0.0062	0.0281
217	-0.0694	-0.0472	-0.0516
218	-0.0482	-0.0506	0.0255
219	-0.0511	-0.0427	-0.0604
220	-0.0511	-0.0482	-0.0512
221	0.0141	0.0083	0.0170
222	-0.0073	0.0051	-0.0234
223	-0.0479	-0.0343	-0.0372
224	-0.0321	-0.0190	-0.0243
225	0.0918	0.0727	0.1033
226	-0.0308	-0.0115	-0.0296
227	0.0205	0.0511	-0.0394
228	0.0007	0.0034	-0.0751
229	0.0396	0.0519	0.0057
230	0.0117	0.0078	0.0189
231	0.0640	0.0432	0.0692
232	-0.0222	-0.0165	-0.0105
233	-0.0010	-0.0335	-0.0484
234	0.2157	0.2235	0.1165
235	0.1337	0.1908	0.1105
236	-0.0146	-0.0178	-0.0097
237	0.0301	0.0171	-0.0250
238	0.0677	0.0252	0.0748
239	-0.0240	-0.0440	-0.0479
240	0.0283	0.0659	0.0720
241	-0.0023	0.0191	0.0504
242	0.0134	0.0264	0.0159
243	-0.0490	-0.0680	-0.0591
244	-0.0376	-0.0493	-0.0493
245	-0.0826	-0.0335	-0.0441
246	-0.0393	-0.0448	-0.0375
247	-0.0686	-0.0891	-0.0390
248	-0.0631	-0.0585	-0.0530
249	-0.0387	-0.0337	-0.0599

Source: HUMANENESS_SMALL_VOICE_IDENTITY_R1_R2_2026-10-02_mediathek_0047.html · SHA-256 bab76f5811287dbb…

g08GermanMediathek voice study

mediathek_0047 · de · 44/50

Generated TTS prediction · Rank 2 qv · 8.4 s

Ich fühle einfach... (slow breathing) nichts mehr, wenn ich daran denke. Jeder Arbeitgeber muss sicherstellen, dass die Dinge anders sind.

Tiny Base · values are model estimates, not ground truth

Strongest emotions relative to training

Fatigue Exhaustion

z +4.36 / +4.36raw 2.38 / 2.38

Disappointment

z +2.42 / +2.53raw 1.70 / 1.77

Sadness

z +2.23 / +2.47raw 1.69 / 1.87

Contemplation

z +2.46 / +2.05raw 1.55 / 1.31

Helplessness

z +2.05 / +2.21raw 1.42 / 1.54

Doubt

z +1.90 / +2.04raw 0.89 / 0.96

Longing

z +1.94 / +1.70raw 1.31 / 1.16

The center of each bar is the S9 teacher median. Positive z is to the right; negative z is to the left. Ranking uses z, not raw teacher units.

Strongest VoiceNet dimensions relative to training

Cognitive load (COGL)

z +1.73 / +1.62raw 3.93 / 3.82

Chest resonance (R_CHST)

z +1.64 / +1.72raw 3.52 / 3.59

Tension (TENS)

z +1.39 / +1.32raw 2.74 / 2.68

Perceived voice age (AGEV)

z +1.32 / +1.23raw 4.62 / 4.51

Disfluency (DFLU)

z +1.00 / +1.12raw 3.67 / 3.81

Whispered talking style (S_WHIS)

z +0.87 / +1.11raw 3.01 / 3.39

Perceived gender (GEND)

z +0.83 / +0.96raw 5.37 / 5.59

All 57 VoiceNet predictions, including raw units, are in the full table below. These seven are ranked by z; the top values may differ from the strongest raw dimensions.

Voice, speed and quality scores in context

Genuineness (0–6)z -0.05 / +0.01raw 2.26 / 2.35

Vocal-burst blend (0–10)z -0.58 / -1.13raw 5.09 / 3.59

Content enjoyment (CE)z +0.08 / +0.16raw 4.88 / 4.96

Production quality (PQ)z +0.46 / +0.59raw 7.45 / 7.57

Speech signal quality, calibratedz +0.05 / +0.05raw 3.51 / 3.51

Background quality, calibratedz +0.80 / +0.41raw 4.13 / 3.77

Overall quality, calibratedz +0.61 / +0.39raw 3.21 / 3.08

P.808 MOS estimatez +0.57 / +0.12raw 3.70 / 3.48

score content enjoymentz -0.25 / +0.15raw 4.43 / 4.55

score overall qualityz +1.36 / +0.76raw 3.34 / 3.04

Background Noisez -1.79 / -1.04raw 0.33 / 0.53

Tempo (TEMP)z -0.95 / -0.80raw 0.98 / 1.17

Arousal (AROU)z -1.25 / -1.18raw 0.92 / 1.00

Valence (VALN)z -0.72 / -0.32raw 1.53 / 1.97

Recording quality (RCQL)z -0.53 / -0.56raw 2.28 / 2.25

Background noise (BKGN)z -0.26 / -0.28raw 2.51 / 2.49

talking speedz +0.47 / +0.12raw 10.81 / 9.49

Characters per second (CPS): 16.52 raw · z +2.00

Orange speaker embedding reconstruction

Cosine against Orange on this same clip (higher means closer to that teacher vector):

Embedding	Tiny	Base
Timbre · 128D	0.896	0.914
Identity · 250D	0.812	0.794

Vocal-burst regions

Tiny

Base

0 s8.4 s

Verified burst intervals are unavailable for this clip.

Tiny: 1 regions, count-head estimate 1.08; Base: 1 regions, count-head estimate 0.96.

Exact predicted start and end times

Model	Region	Start (s)	End (s)	Duration (s)
Tiny	1	2.94	3.12	0.18
Base	1	2.94	3.08	0.14

All 192 score slots · raw and z values

#	Target	Tiny raw	Tiny z	Base raw	Base z	Train median	Train SD
Emotion scores Forty clip-level Empathic Insight emotion teacher outputs. Each row evaluates one named emotion score.
0	Affectionemo_Affection	0.093	+0.15	0.026	+0.03	0.007	0.570
1	Amusementemo_Amusement	0.049	+0.06	0.078	+0.09	-0.001	0.885
2	Angeremo_Anger	0.375	+0.61	0.523	+0.85	0.004	0.613
3	Astonishment Surpriseemo_Astonishment_Surprise	0.004	-0.00	-0.009	-0.03	0.005	0.572
4	Aweemo_Awe	0.026	+0.06	0.015	+0.03	0.000	0.427
5	Bitternessemo_Bitterness	0.792	+1.87	0.744	+1.76	0.013	0.415
6	Concentrationemo_Concentration	0.504	-0.18	0.637	+0.00	0.634	0.741
7	Confusionemo_Confusion	0.524	+0.97	0.807	+1.49	0.001	0.540
8	Contemplationemo_Contemplation	1.555	+2.46	1.306	+2.05	0.082	0.598
9	Contemptemo_Contempt	0.013	+0.03	0.015	+0.03	-0.000	0.464
10	Contentmentemo_Contentment	0.039	+0.08	0.043	+0.08	0.000	0.514
11	Disappointmentemo_Disappointment	1.695	+2.42	1.772	+2.53	0.000	0.700
12	Disgustemo_Disgust	0.029	+0.04	0.032	+0.05	0.007	0.489
13	Distressemo_Distress	1.519	+1.85	1.576	+1.92	0.000	0.821
14	Doubtemo_Doubt	0.892	+1.90	0.956	+2.04	0.006	0.466
15	Elationemo_Elation	0.138	+0.17	0.048	+0.05	0.012	0.728
16	Embarrassmentemo_Embarrassment	0.482	+1.02	0.477	+1.01	0.043	0.430
17	Emotional Numbnessemo_Emotional_Numbness	1.574	+1.71	1.468	+1.60	0.004	0.917
18	Fatigue Exhaustionemo_Fatigue_Exhaustion	2.378	+4.36	2.378	+4.36	0.028	0.539
19	Fearemo_Fear	-0.010	-0.04	0.100	+0.14	0.015	0.610
20	Helplessnessemo_Helplessness	1.421	+2.05	1.537	+2.21	-0.004	0.696
21	Hope Enthusiasm Optimismemo_Hope_Enthusiasm_Optimism	-0.033	-0.20	-0.006	-0.16	0.117	0.760
22	Impatience and Irritabilityemo_Impatience_and_Irritability	0.818	+0.95	0.923	+1.10	0.149	0.705
23	Infatuationemo_Infatuation	-0.000	+0.03	-0.001	+0.03	-0.015	0.533
24	Interestemo_Interest	0.257	-1.47	0.414	-1.30	1.589	0.907
25	Intoxication Altered States of Consciousnessemo_Intoxication_Altered_States_of_Consciousness	0.008	+0.06	0.050	+0.13	-0.025	0.559
26	Jealousy and Envyemo_Jealousy_and_Envy	0.117	+0.13	0.117	+0.13	0.059	0.442
27	Longingemo_Longing	1.309	+1.94	1.160	+1.70	0.087	0.632
28	Malevolence Maliceemo_Malevolence_Malice	0.083	+0.05	0.102	+0.09	0.055	0.534
29	Painemo_Pain	0.221	+0.38	0.400	+0.69	-0.002	0.579
30	Pleasure Ecstasyemo_Pleasure_Ecstasy	-0.037	-0.09	-0.015	-0.05	0.017	0.614
31	Prideemo_Pride	0.056	+0.11	0.031	+0.06	0.002	0.509
32	Reliefemo_Relief	0.733	+1.03	0.861	+1.22	0.033	0.681
33	Sadnessemo_Sadness	1.695	+2.23	1.874	+2.47	0.000	0.759
34	Sexual Lustemo_Sexual_Lust	0.010	-0.04	0.007	-0.05	0.030	0.494
35	Shameemo_Shame	0.952	+1.84	0.854	+1.65	0.013	0.510
36	Sournessemo_Sourness	0.161	+0.38	0.087	+0.21	-0.005	0.439
37	Teasingemo_Teasing	-0.001	-0.00	0.003	+0.01	0.000	0.545
38	Thankfulness Gratitudeemo_Thankfulness_Gratitude	0.158	+0.17	0.233	+0.28	0.041	0.697
39	Triumphemo_Triumph	0.016	+0.04	0.026	+0.06	-0.007	0.521
VoiceNet dimensions Fifty-seven VoiceNet voice, delivery, style, and recording dimensions. Codes are expanded in the target column.
40	Perceived voice age (AGEV)vn_AGEV_reg	4.621	+1.32	4.512	+1.23	2.984	1.238
41	Arousal (AROU)vn_AROU_reg	0.923	-1.25	1.002	-1.18	2.359	1.147
42	Arousal shift (ARSH)vn_ARSH_reg	1.136	-1.66	1.225	-1.56	2.580	0.867
43	Vocal attack (ATCK)vn_ATCK_reg	0.967	-0.92	1.239	-0.71	2.162	1.295
44	Background noise (BKGN)vn_BKGN_reg	2.507	-0.26	2.488	-0.28	2.703	0.761
45	Brightness (BRGT)vn_BRGT_reg	1.820	-0.21	1.932	-0.07	1.991	0.813
46	Speech chunking (CHNK)vn_CHNK_reg	0.450	-1.13	0.674	-0.95	1.847	1.239
47	Articulation clarity (CLRT)vn_CLRT_reg	1.312	-0.75	1.418	-0.64	2.018	0.945
48	Cognitive load (COGL)vn_COGL_reg	3.932	+1.73	3.817	+1.62	2.094	1.061
49	Dynamic arc (DARC)vn_DARC_reg	-0.058	-1.21	0.314	-0.94	1.615	1.380
50	Disfluency (DFLU)vn_DFLU_reg	3.673	+1.00	3.812	+1.12	2.488	1.184
51	Emphasis (EMPH)vn_EMPH_reg	1.906	-0.46	2.255	-0.23	2.607	1.524
52	Esthetics (ESTH)vn_ESTH_reg	1.768	-0.81	2.069	-0.43	2.402	0.782
53	Content appropriateness (EXPL)vn_EXPL_reg	-0.429	-1.60	-0.280	-1.14	0.086	0.322
54	Focus (FOCS)vn_FOCS_reg	0.230	-1.92	0.672	-1.52	2.344	1.102
55	Fullness (FULL)vn_FULL_reg	1.989	+0.24	2.020	+0.27	1.778	0.889
56	Perceived gender (GEND)vn_GEND_reg	5.374	+0.83	5.586	+0.96	4.055	1.588
57	Harmonicity (HARM)vn_HARM_reg	2.032	-0.54	2.135	-0.41	2.480	0.836
58	Metallic character (METL)vn_METL_reg	0.786	-0.87	1.087	-0.56	1.621	0.958
59	Pitch range (RANG)vn_RANG_reg	2.453	-0.51	2.512	-0.45	2.914	0.897
60	Recording quality (RCQL)vn_RCQL_reg	2.280	-0.53	2.252	-0.56	2.754	0.888
61	Vocal register (REGS)vn_REGS_reg	-0.069	-1.00	0.039	-0.91	1.198	1.268
62	Respiration (RESP)vn_RESP_reg	3.548	+0.82	3.352	+0.64	2.680	1.056
63	Roughness (ROUG)vn_ROUG_reg	2.539	+0.57	2.615	+0.66	2.033	0.887
64	Chest resonance (R_CHST)vn_R_CHST_reg	3.520	+1.64	3.587	+1.72	2.135	0.844
65	Head resonance (R_HEAD)vn_R_HEAD_reg	0.915	-1.50	1.387	-0.93	2.148	0.822
66	Mask resonance (R_MASK)vn_R_MASK_reg	1.123	-0.78	1.335	-0.57	1.908	1.005
67	Mixed resonance (R_MIXD)vn_R_MIXD_reg	1.660	+0.27	1.860	+0.51	1.436	0.841
68	Nasal resonance (R_NASL)vn_R_NASL_reg	2.049	-0.71	2.493	-0.28	2.791	1.047
69	Oral resonance (R_ORAL)vn_R_ORAL_reg	1.950	-0.32	2.181	-0.00	2.184	0.741
70	Throat resonance (R_THRT)vn_R_THRT_reg	1.975	-0.12	2.116	+0.06	2.070	0.803
71	Smoothness (SMTH)vn_SMTH_reg	1.364	-0.71	1.650	-0.45	2.143	1.093
72	Stance (STNC)vn_STNC_reg	1.938	-0.61	2.238	-0.35	2.633	1.137
73	Speech structure (STRU)vn_STRU_reg	1.955	-0.19	2.066	-0.07	2.137	0.958
74	ASMR style (S_ASMR)vn_S_ASMR_reg	2.012	+0.46	2.010	+0.45	1.370	1.411
75	Authoritative style (S_AUTH)vn_S_AUTH_reg	0.668	-0.40	0.934	-0.15	1.088	1.043
76	Cartoonish style (S_CART)vn_S_CART_reg	1.281	-0.20	1.203	-0.25	1.560	1.401
77	Casual style (S_CASU)vn_S_CASU_reg	3.344	-0.35	3.507	-0.22	3.793	1.278
78	Conversational style (S_CONV)vn_S_CONV_reg	1.692	-0.68	2.092	-0.38	2.594	1.318
79	Dramatic style (S_DRAM)vn_S_DRAM_reg	2.983	+0.23	2.819	+0.09	2.721	1.148
80	Formal style (S_FORM)vn_S_FORM_reg	0.722	-0.46	0.846	-0.34	1.195	1.021
81	Monologue style (S_MONO)vn_S_MONO_reg	4.058	+0.96	4.048	+0.95	2.824	1.284
82	Narrator style (S_NARR)vn_S_NARR_reg	1.486	+0.12	1.480	+0.12	1.307	1.446
83	Newsreader style (S_NEWS)vn_S_NEWS_reg	0.563	+0.27	0.607	+0.35	0.408	0.568
84	Playful style (S_PLAY)vn_S_PLAY_reg	0.877	-1.12	1.162	-0.90	2.352	1.315
85	Ranting or angry style (S_RANT)vn_S_RANT_reg	2.087	+0.68	2.202	+0.77	1.213	1.289
86	Storytelling style (S_STRY)vn_S_STRY_reg	1.778	-0.51	1.993	-0.36	2.480	1.366
87	Teacher or didactic style (S_TECH)vn_S_TECH_reg	-1.527	-1.77	-0.784	-1.17	0.646	1.227
88	Whispered talking style (S_WHIS)vn_S_WHIS_reg	3.010	+0.87	3.391	+1.11	1.597	1.618
89	Tempo (TEMP)vn_TEMP_reg	0.985	-0.95	1.168	-0.80	2.117	1.190
90	Tension (TENS)vn_TENS_reg	2.739	+1.39	2.680	+1.32	1.559	0.852
91	Valence (VALN)vn_VALN_reg	1.528	-0.72	1.971	-0.32	2.328	1.118
92	Valence shift (VALS)vn_VALS_reg	1.395	-1.04	1.803	-0.66	2.518	1.079
93	Velocity flux (VFLX)vn_VFLX_reg	-0.235	-2.06	0.086	-1.80	2.256	1.208
94	Volatility (VOLT)vn_VOLT_reg	2.625	+0.04	2.650	+0.07	2.586	0.886
95	Vulnerability (VULN)vn_VULN_reg	3.514	+0.88	3.075	+0.43	2.648	0.984
96	Warmth (WARM)vn_WARM_reg	3.287	+0.78	3.326	+0.82	2.578	0.909
Genuineness, blend, and legacy quality Genuineness and vocal-burst blend are predicted. R_quality has Ladder training labels but no valid P3 test labels.
97	Genuineness (0–6)genuineness_0_6	2.257	-0.05	2.345	+0.01	2.332	1.621
98	Vocal-burst blend (0–10)blend_0_10	5.094	-0.58	3.586	-1.13	6.676	2.738
99	Legacy R_quality (no P3 test labels)R_quality	0.884	-0.62	0.756	-1.00	1.095	0.338
Empathic Insight Plus extra scores Nineteen additional clip-level teacher scores, including background noise and content enjoyment.
100	Ageeiv_extra:Age	3.623	+1.27	3.322	+0.24	3.250	0.293
101	Arousaleiv_extra:Arousal	0.861	-0.98	1.138	-0.35	1.289	0.435
102	Authenticityeiv_extra:Authenticity	2.771	+0.68	2.921	+1.66	2.667	0.153
103	Background Noiseeiv_extra:Background_Noise	0.334	-1.79	0.534	-1.04	0.808	0.264
104	Confident vs. Hesitanteiv_extra:Confident_vs._Hesitant	1.503	+1.53	1.520	+1.59	1.040	0.303
105	Gendereiv_extra:Gender	-0.504	+0.12	-0.705	-0.08	-0.621	0.999
106	High-Pitched vs. Low-Pitchedeiv_extra:High-Pitched_vs._Low-Pitched	1.724	-0.41	1.842	+0.06	1.827	0.250
107	Monotone vs. Expressiveeiv_extra:Monotone_vs._Expressive	1.128	-1.56	1.674	-0.39	1.859	0.470
108	Recording Qualityeiv_extra:Recording_Quality	2.140	-0.01	2.112	-0.10	2.144	0.332
109	Serious vs. Humorouseiv_extra:Serious_vs._Humorous	0.688	-0.71	0.710	-0.64	0.929	0.340
110	Soft vs. Harsheiv_extra:Soft_vs._Harsh	0.338	+0.18	0.476	+0.61	0.281	0.320
111	Submissive vs. Dominanteiv_extra:Submissive_vs._Dominant	0.186	-0.59	0.451	+0.23	0.376	0.324
112	Valenceeiv_extra:Valence	-0.582	-1.54	-0.978	-2.59	0.005	0.380
113	Vulnerable vs. Emotionally Detachedeiv_extra:Vulnerable_vs._Emotionally_Detached	1.463	-0.58	1.293	-0.97	1.715	0.437
114	Warm vs. Coldeiv_extra:Warm_vs._Cold	-0.003	-0.18	-0.041	-0.31	0.051	0.300
115	score background qualityeiv_extra:score_background_quality	3.968	+0.96	3.651	+0.50	3.301	0.693
116	score content enjoymenteiv_extra:score_content_enjoyment	4.431	-0.25	4.553	+0.15	4.507	0.303
117	score overall qualityeiv_extra:score_overall_quality	3.341	+1.36	3.036	+0.76	2.652	0.507
118	score speech qualityeiv_extra:score_speech_quality	1.887	+0.54	1.913	+0.72	1.808	0.146
Meta AudioBox Aesthetics Four AudioBox aesthetic teacher outputs. Expansions follow the official Meta model card.
119	Content enjoyment (CE)audiobox:CE	4.880	+0.08	4.960	+0.16	4.799	1.018
120	Content usefulness (CU)audiobox:CU	6.116	+0.47	6.005	+0.36	5.649	1.001
121	Production complexity (PC)audiobox:PC	1.833	-0.31	1.959	-0.23	2.331	1.617
122	Production quality (PQ)audiobox:PQ	7.445	+0.46	7.565	+0.59	7.044	0.879
Microsoft DNSMOS Seven DNSMOS teacher outputs: raw and calibrated SIG/BAK/OVRL estimates plus P.808 MOS.
123	Speech signal quality, rawdnsmos:SIG_raw	3.947	+0.07	3.934	+0.05	3.900	0.669
124	Background quality, rawdnsmos:BAK_raw	4.228	+0.90	3.876	+0.59	3.211	1.124
125	Overall quality, rawdnsmos:OVRL_raw	3.615	+0.65	3.465	+0.47	3.085	0.812
126	Speech signal quality, calibrateddnsmos:SIG	3.513	+0.05	3.513	+0.05	3.488	0.501
127	Background quality, calibrateddnsmos:BAK	4.133	+0.80	3.767	+0.41	3.389	0.928
128	Overall quality, calibrateddnsmos:OVRL	3.212	+0.61	3.077	+0.39	2.840	0.606
129	P.808 MOS estimatednsmos:P808_MOS	3.702	+0.57	3.482	+0.12	3.421	0.496
Vocal-burst count The regression target is log(1 + count). A separate table also reports count error after inverse transformation.
130	Vocal-burst count, log(1 + count)burst_count_log1p	0.732	+1.13	0.674	+1.04	0.000	0.647
VoiceCLAP attributes Sixty-one individual VoiceCLAP attribute teacher scores. The raw 768D VoiceCLAP embedding is stored in sidecars but is not a model output.
131	Affectionvoiceclap_attribute:Affection	0.839	-0.20	0.744	-0.37	0.947	0.554
132	Agevoiceclap_attribute:Age	3.396	+0.31	3.362	+0.24	3.229	0.547
133	Amusementvoiceclap_attribute:Amusement	0.350	-0.07	0.213	-0.31	0.392	0.572
134	Angervoiceclap_attribute:Anger	0.961	-0.06	1.411	+0.83	0.992	0.506
135	Arousalvoiceclap_attribute:Arousal	1.270	-0.24	1.331	-0.14	1.420	0.622
136	Astonishment Surprisevoiceclap_attribute:Astonishment_Surprise	0.363	-0.30	0.389	-0.25	0.509	0.479
137	Authenticityvoiceclap_attribute:Authenticity	3.035	+1.59	2.807	+0.22	2.770	0.167
138	Awevoiceclap_attribute:Awe	0.152	-1.49	0.134	-1.56	0.539	0.259
139	Background Noisevoiceclap_attribute:Background_Noise	0.208	-1.36	0.547	-0.08	0.567	0.264
140	Bitternessvoiceclap_attribute:Bitterness	0.661	+0.29	0.749	+0.66	0.592	0.236
141	Concentrationvoiceclap_attribute:Concentration	0.800	-0.78	1.088	-0.24	1.214	0.531
142	Confident vs. Hesitantvoiceclap_attribute:Confident_vs._Hesitant	1.245	+0.38	1.579	+1.09	1.069	0.468
143	Confusionvoiceclap_attribute:Confusion	1.012	+1.10	1.197	+1.66	0.643	0.334
144	Contemplationvoiceclap_attribute:Contemplation	1.301	+1.28	1.147	+0.90	0.780	0.406
145	Contemptvoiceclap_attribute:Contempt	0.539	-0.50	0.629	-0.23	0.709	0.339
146	Contentmentvoiceclap_attribute:Contentment	0.206	-1.25	0.093	-1.61	0.588	0.307
147	Disappointmentvoiceclap_attribute:Disappointment	1.298	+1.85	1.323	+1.94	0.760	0.291
148	Disgustvoiceclap_attribute:Disgust	0.590	-0.17	0.669	+0.22	0.625	0.207
149	Distressvoiceclap_attribute:Distress	0.965	+0.11	1.002	+0.22	0.927	0.350
150	Doubtvoiceclap_attribute:Doubt	1.039	+2.68	1.006	+2.50	0.535	0.188
151	Elationvoiceclap_attribute:Elation	0.115	-1.07	-0.047	-1.48	0.539	0.397
152	Embarrassmentvoiceclap_attribute:Embarrassment	0.650	+1.09	0.539	+0.74	0.307	0.314
153	Emotional Numbnessvoiceclap_attribute:Emotional_Numbness	0.936	+1.02	1.051	+1.45	0.664	0.266
154	Fatigue Exhaustionvoiceclap_attribute:Fatigue_Exhaustion	1.228	+2.94	1.106	+2.47	0.462	0.261
155	Fearvoiceclap_attribute:Fear	0.772	+0.73	0.728	+0.52	0.618	0.212
156	Gendervoiceclap_attribute:Gender	-0.359	-0.21	-0.488	-0.34	-0.151	1.005
157	Helplessnessvoiceclap_attribute:Helplessness	1.034	+1.40	1.034	+1.40	0.658	0.268
158	High-Pitched vs. Low-Pitchedvoiceclap_attribute:High-Pitched_vs._Low-Pitched	1.962	+0.32	2.003	+0.44	1.840	0.375
159	Hope Enthusiasm Optimismvoiceclap_attribute:Hope_Enthusiasm_Optimism	0.283	-1.06	0.153	-1.39	0.705	0.396
160	Impatience and Irritabilityvoiceclap_attribute:Impatience_and_Irritability	1.126	+0.14	1.352	+0.55	1.052	0.541
161	Infatuationvoiceclap_attribute:Infatuation	0.545	-0.19	0.420	-0.57	0.608	0.332
162	Interestvoiceclap_attribute:Interest	0.555	-2.37	0.833	-1.74	1.598	0.440
163	Intoxication Altered States of Consciousnessvoiceclap_attribute:Intoxication_Altered_States_of_Consciousness	0.883	+0.82	0.809	+0.66	0.502	0.463
164	Jealousy & Envyvoiceclap_attribute:Jealousy_&_Envy	0.532	+0.04	0.589	+0.27	0.523	0.245
165	Longingvoiceclap_attribute:Longing	0.929	+1.78	0.812	+1.25	0.538	0.220
166	Malevolence Malicevoiceclap_attribute:Malevolence_Malice	0.580	-0.73	0.835	+0.00	0.833	0.346
167	Monotone vs. Expressivevoiceclap_attribute:Monotone_vs._Expressive	1.430	-0.58	1.592	-0.31	1.775	0.594
168	Painvoiceclap_attribute:Pain	0.628	+1.13	0.648	+1.22	0.381	0.218
169	Pleasure Ecstasyvoiceclap_attribute:Pleasure_Ecstasy	0.208	-0.98	0.161	-1.14	0.503	0.301
170	Pridevoiceclap_attribute:Pride	0.799	+0.05	0.646	-0.39	0.780	0.349
171	Recording Qualityvoiceclap_attribute:Recording_Quality	2.164	-0.46	1.774	-1.65	2.313	0.328
172	Reliefvoiceclap_attribute:Relief	1.144	+0.29	1.268	+0.59	1.025	0.415
173	Sadnessvoiceclap_attribute:Sadness	1.305	+1.77	1.198	+1.42	0.752	0.313
174	Serious vs. Humorousvoiceclap_attribute:Serious_vs._Humorous	0.616	-0.33	0.587	-0.38	0.803	0.568
175	Sexual Lustvoiceclap_attribute:Sexual_Lust	0.026	-1.45	0.066	-1.36	0.635	0.419
176	Shamevoiceclap_attribute:Shame	0.868	+1.21	0.912	+1.36	0.526	0.283
177	Soft vs. Harshvoiceclap_attribute:Soft_vs._Harsh	0.193	+0.09	0.035	-0.35	0.160	0.360
178	Sournessvoiceclap_attribute:Sourness	0.710	+0.02	0.694	-0.04	0.706	0.291
179	Submissive vs. Dominantvoiceclap_attribute:Submissive_vs._Dominant	0.376	-0.69	0.476	-0.41	0.623	0.359
180	Teasingvoiceclap_attribute:Teasing	0.235	-0.81	0.453	-0.23	0.540	0.379
181	Thankfulness Gratitudevoiceclap_attribute:Thankfulness_Gratitude	1.314	-0.13	1.148	-0.45	1.384	0.529
182	Triumphvoiceclap_attribute:Triumph	0.625	-0.25	0.511	-0.57	0.716	0.359
183	Valencevoiceclap_attribute:Valence	-0.740	-1.16	-1.235	-1.94	-0.007	0.635
184	Vulnerable vs. Emotionally Detachedvoiceclap_attribute:Vulnerable_vs._Emotionally_Detached	1.138	-0.90	1.349	-0.52	1.638	0.556
185	Warm vs. Coldvoiceclap_attribute:Warm_vs._Cold	-0.133	-0.17	-0.497	-1.08	-0.066	0.400
186	durationvoiceclap_attribute:duration	10.349	-0.09	11.877	+0.15	10.914	6.354
187	score background qualityvoiceclap_attribute:score_background_quality	3.585	+0.68	3.608	+0.73	3.245	0.498
188	score content enjoymentvoiceclap_attribute:score_content_enjoyment	4.652	-0.02	4.589	-0.46	4.656	0.147
189	score overall qualityvoiceclap_attribute:score_overall_quality	2.942	+0.74	2.966	+0.80	2.635	0.412
190	score speech qualityvoiceclap_attribute:score_speech_quality	1.932	+0.60	1.946	+0.80	1.891	0.069
191	talking speedvoiceclap_attribute:talking_speed	10.808	+0.47	9.490	+0.12	9.028	3.756

All Orange embedding components

The cosine above is the meaningful vector-level comparison; component values have no standalone semantic label.

Timbre — all 128 vector components

Dimension	Tiny	Base	Orange teacher
0	0.0554	0.0602	0.0685
1	-0.0376	-0.0186	-0.0792
2	-0.0193	-0.0328	-0.0782
3	0.0110	-0.0028	-0.0644
4	-0.0889	-0.0582	-0.0750
5	-0.0625	-0.0796	-0.1009
6	-0.0344	-0.0532	-0.0723
7	0.1013	0.1136	0.1131
8	0.0258	0.0226	0.1183
9	-0.0557	-0.0578	-0.0435
10	0.0412	0.0248	0.0884
11	-0.0394	-0.0844	-0.0677
12	0.0089	0.0124	0.0082
13	-0.0812	-0.0896	-0.0787
14	-0.1256	-0.0968	-0.0830
15	-0.0604	-0.0848	-0.0714
16	-0.0770	-0.0777	-0.0987
17	-0.0658	-0.0525	-0.0449
18	-0.0578	-0.0405	-0.0735
19	-0.0634	-0.0175	-0.0754
20	0.2276	0.1256	0.0949
21	0.0363	0.0690	0.0090
22	-0.0696	-0.0757	-0.0750
23	-0.0316	-0.0638	0.0222
24	-0.0566	-0.0762	-0.0643
25	-0.0433	-0.0270	-0.0565
26	-0.0628	-0.0145	-0.0676
27	0.0684	0.1107	0.1350
28	0.0264	0.0050	0.0101
29	0.0070	0.0499	0.0877
30	0.2157	0.1726	0.1571
31	0.0424	0.0477	-0.0235
32	-0.0566	-0.0978	-0.0768
33	-0.1156	-0.1035	-0.0879
34	-0.0711	-0.0424	-0.0671
35	0.2892	0.2445	0.2153
36	-0.0764	-0.0829	-0.0857
37	-0.0519	-0.0892	-0.0944
38	-0.1031	-0.0786	-0.0514
39	-0.0865	-0.1011	-0.0804
40	-0.0190	-0.0484	0.0335
41	-0.1031	-0.1304	-0.1146
42	0.0059	0.0431	0.0275
43	0.0495	0.0671	0.0638
44	0.1991	0.2531	0.1791
45	0.0690	0.1194	0.1401
46	-0.0978	-0.0978	-0.0751
47	-0.0658	-0.0954	-0.0806
48	-0.0265	-0.0040	-0.0707
49	0.0321	0.0108	0.0208
50	0.1132	0.0858	0.0734
51	-0.0972	-0.0978	-0.0797
52	0.0024	-0.0391	-0.0112
53	0.0307	0.0381	0.0670
54	-0.1233	-0.1131	-0.0892
55	0.2252	0.2033	0.1417
56	-0.0161	-0.0270	-0.0756
57	-0.1221	-0.1381	-0.0874
58	0.0096	-0.0146	0.0660
59	0.1541	0.1131	0.1045
60	-0.0865	-0.0872	-0.0769
61	0.2643	0.2061	0.2571
62	-0.0806	-0.0844	-0.0745
63	-0.0361	-0.0400	-0.0633
64	0.0262	0.0009	0.0654
65	-0.0824	-0.0714	-0.0650
66	-0.0083	0.0729	0.0830
67	-0.0800	-0.0935	-0.0769
68	-0.0895	-0.1112	-0.0843
69	-0.0726	-0.1045	-0.0731
70	0.1683	0.1812	0.1598
71	-0.0304	-0.0753	-0.0436
72	-0.0375	-0.0733	-0.0771
73	0.0308	0.0429	0.0967
74	-0.1013	-0.0767	-0.0871
75	0.0239	0.0460	0.1240
76	-0.0036	0.0134	-0.0200
77	-0.0378	-0.0328	-0.0728
78	0.0658	0.0289	0.0031
79	-0.0652	-0.0767	-0.0692
80	-0.0241	-0.0291	-0.0702
81	0.0403	-0.0027	-0.0515
82	-0.0495	-0.0791	-0.0763
83	-0.1090	-0.1059	-0.0816
84	0.0942	0.1069	0.1655
85	0.0587	0.0839	0.0839
86	-0.0441	-0.0709	-0.0781
87	-0.0367	-0.0338	-0.0396
88	-0.0447	-0.0174	-0.0223
89	-0.0483	-0.0652	-0.0732
90	-0.0877	-0.0762	-0.0864
91	0.1576	0.1745	0.1691
92	-0.1037	-0.0676	-0.0774
93	0.1322	0.1985	0.1757
94	0.1310	0.0877	0.1140
95	-0.0602	-0.0695	-0.0856
96	-0.0960	-0.0887	-0.0910
97	-0.0170	-0.0467	-0.0299
98	0.0919	0.1438	0.1167
99	0.0459	0.0312	0.0774
100	0.0581	0.0964	0.0555
101	0.0996	0.0810	0.0689
102	-0.0133	-0.0295	0.0135
103	-0.0616	-0.0705	-0.0842
104	-0.0613	-0.0762	-0.0779
105	-0.0191	-0.0573	-0.0595
106	-0.0560	-0.0549	-0.0535
107	-0.0462	-0.0165	-0.0515
108	-0.0107	-0.0070	-0.0512
109	-0.0770	-0.0666	-0.0782
110	-0.0519	-0.0590	-0.0479
111	-0.1002	-0.1021	-0.0925
112	-0.0613	-0.0815	-0.0786
113	0.0877	0.1165	0.0477
114	-0.0415	-0.0532	-0.0325
115	0.0584	0.0475	0.1431
116	-0.0548	-0.0369	-0.0684
117	0.1576	0.0978	0.1548
118	-0.1730	-0.1170	-0.0776
119	0.0942	0.1496	0.0771
120	-0.0794	-0.0657	-0.0820
121	0.0091	0.0024	0.0757
122	-0.1073	-0.0968	-0.0819
123	-0.0853	-0.0563	-0.0839
124	-0.0307	-0.0443	-0.0773
125	0.0711	0.1141	0.1079
126	-0.0163	-0.0410	-0.0136
127	-0.0524	-0.0511	-0.0067

Identity — all 250 vector components

Dimension	Tiny	Base	Orange teacher
0	-0.0218	-0.0268	-0.0457
1	-0.0499	-0.0458	-0.0402
2	0.0308	0.0541	0.0720
3	-0.0066	-0.0045	0.0304
4	-0.0121	0.0297	-0.0378
5	-0.0664	-0.0191	-0.0434
6	-0.0032	0.0054	0.0139
7	0.0049	-0.0278	-0.0166
8	0.0019	0.0001	-0.0346
9	0.0527	0.0359	0.0511
10	0.0835	0.0643	0.0187
11	-0.0608	-0.0791	-0.0299
12	-0.0997	-0.0900	-0.0455
13	-0.0625	-0.0671	-0.0367
14	-0.0501	-0.0505	0.0058
15	0.0896	0.0408	0.1163
16	0.0913	0.0796	0.0477
17	-0.0437	-0.0606	-0.0499
18	-0.0232	-0.0315	-0.0423
19	-0.0127	-0.0321	-0.0378
20	0.1087	0.1077	0.0420
21	-0.0574	-0.0676	-0.0385
22	-0.0415	-0.0728	-0.0431
23	-0.1025	-0.0895	-0.0402
24	0.0936	0.1129	0.1256
25	0.0043	0.0222	-0.0479
26	-0.0056	0.0364	-0.0341
27	0.0773	0.0401	0.0431
28	0.0069	0.0211	0.0578
29	-0.0571	-0.0481	-0.0400
30	0.0824	0.0414	0.0415
31	0.0924	0.1467	0.0544
32	-0.0036	0.0226	-0.0325
33	0.0868	0.0663	-0.0024
34	-0.0149	-0.0375	-0.0429
35	-0.0169	-0.0367	-0.0535
36	0.0164	-0.0189	0.0084
37	0.0277	0.0291	0.0058
38	0.0028	0.0770	0.0162
39	-0.0431	-0.0604	-0.0327
40	-0.0599	-0.0445	-0.0481
41	0.0868	0.0765	0.0384
42	-0.0087	-0.0380	-0.0413
43	0.0846	0.0666	-0.0294
44	0.0597	0.0640	0.0058
45	0.0043	0.0105	0.0080
46	-0.1003	-0.0957	-0.0610
47	0.0527	0.0489	0.0057
48	0.0165	0.0356	-0.0443
49	-0.0711	-0.0505	-0.0448
50	0.0004	-0.0120	-0.0512
51	0.0647	0.0765	0.0376
52	-0.0234	-0.0043	-0.0396
53	0.0149	0.0427	0.0435
54	0.0569	0.0492	0.0012
55	0.0639	0.0656	0.1145
56	0.0952	0.1025	0.1649
57	-0.0599	-0.0484	-0.0269
58	0.0225	0.0011	-0.0372
59	0.0084	0.0032	0.0676
60	0.0417	0.0424	0.0841
61	-0.0717	-0.0395	-0.0386
62	-0.0373	-0.0585	-0.0365
63	0.0566	0.0138	0.0477
64	-0.0084	-0.0092	-0.0370
65	0.1098	0.0176	-0.0088
66	0.0102	-0.0005	-0.0274
67	0.0835	0.0137	0.0428
68	-0.0361	-0.0440	-0.0447
69	0.0496	0.0656	0.0576
70	-0.0846	-0.0806	-0.0602
71	0.0134	0.0022	-0.0256
72	0.0026	0.0173	0.0200
73	0.0913	0.0754	0.0799
74	-0.0156	-0.0037	-0.0448
75	0.0723	0.0671	0.0792
76	0.0235	0.0189	0.0228
77	-0.0468	-0.0744	-0.0738
78	-0.0644	-0.0406	-0.0605
79	0.0134	0.0150	0.0478
80	-0.0908	-0.0822	-0.0441
81	-0.0255	-0.0484	-0.0183
82	0.0076	-0.0103	-0.0399
83	-0.0555	-0.0476	-0.0369
84	0.0633	0.0069	0.0621
85	0.0874	0.0713	0.1302
86	-0.0367	-0.0445	-0.0396
87	-0.0086	0.0017	0.0485
88	0.0964	0.0973	0.1271
89	0.0239	0.0346	0.0495
90	-0.0290	0.0220	0.0205
91	-0.0340	-0.0445	-0.0522
92	0.0161	-0.0070	0.0184
93	-0.0190	0.0135	-0.0436
94	-0.0807	-0.0601	-0.0679
95	-0.0658	-0.0403	-0.0463
96	-0.0077	0.0191	-0.0078
97	-0.0471	-0.0414	-0.0522
98	0.0347	0.0786	0.0324
99	0.0154	-0.0468	0.0172
100	-0.0378	0.0006	-0.0145
101	0.0347	0.0152	-0.0226
102	0.0557	0.0744	0.0330
103	-0.0403	-0.0138	-0.0438
104	-0.0476	-0.0656	-0.0578
105	-0.0597	-0.0604	-0.0524
106	-0.0667	-0.0760	-0.0342
107	-0.0734	-0.0942	-0.0397
108	0.1994	0.1759	0.2546
109	-0.0315	-0.0606	-0.0426
110	-0.0473	-0.0637	-0.0528
111	-0.0510	-0.0671	-0.0366
112	-0.0081	-0.0088	-0.0358
113	0.0919	0.0864	0.0962
114	-0.0346	-0.0330	-0.0407
115	0.0162	0.0224	-0.0095
116	-0.0192	-0.0042	-0.0019
117	-0.0041	-0.0065	0.0582
118	-0.0846	-0.0676	-0.0427
119	-0.0119	-0.0208	-0.0456
120	-0.0183	-0.0492	-0.0457
121	-0.0018	-0.0272	-0.0035
122	-0.0818	-0.0848	-0.0344
123	0.0276	0.0250	0.0568
124	0.1384	0.0884	0.0065
125	-0.1288	-0.1228	-0.0431
126	0.0762	0.0525	0.1178
127	-0.0636	-0.0848	-0.0456
128	0.0338	0.0578	0.0625
129	0.0902	0.0760	0.0985
130	-0.0695	-0.0786	-0.0446
131	0.0597	0.0299	-0.0271
132	0.0807	0.0349	0.0282
133	0.0159	-0.0041	-0.0019
134	0.0499	0.0278	0.0925
135	-0.0057	-0.0313	-0.0446
136	-0.0153	-0.0098	0.0226
137	0.0784	0.0702	0.0679
138	0.0678	0.0329	-0.0244
139	0.0231	0.0770	0.0275
140	-0.0384	-0.0315	-0.0521
141	-0.0153	-0.0588	-0.0165
142	-0.0513	-0.0570	-0.0383
143	0.0230	0.0123	0.0201
144	-0.0992	-0.1051	-0.0462
145	0.0304	0.0090	0.0026
146	0.1524	0.1061	0.0856
147	0.0059	0.0116	-0.0159
148	0.1160	0.1707	0.1765
149	0.0496	0.1181	0.0805
150	0.0290	0.0622	0.0940
151	0.0339	-0.0313	0.0772
152	-0.0067	-0.0276	-0.0150
153	0.0099	0.0080	0.0068
154	0.0717	0.0630	0.0768
155	-0.0038	-0.0237	0.0103
156	0.0167	0.0102	-0.0170
157	-0.0378	-0.0565	-0.0363
158	0.0216	0.0119	0.0403
159	0.0075	-0.0269	-0.0519
160	0.0857	0.1056	0.1322
161	-0.0591	-0.0264	-0.0762
162	-0.0795	-0.0900	-0.0515
163	-0.0885	-0.0796	-0.0494
164	-0.0627	-0.0276	-0.0389
165	-0.0294	-0.0209	-0.0060
166	-0.0563	-0.0242	-0.0193
167	-0.1008	-0.1530	-0.0562
168	0.0653	0.0606	0.0634
169	0.0300	0.0336	-0.0260
170	-0.0097	-0.0042	-0.0045
171	-0.0403	-0.0531	-0.0390
172	0.1064	0.0723	0.0920
173	0.0033	0.0032	0.0660
174	-0.0658	-0.0575	-0.0455
175	-0.0457	-0.0817	-0.0735
176	0.0375	0.0442	0.0706
177	-0.0361	-0.0385	-0.0365
178	0.0017	-0.0173	-0.0387
179	0.0896	0.1145	0.1212
180	0.2465	0.2144	0.1609
181	-0.1053	-0.0890	-0.0253
182	-0.0521	-0.0432	-0.0383
183	-0.0543	-0.0528	-0.0556
184	-0.0202	-0.0393	0.0044
185	0.0403	0.0225	0.0865
186	-0.0790	-0.0760	-0.0535
187	0.0179	0.0190	0.0738
188	0.0392	0.0063	0.0777
189	0.0202	0.0351	0.0621
190	0.0127	-0.0153	0.0522
191	0.0225	-0.0048	0.0777
192	0.0602	0.0832	0.1218
193	0.0335	0.0921	0.1112
194	0.0119	0.0838	-0.0298
195	-0.0639	-0.0630	-0.0421
196	0.0863	0.0957	0.1022
197	0.0650	0.1233	0.0591
198	0.0157	0.0101	-0.0428
199	0.0552	0.0973	0.0481
200	-0.0647	-0.0656	-0.0513
201	0.0818	0.0131	0.0435
202	-0.0863	-0.0601	-0.0922
203	0.1188	0.1020	0.0198
204	0.1193	0.1181	0.1466
205	-0.0162	-0.0243	-0.0064
206	0.0331	0.0233	-0.0101
207	0.0155	-0.0200	0.0105
208	-0.0139	-0.0098	-0.0460
209	0.0294	-0.0159	0.0615
210	0.1647	0.1342	0.2393
211	0.0013	-0.0325	-0.0341
212	0.0106	-0.0060	0.0748
213	0.0310	-0.0219	0.0501
214	0.2375	0.2331	0.2542
215	-0.0448	-0.0523	-0.0373
216	-0.0608	0.0142	-0.0042
217	-0.0902	-0.0843	-0.0610
218	-0.0412	-0.0177	-0.0236
219	-0.0639	-0.0416	-0.0577
220	-0.0150	-0.0708	-0.0490
221	-0.0097	0.0246	-0.0291
222	-0.0090	-0.0325	-0.0351
223	-0.0395	-0.0269	-0.0356
224	-0.0054	-0.0226	-0.0201
225	0.0829	0.0884	0.1467
226	-0.0008	0.0494	-0.0105
227	0.0689	0.0585	0.0245
228	-0.0159	0.0265	-0.0718
229	-0.0028	-0.0251	0.0085
230	-0.0283	0.0146	0.0331
231	0.0451	0.0063	0.0603
232	-0.0317	-0.0338	0.0059
233	-0.0220	-0.0105	-0.0905
234	0.2095	0.1707	0.1511
235	0.1171	0.1415	0.1078
236	-0.0109	-0.0293	-0.0381
237	-0.0122	-0.0267	-0.0453
238	0.0361	0.0687	0.0475
239	-0.0262	-0.0346	-0.0458
240	0.0190	0.0312	0.0457
241	0.0454	0.0113	0.0542
242	-0.0241	-0.0238	-0.0342
243	-0.0767	-0.1186	-0.0570
244	-0.0667	-0.0682	-0.0471
245	-0.0619	-0.0900	-0.0421
246	-0.0356	-0.0874	-0.0359
247	-0.0300	-0.0536	-0.0373
248	-0.0767	-0.0640	-0.0507
249	-0.0127	-0.0421	-0.0073

Source: HUMANENESS_SMALL_VOICE_IDENTITY_R1_R2_2026-10-02_mediathek_0047.html · SHA-256 55f329d7c43b46e6…

g09EnglishAnime voice study

anime_000 · en · 6/50

Generated TTS prediction · Rank 1 qkvo · 5.4 s

It's just how things work, you know? (soft whistle) And honestly, I'm not sure if you can really control it.

Tiny Base · values are model estimates, not ground truth

Strongest emotions relative to training

Doubt

z +2.64 / +3.43raw 1.24 / 1.61

Hope Enthusiasm Optimism

z +1.72 / +2.19raw 1.43 / 1.78

Contentment

z +0.80 / +1.38raw 0.41 / 0.71

Affection

z +0.73 / +1.31raw 0.42 / 0.75

Contemplation

z +0.75 / +1.07raw 0.53 / 0.72

Confusion

z +0.35 / +0.86raw 0.19 / 0.47

Teasing

z +0.80 / +0.34raw 0.44 / 0.18

The center of each bar is the S9 teacher median. Positive z is to the right; negative z is to the left. Ranking uses z, not raw teacher units.

Strongest VoiceNet dimensions relative to training

Vocal register (REGS)

z +2.27 / +2.33raw 4.08 / 4.15

Head resonance (R_HEAD)

z +2.23 / +2.28raw 3.98 / 4.02

Brightness (BRGT)

z +2.04 / +2.15raw 3.65 / 3.74

Storytelling style (S_STRY)

z +1.65 / +1.81raw 4.74 / 4.95

Cartoonish style (S_CART)

z +1.64 / +1.72raw 3.85 / 3.97

Conversational style (S_CONV)

z +1.54 / +1.35raw 4.62 / 4.37

Dramatic style (S_DRAM)

z +1.43 / +1.34raw 4.36 / 4.26

All 57 VoiceNet predictions, including raw units, are in the full table below. These seven are ranked by z; the top values may differ from the strongest raw dimensions.

Voice, speed and quality scores in context

Genuineness (0–6)z -0.61 / -0.70raw 1.34 / 1.19

Vocal-burst blend (0–10)z +0.30 / +0.43raw 7.51 / 7.86

Content enjoyment (CE)z +0.84 / +1.04raw 5.65 / 5.86

Production quality (PQ)z -0.01 / +0.24raw 7.04 / 7.26

Speech signal quality, calibratedz -0.34 / -0.17raw 3.32 / 3.40

Background quality, calibratedz +0.15 / +0.49raw 3.53 / 3.84

Overall quality, calibratedz -0.03 / +0.32raw 2.83 / 3.04

P.808 MOS estimatez -0.16 / +0.31raw 3.34 / 3.57

score content enjoymentz +0.72 / +0.77raw 4.73 / 4.74

score overall qualityz +0.01 / +0.15raw 2.65 / 2.73

Background Noisez -1.71 / -3.27raw 0.35 / -0.06

Tempo (TEMP)z +0.86 / +0.88raw 3.14 / 3.17

Arousal (AROU)z +0.11 / +0.19raw 2.49 / 2.58

Valence (VALN)z -0.12 / -0.19raw 2.19 / 2.11

Recording quality (RCQL)z +0.78 / +1.15raw 3.45 / 3.78

Background noise (BKGN)z +0.69 / +0.56raw 3.23 / 3.13

talking speedz +1.55 / +1.46raw 14.85 / 14.52

Characters per second (CPS): 20.00 raw · z +2.92

Orange speaker embedding reconstruction

Cosine against Orange on this same clip (higher means closer to that teacher vector):

Embedding	Tiny	Base
Timbre · 128D	0.808	0.889
Identity · 250D	0.650	0.684

Vocal-burst regions

Tiny

Base

0 s5.4 s

Verified burst intervals are unavailable for this clip.

Tiny: 0 regions, count-head estimate 0.00; Base: 0 regions, count-head estimate 0.02.

Exact predicted start and end times

Model	Region	Start (s)	End (s)	Duration (s)

All 192 score slots · raw and z values

#	Target	Tiny raw	Tiny z	Base raw	Base z	Train median	Train SD
Emotion scores Forty clip-level Empathic Insight emotion teacher outputs. Each row evaluates one named emotion score.
0	Affectionemo_Affection	0.424	+0.73	0.751	+1.31	0.007	0.570
1	Amusementemo_Amusement	0.247	+0.28	0.110	+0.13	-0.001	0.885
2	Angeremo_Anger	0.105	+0.16	-0.041	-0.07	0.004	0.613
3	Astonishment Surpriseemo_Astonishment_Surprise	0.318	+0.55	0.403	+0.70	0.005	0.572
4	Aweemo_Awe	-0.013	-0.03	0.104	+0.24	0.000	0.427
5	Bitternessemo_Bitterness	0.002	-0.03	0.034	+0.05	0.013	0.415
6	Concentrationemo_Concentration	0.368	-0.36	0.237	-0.54	0.634	0.741
7	Confusionemo_Confusion	0.192	+0.35	0.467	+0.86	0.001	0.540
8	Contemplationemo_Contemplation	0.531	+0.75	0.722	+1.07	0.082	0.598
9	Contemptemo_Contempt	0.011	+0.02	0.064	+0.14	-0.000	0.464
10	Contentmentemo_Contentment	0.411	+0.80	0.710	+1.38	0.000	0.514
11	Disappointmentemo_Disappointment	0.225	+0.32	0.051	+0.07	0.000	0.700
12	Disgustemo_Disgust	-0.004	-0.02	0.019	+0.02	0.007	0.489
13	Distressemo_Distress	0.058	+0.07	-0.116	-0.14	0.000	0.821
14	Doubtemo_Doubt	1.235	+2.64	1.605	+3.43	0.006	0.466
15	Elationemo_Elation	0.461	+0.62	0.486	+0.65	0.012	0.728
16	Embarrassmentemo_Embarrassment	0.068	+0.06	-0.019	-0.14	0.043	0.430
17	Emotional Numbnessemo_Emotional_Numbness	0.079	+0.08	0.004	-0.00	0.004	0.917
18	Fatigue Exhaustionemo_Fatigue_Exhaustion	0.045	+0.03	0.006	-0.04	0.028	0.539
19	Fearemo_Fear	0.077	+0.10	0.028	+0.02	0.015	0.610
20	Helplessnessemo_Helplessness	0.175	+0.26	0.197	+0.29	-0.004	0.696
21	Hope Enthusiasm Optimismemo_Hope_Enthusiasm_Optimism	1.428	+1.72	1.784	+2.19	0.117	0.760
22	Impatience and Irritabilityemo_Impatience_and_Irritability	0.383	+0.33	0.105	-0.06	0.149	0.705
23	Infatuationemo_Infatuation	-0.001	+0.03	0.016	+0.06	-0.015	0.533
24	Interestemo_Interest	1.938	+0.39	2.024	+0.48	1.589	0.907
25	Intoxication Altered States of Consciousnessemo_Intoxication_Altered_States_of_Consciousness	0.014	+0.07	0.010	+0.06	-0.025	0.559
26	Jealousy and Envyemo_Jealousy_and_Envy	0.042	-0.04	0.040	-0.04	0.059	0.442
27	Longingemo_Longing	0.110	+0.04	0.018	-0.11	0.087	0.632
28	Malevolence Maliceemo_Malevolence_Malice	0.064	+0.02	0.016	-0.07	0.055	0.534
29	Painemo_Pain	-0.003	-0.00	-0.037	-0.06	-0.002	0.579
30	Pleasure Ecstasyemo_Pleasure_Ecstasy	0.399	+0.62	0.507	+0.80	0.017	0.614
31	Prideemo_Pride	-0.009	-0.02	0.023	+0.04	0.002	0.509
32	Reliefemo_Relief	0.227	+0.28	0.423	+0.57	0.033	0.681
33	Sadnessemo_Sadness	0.056	+0.07	0.077	+0.10	0.000	0.759
34	Sexual Lustemo_Sexual_Lust	0.078	+0.10	-0.008	-0.08	0.030	0.494
35	Shameemo_Shame	-0.010	-0.04	0.006	-0.01	0.013	0.510
36	Sournessemo_Sourness	0.148	+0.35	0.001	+0.02	-0.005	0.439
37	Teasingemo_Teasing	0.438	+0.80	0.183	+0.34	0.000	0.545
38	Thankfulness Gratitudeemo_Thankfulness_Gratitude	0.072	+0.04	0.203	+0.23	0.041	0.697
39	Triumphemo_Triumph	-0.018	-0.02	0.017	+0.05	-0.007	0.521
VoiceNet dimensions Fifty-seven VoiceNet voice, delivery, style, and recording dimensions. Codes are expanded in the target column.
40	Perceived voice age (AGEV)vn_AGEV_reg	2.002	-0.79	2.216	-0.62	2.984	1.238
41	Arousal (AROU)vn_AROU_reg	2.486	+0.11	2.579	+0.19	2.359	1.147
42	Arousal shift (ARSH)vn_ARSH_reg	2.697	+0.14	2.686	+0.12	2.580	0.867
43	Vocal attack (ATCK)vn_ATCK_reg	1.432	-0.56	1.360	-0.62	2.162	1.295
44	Background noise (BKGN)vn_BKGN_reg	3.228	+0.69	3.131	+0.56	2.703	0.761
45	Brightness (BRGT)vn_BRGT_reg	3.648	+2.04	3.737	+2.15	1.991	0.813
46	Speech chunking (CHNK)vn_CHNK_reg	2.612	+0.62	2.617	+0.62	1.847	1.239
47	Articulation clarity (CLRT)vn_CLRT_reg	2.324	+0.32	2.532	+0.54	2.018	0.945
48	Cognitive load (COGL)vn_COGL_reg	1.845	-0.23	1.583	-0.48	2.094	1.061
49	Dynamic arc (DARC)vn_DARC_reg	2.538	+0.67	2.538	+0.67	1.615	1.380
50	Disfluency (DFLU)vn_DFLU_reg	2.216	-0.23	2.118	-0.31	2.488	1.184
51	Emphasis (EMPH)vn_EMPH_reg	3.068	+0.30	3.289	+0.45	2.607	1.524
52	Esthetics (ESTH)vn_ESTH_reg	3.444	+1.33	3.377	+1.25	2.402	0.782
53	Content appropriateness (EXPL)vn_EXPL_reg	-0.151	-0.74	-0.169	-0.79	0.086	0.322
54	Focus (FOCS)vn_FOCS_reg	3.386	+0.95	3.386	+0.95	2.344	1.102
55	Fullness (FULL)vn_FULL_reg	1.399	-0.43	1.627	-0.17	1.778	0.889
56	Perceived gender (GEND)vn_GEND_reg	0.435	-2.28	0.535	-2.22	4.055	1.588
57	Harmonicity (HARM)vn_HARM_reg	1.404	-1.29	1.353	-1.35	2.480	0.836
58	Metallic character (METL)vn_METL_reg	0.966	-0.68	0.902	-0.75	1.621	0.958
59	Pitch range (RANG)vn_RANG_reg	4.062	+1.28	4.055	+1.27	2.914	0.897
60	Recording quality (RCQL)vn_RCQL_reg	3.448	+0.78	3.778	+1.15	2.754	0.888
61	Vocal register (REGS)vn_REGS_reg	4.082	+2.27	4.151	+2.33	1.198	1.268
62	Respiration (RESP)vn_RESP_reg	3.578	+0.85	3.402	+0.68	2.680	1.056
63	Roughness (ROUG)vn_ROUG_reg	1.365	-0.75	1.423	-0.69	2.033	0.887
64	Chest resonance (R_CHST)vn_R_CHST_reg	1.060	-1.27	1.013	-1.33	2.135	0.844
65	Head resonance (R_HEAD)vn_R_HEAD_reg	3.984	+2.23	4.022	+2.28	2.148	0.822
66	Mask resonance (R_MASK)vn_R_MASK_reg	2.914	+1.00	3.042	+1.13	1.908	1.005
67	Mixed resonance (R_MIXD)vn_R_MIXD_reg	1.452	+0.02	1.358	-0.09	1.436	0.841
68	Nasal resonance (R_NASL)vn_R_NASL_reg	3.601	+0.77	3.291	+0.48	2.791	1.047
69	Oral resonance (R_ORAL)vn_R_ORAL_reg	2.705	+0.70	2.504	+0.43	2.184	0.741
70	Throat resonance (R_THRT)vn_R_THRT_reg	1.878	-0.24	1.834	-0.29	2.070	0.803
71	Smoothness (SMTH)vn_SMTH_reg	2.291	+0.14	2.315	+0.16	2.143	1.093
72	Stance (STNC)vn_STNC_reg	1.595	-0.91	1.604	-0.90	2.633	1.137
73	Speech structure (STRU)vn_STRU_reg	2.961	+0.86	2.938	+0.84	2.137	0.958
74	ASMR style (S_ASMR)vn_S_ASMR_reg	1.452	+0.06	1.612	+0.17	1.370	1.411
75	Authoritative style (S_AUTH)vn_S_AUTH_reg	0.177	-0.87	0.323	-0.73	1.088	1.043
76	Cartoonish style (S_CART)vn_S_CART_reg	3.851	+1.64	3.969	+1.72	1.560	1.401
77	Casual style (S_CASU)vn_S_CASU_reg	3.819	+0.02	3.947	+0.12	3.793	1.278
78	Conversational style (S_CONV)vn_S_CONV_reg	4.624	+1.54	4.369	+1.35	2.594	1.318
79	Dramatic style (S_DRAM)vn_S_DRAM_reg	4.364	+1.43	4.257	+1.34	2.721	1.148
80	Formal style (S_FORM)vn_S_FORM_reg	0.938	-0.25	0.948	-0.24	1.195	1.021
81	Monologue style (S_MONO)vn_S_MONO_reg	2.576	-0.19	2.769	-0.04	2.824	1.284
82	Narrator style (S_NARR)vn_S_NARR_reg	3.011	+1.18	3.090	+1.23	1.307	1.446
83	Newsreader style (S_NEWS)vn_S_NEWS_reg	0.221	-0.33	0.319	-0.16	0.408	0.568
84	Playful style (S_PLAY)vn_S_PLAY_reg	3.914	+1.19	3.965	+1.23	2.352	1.315
85	Ranting or angry style (S_RANT)vn_S_RANT_reg	1.730	+0.40	1.763	+0.43	1.213	1.289
86	Storytelling style (S_STRY)vn_S_STRY_reg	4.737	+1.65	4.955	+1.81	2.480	1.366
87	Teacher or didactic style (S_TECH)vn_S_TECH_reg	1.123	+0.39	1.304	+0.54	0.646	1.227
88	Whispered talking style (S_WHIS)vn_S_WHIS_reg	3.703	+1.30	3.391	+1.11	1.597	1.618
89	Tempo (TEMP)vn_TEMP_reg	3.137	+0.86	3.170	+0.88	2.117	1.190
90	Tension (TENS)vn_TENS_reg	1.690	+0.15	1.897	+0.40	1.559	0.852
91	Valence (VALN)vn_VALN_reg	2.193	-0.12	2.111	-0.19	2.328	1.118
92	Valence shift (VALS)vn_VALS_reg	2.884	+0.34	2.674	+0.14	2.518	1.079
93	Velocity flux (VFLX)vn_VFLX_reg	3.041	+0.65	2.961	+0.58	2.256	1.208
94	Volatility (VOLT)vn_VOLT_reg	3.424	+0.95	3.397	+0.92	2.586	0.886
95	Vulnerability (VULN)vn_VULN_reg	3.533	+0.90	3.622	+0.99	2.648	0.984
96	Warmth (WARM)vn_WARM_reg	2.072	-0.56	2.216	-0.40	2.578	0.909
Genuineness, blend, and legacy quality Genuineness and vocal-burst blend are predicted. R_quality has Ladder training labels but no valid P3 test labels.
97	Genuineness (0–6)genuineness_0_6	1.338	-0.61	1.194	-0.70	2.332	1.621
98	Vocal-burst blend (0–10)blend_0_10	7.509	+0.30	7.865	+0.43	6.676	2.738
99	Legacy R_quality (no P3 test labels)R_quality	0.976	-0.35	0.987	-0.32	1.095	0.338
Empathic Insight Plus extra scores Nineteen additional clip-level teacher scores, including background noise and content enjoyment.
100	Ageeiv_extra:Age	3.044	-0.70	3.109	-0.48	3.250	0.293
101	Arousaleiv_extra:Arousal	1.602	+0.72	1.583	+0.68	1.289	0.435
102	Authenticityeiv_extra:Authenticity	3.008	+2.23	3.141	+3.10	2.667	0.153
103	Background Noiseeiv_extra:Background_Noise	0.354	-1.71	-0.056	-3.27	0.808	0.264
104	Confident vs. Hesitanteiv_extra:Confident_vs._Hesitant	1.456	+1.38	1.337	+0.98	1.040	0.303
105	Gendereiv_extra:Gender	1.185	+1.81	1.325	+1.95	-0.621	0.999
106	High-Pitched vs. Low-Pitchedeiv_extra:High-Pitched_vs._Low-Pitched	1.378	-1.80	1.210	-2.47	1.827	0.250
107	Monotone vs. Expressiveeiv_extra:Monotone_vs._Expressive	2.188	+0.70	2.214	+0.76	1.859	0.470
108	Recording Qualityeiv_extra:Recording_Quality	2.544	+1.20	2.731	+1.77	2.144	0.332
109	Serious vs. Humorouseiv_extra:Serious_vs._Humorous	1.142	+0.62	1.248	+0.94	0.929	0.340
110	Soft vs. Harsheiv_extra:Soft_vs._Harsh	0.662	+1.19	0.902	+1.94	0.281	0.320
111	Submissive vs. Dominanteiv_extra:Submissive_vs._Dominant	0.390	+0.04	0.414	+0.12	0.376	0.324
112	Valenceeiv_extra:Valence	0.260	+0.67	0.438	+1.14	0.005	0.380
113	Vulnerable vs. Emotionally Detachedeiv_extra:Vulnerable_vs._Emotionally_Detached	1.235	-1.10	0.928	-1.80	1.715	0.437
114	Warm vs. Coldeiv_extra:Warm_vs._Cold	0.491	+1.47	0.965	+3.04	0.051	0.300
115	score background qualityeiv_extra:score_background_quality	3.379	+0.11	3.456	+0.22	3.301	0.693
116	score content enjoymenteiv_extra:score_content_enjoyment	4.726	+0.72	4.742	+0.77	4.507	0.303
117	score overall qualityeiv_extra:score_overall_quality	2.655	+0.01	2.727	+0.15	2.652	0.507
118	score speech qualityeiv_extra:score_speech_quality	1.893	+0.58	1.901	+0.64	1.808	0.146
Meta AudioBox Aesthetics Four AudioBox aesthetic teacher outputs. Expansions follow the official Meta model card.
119	Content enjoyment (CE)audiobox:CE	5.649	+0.84	5.856	+1.04	4.799	1.018
120	Content usefulness (CU)audiobox:CU	6.401	+0.75	6.667	+1.02	5.649	1.001
121	Production complexity (PC)audiobox:PC	1.820	-0.32	1.587	-0.46	2.331	1.617
122	Production quality (PQ)audiobox:PQ	7.039	-0.01	7.256	+0.24	7.044	0.879
Microsoft DNSMOS Seven DNSMOS teacher outputs: raw and calibrated SIG/BAK/OVRL estimates plus P.808 MOS.
123	Speech signal quality, rawdnsmos:SIG_raw	3.614	-0.43	3.766	-0.20	3.900	0.669
124	Background quality, rawdnsmos:BAK_raw	3.601	+0.35	3.920	+0.63	3.211	1.124
125	Overall quality, rawdnsmos:OVRL_raw	3.111	+0.03	3.395	+0.38	3.085	0.812
126	Speech signal quality, calibrateddnsmos:SIG	3.320	-0.34	3.403	-0.17	3.488	0.501
127	Background quality, calibrateddnsmos:BAK	3.531	+0.15	3.840	+0.49	3.389	0.928
128	Overall quality, calibrateddnsmos:OVRL	2.825	-0.03	3.037	+0.32	2.840	0.606
129	P.808 MOS estimatednsmos:P808_MOS	3.339	-0.16	3.575	+0.31	3.421	0.496
Vocal-burst count The regression target is log(1 + count). A separate table also reports count error after inverse transformation.
130	Vocal-burst count, log(1 + count)burst_count_log1p	-0.005	-0.01	0.015	+0.02	0.000	0.647
VoiceCLAP attributes Sixty-one individual VoiceCLAP attribute teacher scores. The raw 768D VoiceCLAP embedding is stored in sidecars but is not a model output.
131	Affectionvoiceclap_attribute:Affection	1.544	+1.08	1.212	+0.48	0.947	0.554
132	Agevoiceclap_attribute:Age	2.436	-1.45	2.724	-0.92	3.229	0.547
133	Amusementvoiceclap_attribute:Amusement	0.641	+0.43	0.685	+0.51	0.392	0.572
134	Angervoiceclap_attribute:Anger	0.708	-0.56	0.514	-0.95	0.992	0.506
135	Arousalvoiceclap_attribute:Arousal	1.917	+0.80	1.595	+0.28	1.420	0.622
136	Astonishment Surprisevoiceclap_attribute:Astonishment_Surprise	1.482	+2.03	1.654	+2.39	0.509	0.479
137	Authenticityvoiceclap_attribute:Authenticity	3.315	+3.26	3.347	+3.45	2.770	0.167
138	Awevoiceclap_attribute:Awe	0.714	+0.68	0.999	+1.77	0.539	0.259
139	Background Noisevoiceclap_attribute:Background_Noise	0.228	-1.29	0.156	-1.56	0.567	0.264
140	Bitternessvoiceclap_attribute:Bitterness	0.243	-1.48	0.204	-1.65	0.592	0.236
141	Concentrationvoiceclap_attribute:Concentration	0.547	-1.26	0.646	-1.07	1.214	0.531
142	Confident vs. Hesitantvoiceclap_attribute:Confident_vs._Hesitant	1.370	+0.64	1.500	+0.92	1.069	0.468
143	Confusionvoiceclap_attribute:Confusion	1.064	+1.26	0.850	+0.62	0.643	0.334
144	Contemplationvoiceclap_attribute:Contemplation	0.469	-0.77	0.512	-0.66	0.780	0.406
145	Contemptvoiceclap_attribute:Contempt	0.399	-0.92	0.247	-1.36	0.709	0.339
146	Contentmentvoiceclap_attribute:Contentment	0.646	+0.19	0.667	+0.26	0.588	0.307
147	Disappointmentvoiceclap_attribute:Disappointment	0.914	+0.53	0.800	+0.14	0.760	0.291
148	Disgustvoiceclap_attribute:Disgust	0.638	+0.06	0.589	-0.17	0.625	0.207
149	Distressvoiceclap_attribute:Distress	1.130	+0.58	1.148	+0.63	0.927	0.350
150	Doubtvoiceclap_attribute:Doubt	0.791	+1.36	0.853	+1.69	0.535	0.188
151	Elationvoiceclap_attribute:Elation	0.519	-0.05	0.686	+0.37	0.539	0.397
152	Embarrassmentvoiceclap_attribute:Embarrassment	0.454	+0.47	0.543	+0.75	0.307	0.314
153	Emotional Numbnessvoiceclap_attribute:Emotional_Numbness	0.488	-0.66	0.414	-0.94	0.664	0.266
154	Fatigue Exhaustionvoiceclap_attribute:Fatigue_Exhaustion	0.233	-0.88	0.223	-0.91	0.462	0.261
155	Fearvoiceclap_attribute:Fear	0.925	+1.45	0.925	+1.45	0.618	0.212
156	Gendervoiceclap_attribute:Gender	1.380	+1.52	1.356	+1.50	-0.151	1.005
157	Helplessnessvoiceclap_attribute:Helplessness	1.032	+1.39	0.872	+0.80	0.658	0.268
158	High-Pitched vs. Low-Pitchedvoiceclap_attribute:High-Pitched_vs._Low-Pitched	1.122	-1.92	1.175	-1.78	1.840	0.375
159	Hope Enthusiasm Optimismvoiceclap_attribute:Hope_Enthusiasm_Optimism	1.084	+0.96	1.370	+1.68	0.705	0.396
160	Impatience and Irritabilityvoiceclap_attribute:Impatience_and_Irritability	0.994	-0.11	0.889	-0.30	1.052	0.541
161	Infatuationvoiceclap_attribute:Infatuation	1.015	+1.22	0.963	+1.07	0.608	0.332
162	Interestvoiceclap_attribute:Interest	1.698	+0.23	1.827	+0.52	1.598	0.440
163	Intoxication Altered States of Consciousnessvoiceclap_attribute:Intoxication_Altered_States_of_Consciousness	0.200	-0.65	0.111	-0.84	0.502	0.463
164	Jealousy & Envyvoiceclap_attribute:Jealousy_&_Envy	1.029	+2.07	1.066	+2.22	0.523	0.245
165	Longingvoiceclap_attribute:Longing	0.873	+1.52	0.847	+1.41	0.538	0.220
166	Malevolence Malicevoiceclap_attribute:Malevolence_Malice	0.500	-0.96	0.362	-1.36	0.833	0.346
167	Monotone vs. Expressivevoiceclap_attribute:Monotone_vs._Expressive	2.031	+0.43	2.357	+0.98	1.775	0.594
168	Painvoiceclap_attribute:Pain	0.571	+0.87	0.411	+0.14	0.381	0.218
169	Pleasure Ecstasyvoiceclap_attribute:Pleasure_Ecstasy	0.729	+0.75	0.604	+0.34	0.503	0.301
170	Pridevoiceclap_attribute:Pride	0.329	-1.29	0.318	-1.32	0.780	0.349
171	Recording Qualityvoiceclap_attribute:Recording_Quality	2.725	+1.26	2.838	+1.60	2.313	0.328
172	Reliefvoiceclap_attribute:Relief	1.195	+0.41	1.213	+0.46	1.025	0.415
173	Sadnessvoiceclap_attribute:Sadness	0.992	+0.77	1.002	+0.80	0.752	0.313
174	Serious vs. Humorousvoiceclap_attribute:Serious_vs._Humorous	0.758	-0.08	0.948	+0.26	0.803	0.568
175	Sexual Lustvoiceclap_attribute:Sexual_Lust	0.361	-0.65	0.441	-0.46	0.635	0.419
176	Shamevoiceclap_attribute:Shame	0.794	+0.94	0.901	+1.32	0.526	0.283
177	Soft vs. Harshvoiceclap_attribute:Soft_vs._Harsh	0.757	+1.66	0.579	+1.17	0.160	0.360
178	Sournessvoiceclap_attribute:Sourness	0.794	+0.30	0.535	-0.59	0.706	0.291
179	Submissive vs. Dominantvoiceclap_attribute:Submissive_vs._Dominant	0.152	-1.31	0.166	-1.28	0.623	0.359
180	Teasingvoiceclap_attribute:Teasing	0.832	+0.77	0.751	+0.56	0.540	0.379
181	Thankfulness Gratitudevoiceclap_attribute:Thankfulness_Gratitude	1.586	+0.38	1.298	-0.16	1.384	0.529
182	Triumphvoiceclap_attribute:Triumph	0.333	-1.07	0.513	-0.57	0.716	0.359
183	Valencevoiceclap_attribute:Valence	-0.105	-0.15	0.392	+0.63	-0.007	0.635
184	Vulnerable vs. Emotionally Detachedvoiceclap_attribute:Vulnerable_vs._Emotionally_Detached	0.532	-1.99	0.454	-2.13	1.638	0.556
185	Warm vs. Coldvoiceclap_attribute:Warm_vs._Cold	0.236	+0.76	0.461	+1.32	-0.066	0.400
186	durationvoiceclap_attribute:duration	7.479	-0.54	6.984	-0.62	10.914	6.354
187	score background qualityvoiceclap_attribute:score_background_quality	3.511	+0.53	3.462	+0.44	3.245	0.498
188	score content enjoymentvoiceclap_attribute:score_content_enjoyment	4.792	+0.93	4.751	+0.65	4.656	0.147
189	score overall qualityvoiceclap_attribute:score_overall_quality	2.655	+0.05	2.704	+0.17	2.635	0.412
190	score speech qualityvoiceclap_attribute:score_speech_quality	1.964	+1.05	1.961	+1.02	1.891	0.069
191	talking speedvoiceclap_attribute:talking_speed	14.846	+1.55	14.524	+1.46	9.028	3.756

All Orange embedding components

The cosine above is the meaningful vector-level comparison; component values have no standalone semantic label.

Timbre — all 128 vector components

Dimension	Tiny	Base	Orange teacher
0	0.0064	-0.0146	-0.0671
1	0.1684	0.1217	0.0802
2	0.1004	0.1079	0.1346
3	-0.0948	-0.1142	-0.0776
4	-0.0427	-0.0479	-0.0720
5	-0.1316	-0.1119	-0.0969
6	0.0979	0.0542	0.0241
7	0.1759	0.1707	0.2299
8	-0.0161	0.0231	-0.0067
9	-0.0335	-0.0750	0.0759
10	-0.0437	-0.0467	0.0359
11	-0.0440	-0.0761	-0.0895
12	-0.0885	-0.0859	-0.0770
13	-0.0717	-0.0314	-0.0451
14	0.1534	0.1592	0.1450
15	-0.0181	0.0433	0.0380
16	-0.1066	-0.1021	-0.0948
17	-0.0655	-0.0643	-0.0796
18	-0.0811	-0.0666	-0.0087
19	-0.0577	-0.0859	-0.0724
20	-0.0229	-0.0606	-0.0767
21	-0.0103	0.0012	-0.0035
22	-0.0948	-0.0482	-0.0615
23	-0.1659	-0.0992	-0.0906
24	-0.0189	-0.0015	0.0456
25	-0.0811	-0.0744	-0.0673
26	-0.0611	-0.0649	-0.0718
27	-0.0345	-0.0389	-0.0714
28	-0.0748	-0.0854	-0.0844
29	0.1054	0.0427	0.0769
30	0.0761	0.0395	-0.0533
31	-0.0549	-0.0600	-0.0308
32	0.2245	0.2676	0.1733
33	0.0129	-0.0267	-0.0347
34	-0.0689	-0.0756	-0.0687
35	0.0854	0.0981	0.0962
36	-0.0948	-0.0600	-0.0823
37	-0.0505	-0.0415	-0.0906
38	0.0885	0.1534	0.1613
39	-0.1048	-0.0470	-0.0772
40	0.0627	0.0802	0.0440
41	-0.0004	-0.0464	-0.0521
42	-0.0733	-0.0738	-0.0772
43	-0.0288	-0.0120	-0.0149
44	0.0293	-0.0061	0.0014
45	-0.0265	-0.0796	-0.0461
46	0.1995	0.1309	0.0773
47	-0.1191	-0.1246	-0.0774
48	-0.0892	-0.0906	-0.0748
49	-0.0564	-0.0317	-0.0551
50	0.0558	0.0093	-0.0037
51	0.0138	0.0900	0.0914
52	-0.0552	-0.0268	-0.0421
53	-0.0543	-0.0718	-0.0781
54	-0.0904	-0.1021	-0.0857
55	-0.0357	-0.0735	-0.0103
56	-0.0733	-0.0934	-0.0726
57	0.0030	-0.0092	-0.0427
58	-0.0421	0.0102	0.0598
59	0.0711	0.0513	0.0828
60	0.0521	0.0709	0.0582
61	0.1734	0.1638	0.1572
62	-0.0309	0.0871	0.0773
63	0.0120	-0.0232	-0.0457
64	-0.0081	-0.0018	-0.0233
65	-0.0608	-0.0790	-0.0624
66	0.1285	0.1032	0.1564
67	-0.0486	-0.0678	-0.0739
68	0.0720	0.0281	0.0307
69	0.0315	0.0239	0.0657
70	0.0511	0.0761	0.0361
71	0.2968	0.2342	0.1873
72	-0.0302	0.0324	0.0271
73	0.0231	-0.0039	-0.0165
74	-0.0365	0.0235	0.1207
75	0.2494	0.2296	0.1770
76	0.1278	0.1257	0.1493
77	-0.0555	-0.0842	-0.0699
78	-0.0720	-0.0718	-0.0681
79	-0.0110	0.0510	-0.0664
80	-0.0455	-0.0424	-0.0389
81	0.1235	0.1834	0.2500
82	-0.1029	-0.0666	-0.0732
83	0.1746	0.1742	0.2549
84	-0.1035	-0.1096	-0.0949
85	0.0493	0.0882	0.0621
86	-0.0148	-0.0242	0.0650
87	-0.0539	-0.0738	-0.0884
88	-0.0168	-0.0044	0.0422
89	-0.0465	-0.0767	-0.0703
90	0.0424	0.1061	0.0088
91	0.0144	-0.0091	0.0128
92	-0.0214	-0.0212	-0.0074
93	-0.0730	-0.0975	-0.0596
94	-0.0131	-0.0257	-0.0558
95	-0.0733	-0.0378	-0.0822
96	-0.1147	-0.1523	-0.0806
97	0.1253	0.1477	0.1438
98	-0.0490	-0.0643	-0.0432
99	0.1166	0.1407	0.1155
100	0.1465	0.1615	0.1823
101	0.0240	0.0040	-0.0740
102	-0.0157	0.0151	0.0938
103	-0.0773	-0.0796	-0.0808
104	0.0967	0.0900	0.0065
105	-0.0670	-0.0750	-0.0739
106	0.0427	0.0106	0.0508
107	-0.0546	-0.0669	-0.0476
108	-0.0829	-0.0888	-0.0831
109	-0.0848	-0.0534	-0.0481
110	0.0443	0.0320	-0.0097
111	0.0324	0.0482	0.1080
112	-0.0885	-0.0767	-0.0754
113	0.0511	0.0337	-0.0024
114	0.0748	0.0831	0.0854
115	0.1310	0.1707	0.1731
116	0.1098	0.1361	0.0777
117	-0.0162	0.0034	0.0281
118	-0.0773	-0.0854	-0.0745
119	0.0823	0.0021	-0.0740
120	0.0524	0.1067	0.1201
121	-0.0533	0.0784	0.0955
122	-0.0683	-0.0836	-0.0617
123	0.0172	0.0130	-0.0052
124	0.0571	0.0172	0.1062
125	-0.0465	-0.0663	-0.0763
126	-0.1172	-0.0675	-0.0660
127	0.1403	0.0522	0.0012

Identity — all 250 vector components

Dimension	Tiny	Base	Orange teacher
0	-0.0075	0.0484	0.0126
1	-0.1033	-0.0524	-0.0381
2	-0.0444	0.0105	-0.0485
3	0.0152	-0.0526	-0.0648
4	0.1123	0.0758	0.1460
5	-0.0341	-0.0361	-0.0412
6	0.0122	0.0629	0.0048
7	0.0693	0.1022	0.2075
8	0.0480	0.0388	0.0274
9	0.0363	0.0524	0.0920
10	-0.1084	-0.0332	-0.0414
11	-0.0645	-0.0148	-0.0277
12	-0.0436	-0.0306	0.0285
13	0.0525	0.1392	0.1567
14	-0.0441	-0.0172	-0.0293
15	0.1262	0.1187	0.1577
16	-0.0027	0.0161	-0.0637
17	0.0425	-0.0271	-0.0473
18	0.1486	0.1071	0.1893
19	-0.0933	-0.0830	-0.0625
20	0.0246	0.0674	0.0450
21	-0.0165	-0.0180	-0.0366
22	-0.0131	0.0226	0.0367
23	-0.0771	-0.0839	-0.0381
24	0.0293	-0.0091	-0.0337
25	0.0338	0.0515	-0.0044
26	-0.0012	0.0294	-0.0435
27	-0.0112	-0.0549	-0.0320
28	-0.0032	-0.0034	-0.0427
29	-0.0036	-0.0153	0.0829
30	0.0883	0.0180	0.0858
31	0.1586	0.1963	0.2118
32	0.1642	0.1749	0.0387
33	0.0550	0.0569	-0.0106
34	0.0609	0.1535	0.0357
35	0.0570	0.0259	0.0014
36	0.0603	0.0678	0.0999
37	-0.0871	-0.0439	-0.0272
38	-0.0860	-0.0897	-0.0547
39	-0.0413	-0.1098	-0.0587
40	0.0316	-0.0034	0.0023
41	0.0158	0.0058	0.0216
42	0.0108	0.0317	-0.0351
43	0.0628	0.0598	-0.0305
44	0.0715	0.0571	0.0096
45	-0.0681	0.0299	-0.0047
46	-0.1139	-0.1410	-0.0579
47	0.0288	-0.0166	-0.0516
48	0.0053	-0.0319	0.0270
49	-0.0003	0.0114	0.0816
50	0.0152	-0.0399	-0.0055
51	-0.0149	0.0448	-0.0082
52	0.0356	0.0224	-0.0383
53	-0.0229	-0.0727	-0.0381
54	0.0776	-0.0059	-0.0033
55	0.0888	0.0253	-0.0503
56	-0.0334	-0.0377	-0.0140
57	0.0503	0.0240	0.0641
58	-0.0654	0.0048	-0.0378
59	0.0209	0.1178	0.0303
60	0.0037	-0.0128	-0.0259
61	-0.0436	-0.0257	-0.0366
62	0.0175	-0.0758	-0.0346
63	0.0640	0.0674	0.1023
64	-0.0514	-0.0718	-0.0439
65	0.0256	-0.0070	0.0744
66	0.0916	0.1285	0.2050
67	-0.0888	-0.1579	-0.0414
68	0.0123	0.0406	-0.0424
69	0.0721	0.0901	0.0557
70	0.0483	0.0129	0.0704
71	-0.0125	-0.0381	-0.0413
72	0.0049	0.0642	0.0294
73	0.0687	0.0529	0.0214
74	-0.0910	-0.0883	-0.0425
75	0.1368	0.1276	0.1153
76	0.0972	0.1142	0.0947
77	-0.0575	-0.0110	-0.0125
78	0.0441	0.0366	-0.0013
79	-0.0363	-0.0736	-0.0422
80	-0.0004	0.0039	0.0397
81	-0.0005	0.0053	0.0032
82	-0.0270	-0.0651	-0.0378
83	-0.0216	-0.0021	-0.0350
84	0.0261	0.0709	0.0538
85	0.0595	0.0066	-0.0117
86	0.0438	0.0282	-0.0376
87	-0.0793	-0.0257	-0.0336
88	0.0832	0.0593	0.1775
89	0.0564	0.0136	0.1090
90	-0.0413	0.0011	-0.0417
91	0.0654	0.0531	0.1204
92	0.0263	0.0211	0.0379
93	0.0444	0.0560	-0.0042
94	-0.0026	-0.0446	-0.0681
95	0.1899	0.1651	0.1515
96	0.0348	0.0946	0.1537
97	0.0150	0.0629	0.1204
98	-0.0219	-0.0275	0.0429
99	-0.0667	0.0203	0.0056
100	0.1011	0.0569	0.0975
101	0.1050	0.0576	-0.0398
102	-0.0452	-0.1196	-0.0470
103	0.0207	0.0410	0.0071
104	-0.0338	-0.0781	-0.0548
105	-0.0178	-0.0321	-0.0046
106	-0.0511	-0.0404	-0.0324
107	-0.0044	0.0279	-0.0326
108	0.0208	0.0020	-0.0313
109	-0.1000	-0.0529	-0.0405
110	-0.0586	-0.0589	-0.0501
111	0.2212	0.1187	0.1652
112	-0.0318	0.0397	0.0487
113	-0.0667	-0.0892	-0.0717
114	-0.0832	-0.0732	-0.0587
115	-0.0169	-0.0393	-0.0298
116	0.1067	0.1187	0.0602
117	0.0320	-0.0544	0.0044
118	-0.0489	0.0497	0.0069
119	0.0355	0.0569	0.0266
120	-0.0143	-0.0074	-0.0536
121	0.0989	0.0763	0.0442
122	-0.0550	-0.0435	-0.0397
123	0.0129	0.0477	0.0324
124	0.0006	0.0607	0.0019
125	0.1279	0.0834	0.0461
126	0.0411	0.0892	0.0640
127	-0.0304	-0.0332	0.0164
128	-0.0514	-0.0709	-0.0524
129	-0.0228	-0.0482	-0.0446
130	-0.0286	0.0161	-0.0423
131	-0.0251	-0.0377	-0.0368
132	0.0402	0.0874	0.0973
133	-0.0135	0.0156	-0.0416
134	0.1033	0.0772	-0.0750
135	-0.0592	-0.0611	-0.0423
136	-0.0472	0.0168	-0.0451
137	-0.0187	-0.0176	0.0033
138	-0.0232	-0.0359	-0.0371
139	0.0148	-0.0417	-0.0430
140	-0.0214	-0.0598	-0.0325
141	0.0623	0.0393	0.0246
142	-0.0799	-0.0102	-0.0363
143	0.0397	0.0352	0.0399
144	-0.0352	-0.0213	-0.0145
145	-0.0581	-0.0388	-0.0535
146	0.1296	0.0857	0.0362
147	-0.0469	-0.0660	-0.0374
148	-0.0073	-0.0076	-0.0464
149	0.0737	0.1240	0.0504
150	-0.0108	0.0511	0.0044
151	0.0550	-0.0078	0.0545
152	-0.0163	-0.0504	-0.0467
153	-0.0129	0.0292	-0.0663
154	0.0592	-0.0114	-0.0193
155	0.0264	0.0638	0.0345
156	-0.0427	-0.0252	-0.0421
157	0.1223	0.0888	0.0271
158	0.0804	0.0321	0.0484
159	0.1357	0.1481	0.1832
160	-0.1045	0.0359	-0.0399
161	-0.0128	0.0339	-0.0253
162	-0.1430	-0.0799	-0.0488
163	0.0276	-0.0012	-0.0468
164	0.0411	-0.0139	-0.0370
165	0.0475	0.1026	0.1180
166	0.0205	-0.0491	-0.0490
167	0.0112	0.0143	-0.0505
168	-0.0279	-0.0249	-0.0331
169	0.0179	-0.0647	-0.0480
170	-0.0093	-0.0897	-0.0106
171	0.0726	0.0959	-0.0146
172	0.0195	0.0448	-0.0217
173	0.1162	0.0660	0.0756
174	-0.0295	0.0248	0.0421
175	-0.0290	-0.0433	-0.0697
176	-0.0441	-0.0763	-0.0358
177	0.0193	-0.0243	-0.0347
178	0.0486	0.0558	0.0030
179	0.0276	-0.0005	-0.0518
180	0.0662	0.1048	0.0522
181	-0.0480	-0.1285	-0.0600
182	-0.0656	-0.0301	-0.0315
183	-0.0614	-0.0558	-0.0848
184	0.0323	0.0153	-0.0427
185	-0.0072	0.0053	0.0440
186	-0.0408	-0.0462	-0.0507
187	0.0296	-0.0011	0.0907
188	-0.0270	0.0292	0.0316
189	0.0327	0.0141	0.0021
190	0.1078	0.0448	0.0012
191	-0.0097	0.0088	-0.0477
192	0.0290	0.0602	-0.0448
193	-0.0419	-0.0292	-0.0382
194	-0.0427	-0.0109	0.0006
195	-0.0827	-0.0326	-0.0399
196	-0.0107	-0.0047	0.0179
197	0.0018	0.0294	0.0336
198	-0.0707	-0.0576	-0.0406
199	-0.0274	-0.0480	-0.0462
200	-0.0422	-0.1004	-0.0486
201	0.0264	0.0388	0.0900
202	0.0089	0.0741	0.0306
203	-0.0229	-0.0785	-0.0525
204	0.0293	0.0138	0.0815
205	0.0765	0.0361	0.0627
206	0.1357	0.1330	0.0848
207	-0.0065	0.0020	0.0960
208	-0.0057	0.0262	-0.0436
209	-0.0303	-0.0424	-0.0297
210	-0.0138	-0.0377	-0.0547
211	-0.0539	0.0014	-0.0050
212	-0.0137	0.0326	0.0995
213	0.1609	0.1517	0.0740
214	0.0399	0.0216	0.0724
215	0.0709	0.0723	0.0922
216	0.2000	0.1776	0.1321
217	0.0363	0.0177	0.0741
218	-0.1257	-0.1374	-0.0488
219	-0.0289	0.0158	0.0088
220	-0.0910	-0.0941	-0.0464
221	-0.0021	-0.0359	-0.0365
222	-0.0209	-0.0328	-0.0425
223	-0.0267	0.0328	0.0563
224	0.0138	0.0258	0.1022
225	-0.0228	-0.0115	-0.0350
226	0.1061	0.0232	-0.0044
227	0.0447	-0.0292	0.1427
228	0.0032	0.0262	-0.0624
229	0.0514	-0.0158	0.0108
230	-0.0411	-0.0180	-0.0428
231	0.0256	0.0240	0.0126
232	0.0092	0.0526	0.0287
233	0.0589	0.0504	0.0609
234	0.0366	0.0262	-0.0326
235	0.0983	0.1098	0.0297
236	-0.0531	-0.0448	-0.0361
237	-0.0230	-0.0651	-0.0429
238	-0.0136	0.0021	0.0286
239	0.0267	0.0417	-0.0435
240	-0.0698	-0.0446	-0.0429
241	0.0760	-0.0162	0.0862
242	-0.0589	-0.0674	-0.0619
243	-0.0748	-0.0200	-0.0540
244	0.0492	0.0413	0.0299
245	-0.0007	0.0308	0.0620
246	-0.0399	0.0002	-0.0341
247	-0.0041	0.0117	-0.0354
248	-0.0978	-0.0616	-0.0481
249	0.0394	0.0625	-0.0203

Source: HUMANENESS_SMALL_VOICE_IDENTITY_R1_R2_2026-10-02_anime_000.html · SHA-256 f301c97c0aa149c3…

g10EnglishAnime voice study

anime_000 · en · 25/50

Generated TTS prediction · Rank 2 qv · 9.6 s

This long development points to serious damage in the reproductive system or maybe some infection setting in. (low mumble) We need to figure out what is causing this difficult situation right away.

Tiny Base · values are model estimates, not ground truth

Strongest emotions relative to training

Concentration

z +2.13 / +2.48raw 2.21 / 2.47

Fear

z +2.17 / +2.40raw 1.34 / 1.48

Doubt

z +2.10 / +1.60raw 0.99 / 0.75

Contemplation

z +1.75 / +1.37raw 1.13 / 0.90

Distress

z +1.17 / +1.11raw 0.96 / 0.91

Impatience and Irritability

z +1.05 / +1.14raw 0.89 / 0.95

Confusion

z +1.07 / +1.09raw 0.58 / 0.59

The center of each bar is the S9 teacher median. Positive z is to the right; negative z is to the left. Ranking uses z, not raw teacher units.

Strongest VoiceNet dimensions relative to training

Vocal register (REGS)

z +2.25 / +2.20raw 4.05 / 3.98

Narrator style (S_NARR)

z +1.83 / +2.01raw 3.95 / 4.21

Head resonance (R_HEAD)

z +1.74 / +1.75raw 3.58 / 3.59

Whispered talking style (S_WHIS)

z +1.70 / +1.72raw 4.35 / 4.38

Tempo (TEMP)

z +1.36 / +1.46raw 3.74 / 3.86

Esthetics (ESTH)

z +1.30 / +1.34raw 3.42 / 3.45

Storytelling style (S_STRY)

z +1.15 / +1.25raw 4.05 / 4.19

All 57 VoiceNet predictions, including raw units, are in the full table below. These seven are ranked by z; the top values may differ from the strongest raw dimensions.

Voice, speed and quality scores in context

Genuineness (0–6)z -0.71 / -0.76raw 1.18 / 1.09

Vocal-burst blend (0–10)z -0.78 / -0.74raw 4.54 / 4.65

Content enjoyment (CE)z +0.78 / +1.15raw 5.59 / 5.97

Production quality (PQ)z +0.18 / -0.00raw 7.20 / 7.04

Speech signal quality, calibratedz +0.16 / +0.25raw 3.57 / 3.61

Background quality, calibratedz +0.56 / +0.59raw 3.90 / 3.93

Overall quality, calibratedz +0.52 / +0.68raw 3.16 / 3.25

P.808 MOS estimatez +0.47 / +0.45raw 3.66 / 3.65

score content enjoymentz +0.58 / +0.30raw 4.68 / 4.60

score overall qualityz +0.39 / +0.36raw 2.85 / 2.83

Background Noisez -1.26 / -1.11raw 0.47 / 0.52

Tempo (TEMP)z +1.36 / +1.46raw 3.74 / 3.86

Arousal (AROU)z +0.23 / +0.06raw 2.62 / 2.43

Valence (VALN)z -0.22 / +0.04raw 2.08 / 2.37

Recording quality (RCQL)z +0.75 / +0.54raw 3.42 / 3.23

Background noise (BKGN)z +0.95 / +0.83raw 3.43 / 3.34

talking speedz +1.94 / +1.99raw 16.31 / 16.49

Characters per second (CPS): 20.62 raw · z +3.09

Orange speaker embedding reconstruction

Cosine against Orange on this same clip (higher means closer to that teacher vector):

Embedding	Tiny	Base
Timbre · 128D	0.905	0.914
Identity · 250D	0.673	0.712

Vocal-burst regions

Tiny

Base

0 s9.6 s

Verified burst intervals are unavailable for this clip.

Tiny: 1 regions, count-head estimate 1.19; Base: 1 regions, count-head estimate 1.08.

Exact predicted start and end times

Model	Region	Start (s)	End (s)	Duration (s)
Tiny	1	0.02	0.22	0.20
Base	1	0.02	0.22	0.20

All 192 score slots · raw and z values

#	Target	Tiny raw	Tiny z	Base raw	Base z	Train median	Train SD
Emotion scores Forty clip-level Empathic Insight emotion teacher outputs. Each row evaluates one named emotion score.
0	Affectionemo_Affection	0.049	+0.07	0.044	+0.06	0.007	0.570
1	Amusementemo_Amusement	-0.031	-0.03	-0.085	-0.10	-0.001	0.885
2	Angeremo_Anger	0.490	+0.79	0.438	+0.71	0.004	0.613
3	Astonishment Surpriseemo_Astonishment_Surprise	0.061	+0.10	0.045	+0.07	0.005	0.572
4	Aweemo_Awe	0.014	+0.03	0.012	+0.03	0.000	0.427
5	Bitternessemo_Bitterness	-0.016	-0.07	-0.005	-0.04	0.013	0.415
6	Concentrationemo_Concentration	2.212	+2.13	2.474	+2.48	0.634	0.741
7	Confusionemo_Confusion	0.579	+1.07	0.589	+1.09	0.001	0.540
8	Contemplationemo_Contemplation	1.131	+1.75	0.904	+1.37	0.082	0.598
9	Contemptemo_Contempt	0.010	+0.02	0.001	+0.00	-0.000	0.464
10	Contentmentemo_Contentment	-0.043	-0.08	-0.008	-0.02	0.000	0.514
11	Disappointmentemo_Disappointment	0.455	+0.65	0.445	+0.64	0.000	0.700
12	Disgustemo_Disgust	-0.020	-0.06	0.012	+0.01	0.007	0.489
13	Distressemo_Distress	0.963	+1.17	0.912	+1.11	0.000	0.821
14	Doubtemo_Doubt	0.986	+2.10	0.752	+1.60	0.006	0.466
15	Elationemo_Elation	-0.042	-0.07	-0.014	-0.04	0.012	0.728
16	Embarrassmentemo_Embarrassment	0.021	-0.05	-0.008	-0.12	0.043	0.430
17	Emotional Numbnessemo_Emotional_Numbness	0.386	+0.42	0.118	+0.12	0.004	0.917
18	Fatigue Exhaustionemo_Fatigue_Exhaustion	0.068	+0.07	0.022	-0.01	0.028	0.539
19	Fearemo_Fear	1.340	+2.17	1.478	+2.40	0.015	0.610
20	Helplessnessemo_Helplessness	0.676	+0.98	0.593	+0.86	-0.004	0.696
21	Hope Enthusiasm Optimismemo_Hope_Enthusiasm_Optimism	0.326	+0.27	0.213	+0.13	0.117	0.760
22	Impatience and Irritabilityemo_Impatience_and_Irritability	0.888	+1.05	0.950	+1.14	0.149	0.705
23	Infatuationemo_Infatuation	0.021	+0.07	-0.018	-0.01	-0.015	0.533
24	Interestemo_Interest	1.992	+0.44	2.199	+0.67	1.589	0.907
25	Intoxication Altered States of Consciousnessemo_Intoxication_Altered_States_of_Consciousness	-0.043	-0.03	-0.039	-0.03	-0.025	0.559
26	Jealousy and Envyemo_Jealousy_and_Envy	0.027	-0.07	0.035	-0.05	0.059	0.442
27	Longingemo_Longing	0.005	-0.13	-0.017	-0.16	0.087	0.632
28	Malevolence Maliceemo_Malevolence_Malice	0.062	+0.01	0.052	-0.01	0.055	0.534
29	Painemo_Pain	-0.001	+0.00	0.014	+0.03	-0.002	0.579
30	Pleasure Ecstasyemo_Pleasure_Ecstasy	0.008	-0.01	0.001	-0.03	0.017	0.614
31	Prideemo_Pride	-0.025	-0.05	0.032	+0.06	0.002	0.509
32	Reliefemo_Relief	0.070	+0.05	0.156	+0.18	0.033	0.681
33	Sadnessemo_Sadness	0.398	+0.52	0.441	+0.58	0.000	0.759
34	Sexual Lustemo_Sexual_Lust	-0.068	-0.20	-0.041	-0.14	0.030	0.494
35	Shameemo_Shame	0.022	+0.02	-0.015	-0.05	0.013	0.510
36	Sournessemo_Sourness	0.045	+0.12	-0.048	-0.10	-0.005	0.439
37	Teasingemo_Teasing	-0.028	-0.05	-0.018	-0.03	0.000	0.545
38	Thankfulness Gratitudeemo_Thankfulness_Gratitude	-0.005	-0.07	0.039	-0.00	0.041	0.697
39	Triumphemo_Triumph	-0.019	-0.02	-0.009	-0.00	-0.007	0.521
VoiceNet dimensions Fifty-seven VoiceNet voice, delivery, style, and recording dimensions. Codes are expanded in the target column.
40	Perceived voice age (AGEV)vn_AGEV_reg	2.873	-0.09	2.667	-0.26	2.984	1.238
41	Arousal (AROU)vn_AROU_reg	2.625	+0.23	2.434	+0.06	2.359	1.147
42	Arousal shift (ARSH)vn_ARSH_reg	2.403	-0.20	2.415	-0.19	2.580	0.867
43	Vocal attack (ATCK)vn_ATCK_reg	1.568	-0.46	1.630	-0.41	2.162	1.295
44	Background noise (BKGN)vn_BKGN_reg	3.429	+0.95	3.338	+0.83	2.703	0.761
45	Brightness (BRGT)vn_BRGT_reg	2.622	+0.78	2.429	+0.54	1.991	0.813
46	Speech chunking (CHNK)vn_CHNK_reg	3.075	+0.99	2.953	+0.89	1.847	1.239
47	Articulation clarity (CLRT)vn_CLRT_reg	3.148	+1.20	3.035	+1.08	2.018	0.945
48	Cognitive load (COGL)vn_COGL_reg	1.733	-0.34	1.482	-0.58	2.094	1.061
49	Dynamic arc (DARC)vn_DARC_reg	1.632	+0.01	1.563	-0.04	1.615	1.380
50	Disfluency (DFLU)vn_DFLU_reg	1.629	-0.73	1.343	-0.97	2.488	1.184
51	Emphasis (EMPH)vn_EMPH_reg	2.721	+0.07	2.779	+0.11	2.607	1.524
52	Esthetics (ESTH)vn_ESTH_reg	3.420	+1.30	3.450	+1.34	2.402	0.782
53	Content appropriateness (EXPL)vn_EXPL_reg	0.141	+0.17	0.183	+0.30	0.086	0.322
54	Focus (FOCS)vn_FOCS_reg	3.655	+1.19	3.620	+1.16	2.344	1.102
55	Fullness (FULL)vn_FULL_reg	2.000	+0.25	1.744	-0.04	1.778	0.889
56	Perceived gender (GEND)vn_GEND_reg	0.684	-2.12	0.373	-2.32	4.055	1.588
57	Harmonicity (HARM)vn_HARM_reg	1.637	-1.01	1.679	-0.96	2.480	0.836
58	Metallic character (METL)vn_METL_reg	1.463	-0.16	1.372	-0.26	1.621	0.958
59	Pitch range (RANG)vn_RANG_reg	3.522	+0.68	3.755	+0.94	2.914	0.897
60	Recording quality (RCQL)vn_RCQL_reg	3.423	+0.75	3.230	+0.54	2.754	0.888
61	Vocal register (REGS)vn_REGS_reg	4.053	+2.25	3.984	+2.20	1.198	1.268
62	Respiration (RESP)vn_RESP_reg	3.411	+0.69	3.145	+0.44	2.680	1.056
63	Roughness (ROUG)vn_ROUG_reg	1.210	-0.93	1.241	-0.89	2.033	0.887
64	Chest resonance (R_CHST)vn_R_CHST_reg	1.338	-0.94	1.229	-1.07	2.135	0.844
65	Head resonance (R_HEAD)vn_R_HEAD_reg	3.578	+1.74	3.591	+1.75	2.148	0.822
66	Mask resonance (R_MASK)vn_R_MASK_reg	2.786	+0.87	2.590	+0.68	1.908	1.005
67	Mixed resonance (R_MIXD)vn_R_MIXD_reg	1.808	+0.44	1.525	+0.11	1.436	0.841
68	Nasal resonance (R_NASL)vn_R_NASL_reg	3.980	+1.14	3.757	+0.92	2.791	1.047
69	Oral resonance (R_ORAL)vn_R_ORAL_reg	2.321	+0.19	2.117	-0.09	2.184	0.741
70	Throat resonance (R_THRT)vn_R_THRT_reg	2.232	+0.20	2.154	+0.10	2.070	0.803
71	Smoothness (SMTH)vn_SMTH_reg	2.966	+0.75	2.862	+0.66	2.143	1.093
72	Stance (STNC)vn_STNC_reg	2.278	-0.31	2.171	-0.41	2.633	1.137
73	Speech structure (STRU)vn_STRU_reg	3.108	+1.01	3.146	+1.05	2.137	0.958
74	ASMR style (S_ASMR)vn_S_ASMR_reg	2.621	+0.89	2.734	+0.97	1.370	1.411
75	Authoritative style (S_AUTH)vn_S_AUTH_reg	1.318	+0.22	1.227	+0.13	1.088	1.043
76	Cartoonish style (S_CART)vn_S_CART_reg	2.867	+0.93	2.776	+0.87	1.560	1.401
77	Casual style (S_CASU)vn_S_CASU_reg	3.496	-0.23	3.322	-0.37	3.793	1.278
78	Conversational style (S_CONV)vn_S_CONV_reg	3.492	+0.68	3.365	+0.58	2.594	1.318
79	Dramatic style (S_DRAM)vn_S_DRAM_reg	3.518	+0.69	3.638	+0.80	2.721	1.148
80	Formal style (S_FORM)vn_S_FORM_reg	2.203	+0.99	2.179	+0.96	1.195	1.021
81	Monologue style (S_MONO)vn_S_MONO_reg	3.079	+0.20	3.046	+0.17	2.824	1.284
82	Narrator style (S_NARR)vn_S_NARR_reg	3.953	+1.83	4.211	+2.01	1.307	1.446
83	Newsreader style (S_NEWS)vn_S_NEWS_reg	0.343	-0.11	0.360	-0.08	0.408	0.568
84	Playful style (S_PLAY)vn_S_PLAY_reg	3.010	+0.50	3.299	+0.72	2.352	1.315
85	Ranting or angry style (S_RANT)vn_S_RANT_reg	1.385	+0.13	1.013	-0.16	1.213	1.289
86	Storytelling style (S_STRY)vn_S_STRY_reg	4.051	+1.15	4.193	+1.25	2.480	1.366
87	Teacher or didactic style (S_TECH)vn_S_TECH_reg	1.180	+0.44	1.171	+0.43	0.646	1.227
88	Whispered talking style (S_WHIS)vn_S_WHIS_reg	4.352	+1.70	4.377	+1.72	1.597	1.618
89	Tempo (TEMP)vn_TEMP_reg	3.738	+1.36	3.860	+1.46	2.117	1.190
90	Tension (TENS)vn_TENS_reg	2.141	+0.68	1.921	+0.43	1.559	0.852
91	Valence (VALN)vn_VALN_reg	2.077	-0.22	2.369	+0.04	2.328	1.118
92	Valence shift (VALS)vn_VALS_reg	2.337	-0.17	2.321	-0.18	2.518	1.079
93	Velocity flux (VFLX)vn_VFLX_reg	2.726	+0.39	2.961	+0.58	2.256	1.208
94	Volatility (VOLT)vn_VOLT_reg	2.462	-0.14	2.602	+0.02	2.586	0.886
95	Vulnerability (VULN)vn_VULN_reg	2.921	+0.28	2.861	+0.22	2.648	0.984
96	Warmth (WARM)vn_WARM_reg	2.239	-0.37	2.271	-0.34	2.578	0.909
Genuineness, blend, and legacy quality Genuineness and vocal-burst blend are predicted. R_quality has Ladder training labels but no valid P3 test labels.
97	Genuineness (0–6)genuineness_0_6	1.181	-0.71	1.093	-0.76	2.332	1.621
98	Vocal-burst blend (0–10)blend_0_10	4.542	-0.78	4.648	-0.74	6.676	2.738
99	Legacy R_quality (no P3 test labels)R_quality	0.671	-1.26	0.661	-1.29	1.095	0.338
Empathic Insight Plus extra scores Nineteen additional clip-level teacher scores, including background noise and content enjoyment.
100	Ageeiv_extra:Age	3.238	-0.04	3.294	+0.15	3.250	0.293
101	Arousaleiv_extra:Arousal	1.490	+0.46	1.562	+0.63	1.289	0.435
102	Authenticityeiv_extra:Authenticity	2.946	+1.82	2.878	+1.38	2.667	0.153
103	Background Noiseeiv_extra:Background_Noise	0.474	-1.26	0.515	-1.11	0.808	0.264
104	Confident vs. Hesitanteiv_extra:Confident_vs._Hesitant	1.446	+1.34	1.367	+1.08	1.040	0.303
105	Gendereiv_extra:Gender	0.795	+1.42	0.666	+1.29	-0.621	0.999
106	High-Pitched vs. Low-Pitchedeiv_extra:High-Pitched_vs._Low-Pitched	1.747	-0.32	1.680	-0.59	1.827	0.250
107	Monotone vs. Expressiveeiv_extra:Monotone_vs._Expressive	1.886	+0.06	1.922	+0.13	1.859	0.470
108	Recording Qualityeiv_extra:Recording_Quality	2.588	+1.34	2.499	+1.07	2.144	0.332
109	Serious vs. Humorouseiv_extra:Serious_vs._Humorous	0.449	-1.41	0.609	-0.94	0.929	0.340
110	Soft vs. Harsheiv_extra:Soft_vs._Harsh	0.456	+0.55	0.469	+0.59	0.281	0.320
111	Submissive vs. Dominanteiv_extra:Submissive_vs._Dominant	0.344	-0.10	0.395	+0.06	0.376	0.324
112	Valenceeiv_extra:Valence	-0.185	-0.50	-0.163	-0.44	0.005	0.380
113	Vulnerable vs. Emotionally Detachedeiv_extra:Vulnerable_vs._Emotionally_Detached	1.844	+0.30	1.834	+0.27	1.715	0.437
114	Warm vs. Coldeiv_extra:Warm_vs._Cold	-0.141	-0.64	-0.017	-0.23	0.051	0.300
115	score background qualityeiv_extra:score_background_quality	3.502	+0.29	3.418	+0.17	3.301	0.693
116	score content enjoymenteiv_extra:score_content_enjoyment	4.684	+0.58	4.599	+0.30	4.507	0.303
117	score overall qualityeiv_extra:score_overall_quality	2.850	+0.39	2.832	+0.36	2.652	0.507
118	score speech qualityeiv_extra:score_speech_quality	1.877	+0.47	1.833	+0.18	1.808	0.146
Meta AudioBox Aesthetics Four AudioBox aesthetic teacher outputs. Expansions follow the official Meta model card.
119	Content enjoyment (CE)audiobox:CE	5.594	+0.78	5.967	+1.15	4.799	1.018
120	Content usefulness (CU)audiobox:CU	6.573	+0.92	6.721	+1.07	5.649	1.001
121	Production complexity (PC)audiobox:PC	1.454	-0.54	1.404	-0.57	2.331	1.617
122	Production quality (PQ)audiobox:PQ	7.201	+0.18	7.043	-0.00	7.044	0.879
Microsoft DNSMOS Seven DNSMOS teacher outputs: raw and calibrated SIG/BAK/OVRL estimates plus P.808 MOS.
123	Speech signal quality, rawdnsmos:SIG_raw	4.025	+0.19	4.118	+0.33	3.900	0.669
124	Background quality, rawdnsmos:BAK_raw	4.030	+0.73	4.065	+0.76	3.211	1.124
125	Overall quality, rawdnsmos:OVRL_raw	3.564	+0.59	3.726	+0.79	3.085	0.812
126	Speech signal quality, calibrateddnsmos:SIG	3.569	+0.16	3.614	+0.25	3.488	0.501
127	Background quality, calibrateddnsmos:BAK	3.905	+0.56	3.934	+0.59	3.389	0.928
128	Overall quality, calibrateddnsmos:OVRL	3.157	+0.52	3.252	+0.68	2.840	0.606
129	P.808 MOS estimatednsmos:P808_MOS	3.655	+0.47	3.645	+0.45	3.421	0.496
Vocal-burst count The regression target is log(1 + count). A separate table also reports count error after inverse transformation.
130	Vocal-burst count, log(1 + count)burst_count_log1p	0.784	+1.21	0.732	+1.13	0.000	0.647
VoiceCLAP attributes Sixty-one individual VoiceCLAP attribute teacher scores. The raw 768D VoiceCLAP embedding is stored in sidecars but is not a model output.
131	Affectionvoiceclap_attribute:Affection	0.956	+0.02	1.040	+0.17	0.947	0.554
132	Agevoiceclap_attribute:Age	2.684	-1.00	2.800	-0.79	3.229	0.547
133	Amusementvoiceclap_attribute:Amusement	0.274	-0.21	0.557	+0.29	0.392	0.572
134	Angervoiceclap_attribute:Anger	0.975	-0.03	0.765	-0.45	0.992	0.506
135	Arousalvoiceclap_attribute:Arousal	1.861	+0.71	1.759	+0.54	1.420	0.622
136	Astonishment Surprisevoiceclap_attribute:Astonishment_Surprise	0.954	+0.93	1.001	+1.03	0.509	0.479
137	Authenticityvoiceclap_attribute:Authenticity	3.304	+3.19	3.273	+3.01	2.770	0.167
138	Awevoiceclap_attribute:Awe	0.605	+0.25	0.747	+0.80	0.539	0.259
139	Background Noisevoiceclap_attribute:Background_Noise	0.241	-1.24	0.332	-0.89	0.567	0.264
140	Bitternessvoiceclap_attribute:Bitterness	0.411	-0.77	0.278	-1.33	0.592	0.236
141	Concentrationvoiceclap_attribute:Concentration	1.259	+0.08	1.246	+0.06	1.214	0.531
142	Confident vs. Hesitantvoiceclap_attribute:Confident_vs._Hesitant	1.498	+0.92	1.463	+0.84	1.069	0.468
143	Confusionvoiceclap_attribute:Confusion	0.977	+1.00	0.916	+0.82	0.643	0.334
144	Contemplationvoiceclap_attribute:Contemplation	0.831	+0.13	0.720	-0.15	0.780	0.406
145	Contemptvoiceclap_attribute:Contempt	0.578	-0.38	0.372	-0.99	0.709	0.339
146	Contentmentvoiceclap_attribute:Contentment	0.526	-0.20	0.641	+0.17	0.588	0.307
147	Disappointmentvoiceclap_attribute:Disappointment	1.036	+0.95	0.932	+0.59	0.760	0.291
148	Disgustvoiceclap_attribute:Disgust	0.641	+0.08	0.641	+0.08	0.625	0.207
149	Distressvoiceclap_attribute:Distress	1.163	+0.67	1.097	+0.49	0.927	0.350
150	Doubtvoiceclap_attribute:Doubt	0.686	+0.81	0.662	+0.68	0.535	0.188
151	Elationvoiceclap_attribute:Elation	0.375	-0.41	0.603	+0.16	0.539	0.397
152	Embarrassmentvoiceclap_attribute:Embarrassment	0.481	+0.55	0.506	+0.63	0.307	0.314
153	Emotional Numbnessvoiceclap_attribute:Emotional_Numbness	0.771	+0.40	0.637	-0.10	0.664	0.266
154	Fatigue Exhaustionvoiceclap_attribute:Fatigue_Exhaustion	0.389	-0.28	0.410	-0.20	0.462	0.261
155	Fearvoiceclap_attribute:Fear	0.860	+1.14	0.768	+0.71	0.618	0.212
156	Gendervoiceclap_attribute:Gender	1.246	+1.39	1.497	+1.64	-0.151	1.005
157	Helplessnessvoiceclap_attribute:Helplessness	0.902	+0.91	0.823	+0.62	0.658	0.268
158	High-Pitched vs. Low-Pitchedvoiceclap_attribute:High-Pitched_vs._Low-Pitched	1.545	-0.79	1.557	-0.76	1.840	0.375
159	Hope Enthusiasm Optimismvoiceclap_attribute:Hope_Enthusiasm_Optimism	1.014	+0.78	1.199	+1.25	0.705	0.396
160	Impatience and Irritabilityvoiceclap_attribute:Impatience_and_Irritability	1.218	+0.31	1.052	+0.00	1.052	0.541
161	Infatuationvoiceclap_attribute:Infatuation	0.704	+0.29	0.778	+0.51	0.608	0.332
162	Interestvoiceclap_attribute:Interest	1.815	+0.49	1.883	+0.65	1.598	0.440
163	Intoxication Altered States of Consciousnessvoiceclap_attribute:Intoxication_Altered_States_of_Consciousness	-0.023	-1.13	0.146	-0.77	0.502	0.463
164	Jealousy & Envyvoiceclap_attribute:Jealousy_&_Envy	0.940	+1.70	1.018	+2.02	0.523	0.245
165	Longingvoiceclap_attribute:Longing	0.793	+1.16	0.790	+1.15	0.538	0.220
166	Malevolence Malicevoiceclap_attribute:Malevolence_Malice	0.584	-0.72	0.553	-0.81	0.833	0.346
167	Monotone vs. Expressivevoiceclap_attribute:Monotone_vs._Expressive	2.185	+0.69	2.341	+0.95	1.775	0.594
168	Painvoiceclap_attribute:Pain	0.569	+0.86	0.468	+0.40	0.381	0.218
169	Pleasure Ecstasyvoiceclap_attribute:Pleasure_Ecstasy	0.493	-0.04	0.511	+0.03	0.503	0.301
170	Pridevoiceclap_attribute:Pride	0.569	-0.60	0.570	-0.60	0.780	0.349
171	Recording Qualityvoiceclap_attribute:Recording_Quality	2.851	+1.64	2.840	+1.61	2.313	0.328
172	Reliefvoiceclap_attribute:Relief	1.081	+0.14	1.052	+0.07	1.025	0.415
173	Sadnessvoiceclap_attribute:Sadness	0.996	+0.78	0.956	+0.65	0.752	0.313
174	Serious vs. Humorousvoiceclap_attribute:Serious_vs._Humorous	0.353	-0.79	0.786	-0.03	0.803	0.568
175	Sexual Lustvoiceclap_attribute:Sexual_Lust	0.315	-0.76	0.483	-0.36	0.635	0.419
176	Shamevoiceclap_attribute:Shame	1.030	+1.78	0.859	+1.17	0.526	0.283
177	Soft vs. Harshvoiceclap_attribute:Soft_vs._Harsh	0.666	+1.41	0.737	+1.60	0.160	0.360
178	Sournessvoiceclap_attribute:Sourness	0.837	+0.45	0.584	-0.42	0.706	0.291
179	Submissive vs. Dominantvoiceclap_attribute:Submissive_vs._Dominant	0.320	-0.85	0.253	-1.03	0.623	0.359
180	Teasingvoiceclap_attribute:Teasing	0.490	-0.13	0.521	-0.05	0.540	0.379
181	Thankfulness Gratitudevoiceclap_attribute:Thankfulness_Gratitude	1.575	+0.36	1.266	-0.22	1.384	0.529
182	Triumphvoiceclap_attribute:Triumph	0.353	-1.01	0.508	-0.58	0.716	0.359
183	Valencevoiceclap_attribute:Valence	-0.735	-1.15	-0.324	-0.50	-0.007	0.635
184	Vulnerable vs. Emotionally Detachedvoiceclap_attribute:Vulnerable_vs._Emotionally_Detached	1.445	-0.35	1.333	-0.55	1.638	0.556
185	Warm vs. Coldvoiceclap_attribute:Warm_vs._Cold	0.129	+0.49	0.467	+1.33	-0.066	0.400
186	durationvoiceclap_attribute:duration	9.273	-0.26	9.879	-0.16	10.914	6.354
187	score background qualityvoiceclap_attribute:score_background_quality	3.612	+0.74	3.493	+0.50	3.245	0.498
188	score content enjoymentvoiceclap_attribute:score_content_enjoyment	4.823	+1.13	4.843	+1.27	4.656	0.147
189	score overall qualityvoiceclap_attribute:score_overall_quality	2.837	+0.49	2.844	+0.50	2.635	0.412
190	score speech qualityvoiceclap_attribute:score_speech_quality	1.907	+0.23	1.901	+0.15	1.891	0.069
191	talking speedvoiceclap_attribute:talking_speed	16.312	+1.94	16.488	+1.99	9.028	3.756

All Orange embedding components

The cosine above is the meaningful vector-level comparison; component values have no standalone semantic label.

Timbre — all 128 vector components

Dimension	Tiny	Base	Orange teacher
0	-0.0085	-0.0250	-0.0510
1	0.1275	0.0641	0.0687
2	0.1100	0.1048	0.1268
3	-0.1078	-0.0927	-0.0837
4	-0.0733	-0.0660	-0.0776
5	-0.1484	-0.1262	-0.1044
6	0.1144	0.1039	0.0107
7	0.2139	0.2068	0.2114
8	-0.0204	-0.0256	-0.0155
9	0.0099	0.0251	0.0809
10	-0.0498	-0.0556	-0.0127
11	-0.0716	-0.1121	-0.0965
12	-0.0864	-0.0684	-0.0830
13	-0.0773	-0.0456	-0.0345
14	0.1467	0.1160	0.1226
15	0.0276	0.0240	0.0482
16	-0.0943	-0.1005	-0.1022
17	-0.0768	-0.0752	-0.0858
18	-0.0733	-0.0670	-0.0509
19	-0.0952	-0.0815	-0.0781
20	-0.0336	-0.0227	-0.0647
21	-0.0195	-0.0268	-0.0441
22	-0.0821	-0.0665	-0.0681
23	-0.1668	-0.1728	-0.0977
24	-0.0136	-0.0383	0.0092
25	-0.0616	-0.0762	-0.0725
26	-0.0535	-0.0587	-0.0622
27	-0.0502	-0.0323	-0.0770
28	-0.0873	-0.0927	-0.0909
29	0.1266	0.1359	0.1008
30	0.0373	0.0393	-0.0114
31	-0.0548	-0.0512	-0.0205
32	0.2157	0.1961	0.1807
33	-0.0156	-0.0095	-0.0603
34	-0.0637	-0.0743	-0.0740
35	0.1519	0.1932	0.1493
36	-0.0681	-0.0544	-0.0887
37	-0.0851	-0.0609	-0.0977
38	0.0877	0.0675	0.1287
39	-0.0960	-0.0913	-0.0833
40	0.0602	0.1233	0.0958
41	-0.0404	-0.0641	-0.0944
42	-0.0733	-0.0680	-0.0833
43	0.0284	0.0271	0.0038
44	0.0308	0.0245	0.0109
45	-0.0083	-0.0182	0.0247
46	0.1781	0.1660	0.0888
47	-0.0925	-0.0903	-0.0834
48	-0.0812	-0.0830	-0.0806
49	-0.0332	-0.0191	-0.0352
50	0.0443	0.0405	0.0141
51	0.0441	0.0599	0.0713
52	-0.0908	-0.0801	-0.0938
53	-0.0142	0.0081	-0.0687
54	-0.0882	-0.0854	-0.0923
55	-0.0227	-0.0342	-0.0059
56	-0.0738	-0.0869	-0.0783
57	-0.0535	-0.0825	-0.0842
58	0.0332	0.0352	0.0294
59	0.0681	0.1252	0.1281
60	0.1048	0.1000	0.0417
61	0.1545	0.1281	0.1769
62	0.0267	0.0631	0.0691
63	-0.0213	0.0210	-0.0030
64	0.0493	0.0379	0.0335
65	-0.0668	-0.0728	-0.0673
66	0.1283	0.0947	0.1437
67	-0.0659	-0.0815	-0.0796
68	0.0445	0.0599	0.0924
69	0.0234	-0.0223	0.0260
70	0.0310	0.0245	0.0199
71	0.2934	0.2971	0.1877
72	-0.0543	-0.1184	-0.0541
73	0.0426	0.0568	0.0141
74	-0.0150	0.0239	0.0571
75	0.2183	0.1718	0.1991
76	0.1292	0.1010	0.1379
77	-0.0698	-0.0874	-0.0754
78	-0.0738	-0.0699	-0.0734
79	-0.0764	-0.1039	-0.0716
80	-0.0378	-0.0347	0.0030
81	0.1589	0.1408	0.2004
82	-0.0712	-0.0561	-0.0790
83	0.1781	0.2116	0.2322
84	-0.1030	-0.0723	-0.0984
85	0.0330	0.1281	0.0779
86	-0.0423	-0.1005	-0.0255
87	-0.1056	-0.1126	-0.0953
88	-0.0224	0.0001	0.0363
89	-0.0421	-0.0485	-0.0502
90	0.0607	0.0680	-0.0039
91	0.0122	0.0084	0.0443
92	-0.0310	-0.0374	-0.0112
93	-0.0515	-0.0517	-0.0699
94	-0.0308	-0.0371	0.0087
95	-0.0404	-0.0757	-0.0887
96	-0.0768	-0.0767	-0.0212
97	0.1318	0.1262	0.2073
98	-0.0720	-0.0515	-0.0420
99	0.0821	0.0616	0.0712
100	0.1572	0.1573	0.1707
101	-0.0223	-0.0002	-0.0798
102	-0.0032	0.0556	0.0797
103	-0.1096	-0.1199	-0.0871
104	0.0312	0.0222	0.0431
105	-0.0851	-0.0864	-0.0796
106	0.0308	0.0512	0.0764
107	-0.0576	-0.0811	-0.0769
108	-0.0864	-0.0976	-0.0895
109	-0.0576	-0.0830	-0.0630
110	0.0299	-0.0054	-0.0244
111	0.0327	0.0033	0.0377
112	-0.0742	-0.0811	-0.0814
113	-0.0231	-0.0313	-0.0402
114	0.1030	0.0595	0.0161
115	0.1327	0.1388	0.1740
116	0.0956	0.0757	0.1097
117	-0.0244	0.0056	0.0373
118	-0.0825	-0.0859	-0.0804
119	0.0589	0.0502	-0.0629
120	0.0522	0.0830	0.0965
121	0.0025	0.0398	0.0940
122	-0.0148	0.0220	-0.0032
123	0.0094	-0.0299	-0.0024
124	0.0493	0.0252	0.0444
125	-0.0939	-0.0284	-0.0823
126	-0.1070	-0.0937	-0.0712
127	0.1118	0.0951	0.0695

Identity — all 250 vector components

Dimension	Tiny	Base	Orange teacher
0	0.0320	0.0814	-0.0303
1	-0.0422	-0.0273	-0.0363
2	-0.0655	0.0134	-0.0461
3	-0.0246	-0.0368	-0.0490
4	0.0615	0.0929	0.1310
5	0.0318	0.0087	-0.0392
6	0.0583	0.0900	0.0266
7	0.0838	0.1449	0.2192
8	0.0444	-0.0149	0.0133
9	0.0369	0.0493	0.0682
10	-0.0633	-0.0028	-0.0394
11	-0.0807	-0.0105	-0.0358
12	0.0451	-0.0302	0.0671
13	0.1330	0.1535	0.1812
14	-0.0479	-0.0330	-0.0326
15	0.1481	0.1160	0.1469
16	0.0728	0.0345	0.0247
17	0.0065	0.0232	-0.0325
18	0.1235	0.0730	0.1375
19	-0.1065	-0.0592	-0.0595
20	0.0164	0.0247	0.0461
21	-0.0113	-0.0228	-0.0348
22	0.0403	0.0496	0.1013
23	-0.0586	-0.0756	-0.0363
24	-0.0150	-0.0036	-0.0320
25	-0.0058	0.0164	-0.0440
26	-0.0060	0.0105	-0.0414
27	-0.0304	-0.0089	-0.0305
28	-0.0117	0.0128	-0.0406
29	-0.0249	-0.0020	0.1152
30	0.0435	0.0297	0.1844
31	0.1487	0.1547	0.1786
32	0.1273	0.0756	0.0751
33	0.0254	0.0672	0.0415
34	0.1595	0.1581	0.0498
35	0.0298	0.0791	0.0569
36	0.0753	0.0900	0.0481
37	-0.0914	-0.0459	-0.0259
38	-0.0570	-0.0713	-0.0521
39	-0.0592	-0.0912	-0.0559
40	0.0056	-0.0181	-0.0204
41	0.0149	0.0332	0.0125
42	-0.0131	0.0008	-0.0177
43	0.0176	0.0384	0.0253
44	0.0139	0.0993	0.0548
45	-0.0826	-0.0479	-0.0282
46	-0.1090	-0.0941	-0.0551
47	-0.0608	-0.0785	-0.0174
48	0.0266	-0.0235	0.0252
49	-0.0083	0.0247	0.0869
50	-0.0087	0.0095	0.0249
51	-0.0066	0.0413	0.0394
52	0.0580	0.0491	0.0027
53	-0.0655	-0.0511	-0.0363
54	0.0047	0.0281	0.0280
55	0.0171	0.0001	-0.0103
56	0.0144	-0.0430	-0.0203
57	0.0772	0.0511	0.0499
58	-0.0378	0.0088	-0.0290
59	0.0113	0.0296	0.0221
60	0.0129	-0.0024	-0.0200
61	-0.0908	-0.0390	-0.0349
62	-0.0084	-0.0410	-0.0330
63	0.0690	0.0987	0.1071
64	-0.0457	-0.0724	-0.0418
65	0.0983	0.0424	0.0696
66	0.1513	0.1206	0.1475
67	-0.1223	-0.1685	-0.0395
68	0.0235	-0.0162	-0.0282
69	0.1128	0.0802	0.0057
70	0.0457	0.0534	0.0953
71	-0.0084	-0.0130	-0.0337
72	0.0285	0.0024	-0.0416
73	0.0863	0.0796	0.0165
74	-0.0901	-0.0871	-0.0405
75	0.1317	0.0918	0.1119
76	0.1134	0.1327	0.0521
77	-0.0605	0.0278	0.0492
78	0.0348	-0.0073	-0.0090
79	-0.0291	-0.0439	-0.0402
80	0.0116	0.0159	0.1488
81	0.0126	0.0866	0.0787
82	-0.0432	-0.0785	-0.0360
83	-0.0416	-0.0147	-0.0333
84	0.0284	0.0129	-0.0030
85	0.0059	0.0126	-0.0376
86	-0.0109	-0.0065	-0.0358
87	-0.0615	-0.0395	-0.0320
88	0.1097	0.0626	0.1161
89	0.0392	0.0051	0.1053
90	0.0043	0.0189	-0.0017
91	0.0476	-0.0043	0.0503
92	0.0466	0.0320	0.0122
93	0.0476	0.0667	0.0652
94	-0.0055	0.0131	-0.0493
95	0.2219	0.1766	0.1650
96	0.0624	0.1096	0.1506
97	-0.0208	0.0416	0.1021
98	-0.0425	0.0291	0.0914
99	-0.0151	0.0151	0.0391
100	0.0759	0.0108	0.0381
101	0.0057	-0.0004	-0.0108
102	-0.1097	-0.1143	-0.0448
103	0.0429	-0.0096	-0.0379
104	-0.0495	-0.0848	-0.0522
105	-0.0266	-0.0310	0.0124
106	-0.0432	-0.0039	-0.0024
107	-0.0266	-0.0229	0.0509
108	-0.0369	-0.0074	-0.0298
109	-0.0413	0.0180	-0.0385
110	-0.0488	-0.0531	-0.0179
111	0.1437	0.1247	0.1610
112	-0.0067	-0.0106	0.0334
113	-0.1204	-0.1581	-0.0683
114	-0.0681	-0.0730	-0.0559
115	-0.0071	-0.0326	-0.0118
116	-0.0114	0.0268	0.0204
117	0.0199	-0.0107	0.0527
118	0.0107	0.0488	0.0922
119	0.0577	0.0866	0.1028
120	0.0043	0.0597	-0.0343
121	0.0725	0.0034	0.0380
122	-0.0239	-0.0134	0.0296
123	0.0230	0.0421	0.1013
124	-0.0026	-0.0030	-0.0217
125	0.1639	0.1045	0.0720
126	0.0703	0.0351	0.0605
127	-0.0383	-0.0450	0.0615
128	-0.0731	-0.0964	-0.0499
129	-0.0529	-0.0545	-0.0425
130	0.0832	0.0531	-0.0122
131	-0.0696	-0.0338	-0.0351
132	0.0574	0.0105	0.0780
133	0.0235	0.0540	-0.0318
134	0.0293	0.0658	-0.0384
135	-0.0838	-0.0652	-0.0403
136	-0.0725	-0.0465	-0.0429
137	0.0372	0.0300	0.0735
138	-0.0362	-0.0092	-0.0353
139	0.0030	-0.0070	-0.0410
140	-0.0586	0.0009	0.0119
141	0.0668	0.0508	0.0808
142	-0.0373	-0.0146	-0.0346
143	0.0473	0.0113	0.0219
144	-0.0102	0.0017	-0.0244
145	-0.0599	-0.0525	-0.0509
146	0.0526	0.0413	0.0421
147	-0.0649	-0.0580	-0.0356
148	-0.0148	0.0159	-0.0442
149	0.1210	0.1558	0.0748
150	0.0326	0.0848	0.0393
151	-0.0128	0.0441	0.0712
152	-0.0596	-0.0118	-0.0190
153	0.0288	0.0231	-0.0168
154	-0.0282	0.0105	0.0187
155	0.0696	0.0652	0.0488
156	-0.0542	-0.0505	-0.0401
157	0.1613	0.1743	0.0739
158	0.0296	-0.0294	-0.0245
159	0.1084	0.1154	0.1732
160	-0.0517	-0.0175	-0.0197
161	0.0429	0.0545	0.0176
162	-0.0684	-0.0326	-0.0465
163	-0.0019	0.0302	-0.0278
164	0.0006	-0.0303	-0.0352
165	0.0551	0.0929	0.0839
166	-0.0124	0.0291	-0.0212
167	0.0109	0.0134	0.0069
168	-0.0217	-0.0000	-0.0145
169	0.0435	0.0004	0.0114
170	-0.0558	-0.0929	0.0390
171	0.0284	-0.0103	-0.0352
172	-0.0050	0.0356	0.0217
173	0.0561	0.0825	0.0454
174	0.0150	0.0232	0.0574
175	-0.0403	-0.0343	-0.0663
176	-0.0258	-0.0525	-0.0341
177	-0.0197	-0.0355	-0.0330
178	0.1292	0.1420	0.1076
179	0.0118	-0.0015	-0.0493
180	0.0090	0.0975	0.0743
181	-0.0422	-0.0554	-0.0571
182	-0.0162	-0.0198	0.0373
183	-0.0882	-0.0768	-0.0792
184	0.0719	0.0531	-0.0407
185	0.0269	0.0118	0.0737
186	-0.0605	-0.0548	-0.0432
187	0.0069	0.0467	0.1021
188	0.0039	0.0733	0.0590
189	0.0216	0.0941	0.0515
190	0.0419	0.0276	-0.0039
191	0.0143	0.0170	-0.0002
192	0.0747	0.0773	-0.0485
193	-0.0438	0.0030	-0.0060
194	-0.0298	-0.0061	0.0011
195	-0.0520	0.0276	-0.0381
196	-0.0153	0.0136	-0.0072
197	0.0147	0.0785	0.0621
198	-0.0785	-0.0427	-0.0387
199	-0.1128	-0.0900	-0.0299
200	-0.0277	-0.0672	-0.0463
201	0.0596	0.0698	0.1054
202	0.0170	0.0710	0.0005
203	0.0107	-0.0450	-0.0500
204	0.0492	0.0958	0.1074
205	0.0046	0.0252	-0.0144
206	0.1109	0.1449	0.0600
207	-0.0071	0.0352	0.1318
208	0.0060	-0.0198	-0.0415
209	-0.0753	-0.0528	0.0170
210	-0.0416	-0.0756	-0.0521
211	-0.0040	0.0261	0.0120
212	-0.0014	-0.0310	0.0721
213	0.1626	0.1368	0.0809
214	0.0062	0.0540	0.0716
215	0.0819	0.0577	0.0901
216	0.1538	0.1322	0.0778
217	0.0977	0.0964	0.0524
218	-0.1128	-0.0854	-0.0465
219	0.0041	0.0300	0.0331
220	-0.0845	-0.0531	-0.0442
221	-0.0728	-0.0819	-0.0348
222	-0.0520	-0.0398	0.0144
223	-0.0064	0.0485	0.0803
224	0.0326	0.0563	0.1141
225	-0.0851	-0.0365	-0.0321
226	0.0257	0.0362	0.0235
227	0.0555	-0.0024	0.1272
228	-0.0388	0.0303	-0.0232
229	0.0826	0.1068	0.0566
230	-0.0087	-0.0121	-0.0007
231	0.0285	0.0450	0.0645
232	0.0375	0.0365	0.0125
233	0.0832	0.0860	0.0581
234	0.0863	0.1114	0.0605
235	0.0908	0.0952	0.0058
236	-0.0511	-0.0364	-0.0191
237	-0.0353	-0.0248	-0.0409
238	-0.0126	0.0381	0.0198
239	-0.0043	-0.0001	-0.0414
240	-0.0596	-0.0534	-0.0408
241	0.0247	-0.0369	0.0545
242	-0.0671	-0.0756	-0.0590
243	-0.0174	-0.0084	-0.0500
244	0.0485	0.0802	0.1055
245	0.0065	-0.0467	0.0249
246	-0.0028	0.0089	0.0438
247	-0.0056	-0.0378	-0.0337
248	-0.1298	-0.0929	-0.0458
249	-0.0098	0.0185	-0.0597

Source: HUMANENESS_SMALL_VOICE_IDENTITY_R1_R2_2026-10-02_anime_000.html · SHA-256 b0c1ea42224790d9…

g11GermanAnime voice study

anime_000 · de · 32/50

Generated TTS prediction · Rank 2 qkvo · 11.3 s

Wir müssen aufhören, das für diese ganze Generation neuer Leute wie ein reines Glücksspiel zu sehen. Es ist absolut entscheidend, dass wir diese Wahrnehmung jetzt ändern.

Tiny Base · values are model estimates, not ground truth

Strongest emotions relative to training

Hope Enthusiasm Optimism

z +3.31 / +3.10raw 2.64 / 2.47

Contentment

z +1.95 / +1.74raw 1.00 / 0.89

Elation

z +1.85 / +1.56raw 1.36 / 1.15

Pleasure Ecstasy

z +1.54 / +1.33raw 0.96 / 0.83

Concentration

z +1.18 / +1.51raw 1.51 / 1.76

Relief

z +1.17 / +1.41raw 0.83 / 0.99

Contemplation

z +1.36 / +1.40raw 0.90 / 0.92

The center of each bar is the S9 teacher median. Positive z is to the right; negative z is to the left. Ranking uses z, not raw teacher units.

Strongest VoiceNet dimensions relative to training

Narrator style (S_NARR)

z +1.84 / +2.30raw 3.96 / 4.64

Vocal register (REGS)

z +1.65 / +1.69raw 3.30 / 3.35

ASMR style (S_ASMR)

z +1.18 / +1.52raw 3.04 / 3.52

Whispered talking style (S_WHIS)

z +1.15 / +1.40raw 3.45 / 3.87

Monologue style (S_MONO)

z +1.25 / +1.39raw 4.43 / 4.61

Storytelling style (S_STRY)

z +0.97 / +1.29raw 3.81 / 4.25

Respiration (RESP)

z +1.13 / +1.19raw 3.87 / 3.93

All 57 VoiceNet predictions, including raw units, are in the full table below. These seven are ranked by z; the top values may differ from the strongest raw dimensions.

Voice, speed and quality scores in context

Genuineness (0–6)z -0.40 / -0.48raw 1.68 / 1.55

Vocal-burst blend (0–10)z -0.73 / -0.92raw 4.69 / 4.15

Content enjoyment (CE)z +0.98 / +1.18raw 5.80 / 6.00

Production quality (PQ)z +0.41 / +0.41raw 7.40 / 7.41

Speech signal quality, calibratedz +0.08 / +0.13raw 3.53 / 3.55

Background quality, calibratedz +0.33 / +0.51raw 3.69 / 3.86

Overall quality, calibratedz +0.40 / +0.55raw 3.08 / 3.17

P.808 MOS estimatez +0.55 / +0.11raw 3.69 / 3.48

score content enjoymentz +0.91 / +0.57raw 4.78 / 4.68

score overall qualityz +0.51 / +0.51raw 2.91 / 2.91

Background Noisez -0.87 / -0.44raw 0.58 / 0.69

Tempo (TEMP)z -0.09 / -0.20raw 2.01 / 1.88

Arousal (AROU)z -0.99 / -1.11raw 1.22 / 1.08

Valence (VALN)z -0.87 / -1.10raw 1.36 / 1.10

Recording quality (RCQL)z +0.72 / +0.91raw 3.39 / 3.56

Background noise (BKGN)z +0.57 / +0.58raw 3.14 / 3.14

talking speedz +0.47 / +0.64raw 10.80 / 11.45

Characters per second (CPS): 15.04 raw · z +1.60

Orange speaker embedding reconstruction

Cosine against Orange on this same clip (higher means closer to that teacher vector):

Embedding	Tiny	Base
Timbre · 128D	0.790	0.846
Identity · 250D	0.680	0.741

Vocal-burst regions

Tiny

Base

0 s11.3 s

Verified burst intervals are unavailable for this clip.

Tiny: 0 regions, count-head estimate 0.02; Base: 0 regions, count-head estimate 0.01.

Exact predicted start and end times

Model	Region	Start (s)	End (s)	Duration (s)

All 192 score slots · raw and z values

#	Target	Tiny raw	Tiny z	Base raw	Base z	Train median	Train SD
Emotion scores Forty clip-level Empathic Insight emotion teacher outputs. Each row evaluates one named emotion score.
0	Affectionemo_Affection	0.520	+0.90	0.798	+1.39	0.007	0.570
1	Amusementemo_Amusement	0.200	+0.23	0.088	+0.10	-0.001	0.885
2	Angeremo_Anger	0.110	+0.17	0.176	+0.28	0.004	0.613
3	Astonishment Surpriseemo_Astonishment_Surprise	0.198	+0.34	0.081	+0.13	0.005	0.572
4	Aweemo_Awe	0.249	+0.58	0.043	+0.10	0.000	0.427
5	Bitternessemo_Bitterness	0.018	+0.01	-0.003	-0.04	0.013	0.415
6	Concentrationemo_Concentration	1.510	+1.18	1.755	+1.51	0.634	0.741
7	Confusionemo_Confusion	0.034	+0.06	0.009	+0.02	0.001	0.540
8	Contemplationemo_Contemplation	0.897	+1.36	0.920	+1.40	0.082	0.598
9	Contemptemo_Contempt	-0.064	-0.14	-0.034	-0.07	-0.000	0.464
10	Contentmentemo_Contentment	1.004	+1.95	0.893	+1.74	0.000	0.514
11	Disappointmentemo_Disappointment	0.299	+0.43	0.536	+0.77	0.000	0.700
12	Disgustemo_Disgust	0.027	+0.04	0.011	+0.01	0.007	0.489
13	Distressemo_Distress	0.304	+0.37	0.550	+0.67	0.000	0.821
14	Doubtemo_Doubt	0.040	+0.07	0.046	+0.09	0.006	0.466
15	Elationemo_Elation	1.361	+1.85	1.151	+1.56	0.012	0.728
16	Embarrassmentemo_Embarrassment	-0.037	-0.19	-0.017	-0.14	0.043	0.430
17	Emotional Numbnessemo_Emotional_Numbness	0.098	+0.10	0.126	+0.13	0.004	0.917
18	Fatigue Exhaustionemo_Fatigue_Exhaustion	-0.011	-0.07	0.024	-0.01	0.028	0.539
19	Fearemo_Fear	0.345	+0.54	0.637	+1.02	0.015	0.610
20	Helplessnessemo_Helplessness	0.107	+0.16	0.322	+0.47	-0.004	0.696
21	Hope Enthusiasm Optimismemo_Hope_Enthusiasm_Optimism	2.637	+3.31	2.471	+3.10	0.117	0.760
22	Impatience and Irritabilityemo_Impatience_and_Irritability	0.175	+0.04	0.335	+0.26	0.149	0.705
23	Infatuationemo_Infatuation	0.008	+0.04	0.027	+0.08	-0.015	0.533
24	Interestemo_Interest	2.585	+1.10	2.413	+0.91	1.589	0.907
25	Intoxication Altered States of Consciousnessemo_Intoxication_Altered_States_of_Consciousness	0.013	+0.07	-0.015	+0.02	-0.025	0.559
26	Jealousy and Envyemo_Jealousy_and_Envy	0.110	+0.12	0.072	+0.03	0.059	0.442
27	Longingemo_Longing	0.390	+0.48	0.557	+0.74	0.087	0.632
28	Malevolence Maliceemo_Malevolence_Malice	0.071	+0.03	0.067	+0.02	0.055	0.534
29	Painemo_Pain	0.013	+0.03	-0.000	+0.00	-0.002	0.579
30	Pleasure Ecstasyemo_Pleasure_Ecstasy	0.962	+1.54	0.831	+1.33	0.017	0.614
31	Prideemo_Pride	0.389	+0.76	0.387	+0.76	0.002	0.509
32	Reliefemo_Relief	0.828	+1.17	0.992	+1.41	0.033	0.681
33	Sadnessemo_Sadness	0.499	+0.66	0.859	+1.13	0.000	0.759
34	Sexual Lustemo_Sexual_Lust	0.021	-0.02	0.056	+0.05	0.030	0.494
35	Shameemo_Shame	-0.001	-0.03	0.002	-0.02	0.013	0.510
36	Sournessemo_Sourness	0.032	+0.08	-0.023	-0.04	-0.005	0.439
37	Teasingemo_Teasing	-0.035	-0.06	-0.070	-0.13	0.000	0.545
38	Thankfulness Gratitudeemo_Thankfulness_Gratitude	0.359	+0.46	0.543	+0.72	0.041	0.697
39	Triumphemo_Triumph	0.529	+1.03	0.513	+1.00	-0.007	0.521
VoiceNet dimensions Fifty-seven VoiceNet voice, delivery, style, and recording dimensions. Codes are expanded in the target column.
40	Perceived voice age (AGEV)vn_AGEV_reg	3.814	+0.67	4.040	+0.85	2.984	1.238
41	Arousal (AROU)vn_AROU_reg	1.222	-0.99	1.081	-1.11	2.359	1.147
42	Arousal shift (ARSH)vn_ARSH_reg	1.136	-1.66	1.068	-1.74	2.580	0.867
43	Vocal attack (ATCK)vn_ATCK_reg	0.941	-0.94	0.679	-1.15	2.162	1.295
44	Background noise (BKGN)vn_BKGN_reg	3.137	+0.57	3.142	+0.58	2.703	0.761
45	Brightness (BRGT)vn_BRGT_reg	1.865	-0.15	1.725	-0.33	1.991	0.813
46	Speech chunking (CHNK)vn_CHNK_reg	1.843	-0.00	1.921	+0.06	1.847	1.239
47	Articulation clarity (CLRT)vn_CLRT_reg	2.155	+0.15	2.039	+0.02	2.018	0.945
48	Cognitive load (COGL)vn_COGL_reg	3.104	+0.95	2.890	+0.75	2.094	1.061
49	Dynamic arc (DARC)vn_DARC_reg	0.336	-0.93	0.187	-1.04	1.615	1.380
50	Disfluency (DFLU)vn_DFLU_reg	1.779	-0.60	1.583	-0.76	2.488	1.184
51	Emphasis (EMPH)vn_EMPH_reg	2.831	+0.15	2.865	+0.17	2.607	1.524
52	Esthetics (ESTH)vn_ESTH_reg	3.116	+0.91	3.238	+1.07	2.402	0.782
53	Content appropriateness (EXPL)vn_EXPL_reg	0.109	+0.07	0.170	+0.26	0.086	0.322
54	Focus (FOCS)vn_FOCS_reg	2.287	-0.05	2.504	+0.15	2.344	1.102
55	Fullness (FULL)vn_FULL_reg	2.262	+0.54	2.105	+0.37	1.778	0.889
56	Perceived gender (GEND)vn_GEND_reg	1.119	-1.85	1.020	-1.91	4.055	1.588
57	Harmonicity (HARM)vn_HARM_reg	1.185	-1.55	1.165	-1.57	2.480	0.836
58	Metallic character (METL)vn_METL_reg	0.210	-1.47	0.016	-1.68	1.621	0.958
59	Pitch range (RANG)vn_RANG_reg	3.295	+0.43	3.344	+0.48	2.914	0.897
60	Recording quality (RCQL)vn_RCQL_reg	3.392	+0.72	3.560	+0.91	2.754	0.888
61	Vocal register (REGS)vn_REGS_reg	3.297	+1.65	3.346	+1.69	1.198	1.268
62	Respiration (RESP)vn_RESP_reg	3.874	+1.13	3.933	+1.19	2.680	1.056
63	Roughness (ROUG)vn_ROUG_reg	1.575	-0.52	1.468	-0.64	2.033	0.887
64	Chest resonance (R_CHST)vn_R_CHST_reg	1.298	-0.99	1.146	-1.17	2.135	0.844
65	Head resonance (R_HEAD)vn_R_HEAD_reg	2.162	+0.02	2.277	+0.16	2.148	0.822
66	Mask resonance (R_MASK)vn_R_MASK_reg	1.891	-0.02	1.730	-0.18	1.908	1.005
67	Mixed resonance (R_MIXD)vn_R_MIXD_reg	1.180	-0.30	1.036	-0.47	1.436	0.841
68	Nasal resonance (R_NASL)vn_R_NASL_reg	2.049	-0.71	2.000	-0.76	2.791	1.047
69	Oral resonance (R_ORAL)vn_R_ORAL_reg	1.687	-0.67	1.484	-0.94	2.184	0.741
70	Throat resonance (R_THRT)vn_R_THRT_reg	1.398	-0.84	1.389	-0.85	2.070	0.803
71	Smoothness (SMTH)vn_SMTH_reg	2.519	+0.34	2.801	+0.60	2.143	1.093
72	Stance (STNC)vn_STNC_reg	1.466	-1.03	1.627	-0.88	2.633	1.137
73	Speech structure (STRU)vn_STRU_reg	2.141	+0.00	2.197	+0.06	2.137	0.958
74	ASMR style (S_ASMR)vn_S_ASMR_reg	3.041	+1.18	3.515	+1.52	1.370	1.411
75	Authoritative style (S_AUTH)vn_S_AUTH_reg	0.897	-0.18	0.891	-0.19	1.088	1.043
76	Cartoonish style (S_CART)vn_S_CART_reg	1.326	-0.17	1.337	-0.16	1.560	1.401
77	Casual style (S_CASU)vn_S_CASU_reg	3.506	-0.22	3.314	-0.37	3.793	1.278
78	Conversational style (S_CONV)vn_S_CONV_reg	1.891	-0.53	1.779	-0.62	2.594	1.318
79	Dramatic style (S_DRAM)vn_S_DRAM_reg	3.389	+0.58	3.620	+0.78	2.721	1.148
80	Formal style (S_FORM)vn_S_FORM_reg	2.010	+0.80	1.927	+0.72	1.195	1.021
81	Monologue style (S_MONO)vn_S_MONO_reg	4.425	+1.25	4.614	+1.39	2.824	1.284
82	Narrator style (S_NARR)vn_S_NARR_reg	3.964	+1.84	4.637	+2.30	1.307	1.446
83	Newsreader style (S_NEWS)vn_S_NEWS_reg	0.453	+0.08	0.568	+0.28	0.408	0.568
84	Playful style (S_PLAY)vn_S_PLAY_reg	1.872	-0.36	1.613	-0.56	2.352	1.315
85	Ranting or angry style (S_RANT)vn_S_RANT_reg	1.611	+0.31	1.571	+0.28	1.213	1.289
86	Storytelling style (S_STRY)vn_S_STRY_reg	3.812	+0.97	4.247	+1.29	2.480	1.366
87	Teacher or didactic style (S_TECH)vn_S_TECH_reg	0.825	+0.15	0.749	+0.08	0.646	1.227
88	Whispered talking style (S_WHIS)vn_S_WHIS_reg	3.453	+1.15	3.865	+1.40	1.597	1.618
89	Tempo (TEMP)vn_TEMP_reg	2.013	-0.09	1.876	-0.20	2.117	1.190
90	Tension (TENS)vn_TENS_reg	1.221	-0.40	1.016	-0.64	1.559	0.852
91	Valence (VALN)vn_VALN_reg	1.356	-0.87	1.096	-1.10	2.328	1.118
92	Valence shift (VALS)vn_VALS_reg	1.528	-0.92	1.575	-0.87	2.518	1.079
93	Velocity flux (VFLX)vn_VFLX_reg	1.189	-0.88	1.137	-0.93	2.256	1.208
94	Volatility (VOLT)vn_VOLT_reg	3.214	+0.71	2.991	+0.46	2.586	0.886
95	Vulnerability (VULN)vn_VULN_reg	3.746	+1.12	3.491	+0.86	2.648	0.984
96	Warmth (WARM)vn_WARM_reg	3.079	+0.55	3.217	+0.70	2.578	0.909
Genuineness, blend, and legacy quality Genuineness and vocal-burst blend are predicted. R_quality has Ladder training labels but no valid P3 test labels.
97	Genuineness (0–6)genuineness_0_6	1.683	-0.40	1.551	-0.48	2.332	1.621
98	Vocal-burst blend (0–10)blend_0_10	4.690	-0.73	4.149	-0.92	6.676	2.738
99	Legacy R_quality (no P3 test labels)R_quality	0.756	-1.00	0.684	-1.22	1.095	0.338
Empathic Insight Plus extra scores Nineteen additional clip-level teacher scores, including background noise and content enjoyment.
100	Ageeiv_extra:Age	3.050	-0.68	3.243	-0.02	3.250	0.293
101	Arousaleiv_extra:Arousal	2.029	+1.70	2.073	+1.80	1.289	0.435
102	Authenticityeiv_extra:Authenticity	3.000	+2.18	3.030	+2.37	2.667	0.153
103	Background Noiseeiv_extra:Background_Noise	0.578	-0.87	0.690	-0.44	0.808	0.264
104	Confident vs. Hesitanteiv_extra:Confident_vs._Hesitant	1.131	+0.30	1.095	+0.18	1.040	0.303
105	Gendereiv_extra:Gender	1.224	+1.85	1.294	+1.92	-0.621	0.999
106	High-Pitched vs. Low-Pitchedeiv_extra:High-Pitched_vs._Low-Pitched	1.682	-0.58	1.618	-0.84	1.827	0.250
107	Monotone vs. Expressiveeiv_extra:Monotone_vs._Expressive	2.616	+1.61	2.499	+1.36	1.859	0.470
108	Recording Qualityeiv_extra:Recording_Quality	2.689	+1.64	2.699	+1.67	2.144	0.332
109	Serious vs. Humorouseiv_extra:Serious_vs._Humorous	1.061	+0.39	0.816	-0.33	0.929	0.340
110	Soft vs. Harsheiv_extra:Soft_vs._Harsh	0.743	+1.44	0.825	+1.70	0.281	0.320
111	Submissive vs. Dominanteiv_extra:Submissive_vs._Dominant	0.595	+0.68	0.687	+0.96	0.376	0.324
112	Valenceeiv_extra:Valence	0.596	+1.55	0.515	+1.34	0.005	0.380
113	Vulnerable vs. Emotionally Detachedeiv_extra:Vulnerable_vs._Emotionally_Detached	1.487	-0.52	1.364	-0.80	1.715	0.437
114	Warm vs. Coldeiv_extra:Warm_vs._Cold	0.716	+2.22	0.735	+2.28	0.051	0.300
115	score background qualityeiv_extra:score_background_quality	3.515	+0.31	3.461	+0.23	3.301	0.693
116	score content enjoymenteiv_extra:score_content_enjoyment	4.783	+0.91	4.679	+0.57	4.507	0.303
117	score overall qualityeiv_extra:score_overall_quality	2.909	+0.51	2.911	+0.51	2.652	0.507
118	score speech qualityeiv_extra:score_speech_quality	1.796	-0.08	1.748	-0.41	1.808	0.146
Meta AudioBox Aesthetics Four AudioBox aesthetic teacher outputs. Expansions follow the official Meta model card.
119	Content enjoyment (CE)audiobox:CE	5.800	+0.98	5.999	+1.18	4.799	1.018
120	Content usefulness (CU)audiobox:CU	6.358	+0.71	6.737	+1.09	5.649	1.001
121	Production complexity (PC)audiobox:PC	1.877	-0.28	2.016	-0.19	2.331	1.617
122	Production quality (PQ)audiobox:PQ	7.400	+0.41	7.407	+0.41	7.044	0.879
Microsoft DNSMOS Seven DNSMOS teacher outputs: raw and calibrated SIG/BAK/OVRL estimates plus P.808 MOS.
123	Speech signal quality, rawdnsmos:SIG_raw	3.967	+0.10	4.007	+0.16	3.900	0.669
124	Background quality, rawdnsmos:BAK_raw	3.735	+0.47	3.973	+0.68	3.211	1.124
125	Overall quality, rawdnsmos:OVRL_raw	3.459	+0.46	3.595	+0.63	3.085	0.812
126	Speech signal quality, calibrateddnsmos:SIG	3.528	+0.08	3.553	+0.13	3.488	0.501
127	Background quality, calibrateddnsmos:BAK	3.694	+0.33	3.865	+0.51	3.389	0.928
128	Overall quality, calibrateddnsmos:OVRL	3.084	+0.40	3.172	+0.55	2.840	0.606
129	P.808 MOS estimatednsmos:P808_MOS	3.692	+0.55	3.475	+0.11	3.421	0.496
Vocal-burst count The regression target is log(1 + count). A separate table also reports count error after inverse transformation.
130	Vocal-burst count, log(1 + count)burst_count_log1p	0.018	+0.03	0.010	+0.02	0.000	0.647
VoiceCLAP attributes Sixty-one individual VoiceCLAP attribute teacher scores. The raw 768D VoiceCLAP embedding is stored in sidecars but is not a model output.
131	Affectionvoiceclap_attribute:Affection	1.266	+0.57	1.083	+0.25	0.947	0.554
132	Agevoiceclap_attribute:Age	3.203	-0.05	3.269	+0.07	3.229	0.547
133	Amusementvoiceclap_attribute:Amusement	0.324	-0.12	0.236	-0.27	0.392	0.572
134	Angervoiceclap_attribute:Anger	0.869	-0.24	0.789	-0.40	0.992	0.506
135	Arousalvoiceclap_attribute:Arousal	1.487	+0.11	1.431	+0.02	1.420	0.622
136	Astonishment Surprisevoiceclap_attribute:Astonishment_Surprise	0.818	+0.65	0.806	+0.62	0.509	0.479
137	Authenticityvoiceclap_attribute:Authenticity	3.216	+2.67	3.220	+2.69	2.770	0.167
138	Awevoiceclap_attribute:Awe	0.647	+0.42	0.699	+0.62	0.539	0.259
139	Background Noisevoiceclap_attribute:Background_Noise	0.419	-0.56	0.465	-0.39	0.567	0.264
140	Bitternessvoiceclap_attribute:Bitterness	0.596	+0.01	0.560	-0.14	0.592	0.236
141	Concentrationvoiceclap_attribute:Concentration	1.182	-0.06	1.347	+0.25	1.214	0.531
142	Confident vs. Hesitantvoiceclap_attribute:Confident_vs._Hesitant	1.312	+0.52	1.387	+0.68	1.069	0.468
143	Confusionvoiceclap_attribute:Confusion	1.116	+1.42	1.156	+1.53	0.643	0.334
144	Contemplationvoiceclap_attribute:Contemplation	1.164	+0.95	1.215	+1.07	0.780	0.406
145	Contemptvoiceclap_attribute:Contempt	0.452	-0.76	0.399	-0.92	0.709	0.339
146	Contentmentvoiceclap_attribute:Contentment	0.728	+0.46	0.611	+0.07	0.588	0.307
147	Disappointmentvoiceclap_attribute:Disappointment	1.059	+1.03	0.989	+0.79	0.760	0.291
148	Disgustvoiceclap_attribute:Disgust	0.686	+0.30	0.669	+0.22	0.625	0.207
149	Distressvoiceclap_attribute:Distress	1.481	+1.59	1.402	+1.36	0.927	0.350
150	Doubtvoiceclap_attribute:Doubt	0.617	+0.43	0.622	+0.46	0.535	0.188
151	Elationvoiceclap_attribute:Elation	0.537	-0.00	0.623	+0.21	0.539	0.397
152	Embarrassmentvoiceclap_attribute:Embarrassment	0.425	+0.38	0.423	+0.37	0.307	0.314
153	Emotional Numbnessvoiceclap_attribute:Emotional_Numbness	0.808	+0.54	0.739	+0.28	0.664	0.266
154	Fatigue Exhaustionvoiceclap_attribute:Fatigue_Exhaustion	0.557	+0.37	0.601	+0.53	0.462	0.261
155	Fearvoiceclap_attribute:Fear	1.091	+2.23	1.120	+2.37	0.618	0.212
156	Gendervoiceclap_attribute:Gender	1.301	+1.44	1.513	+1.66	-0.151	1.005
157	Helplessnessvoiceclap_attribute:Helplessness	1.164	+1.88	1.086	+1.60	0.658	0.268
158	High-Pitched vs. Low-Pitchedvoiceclap_attribute:High-Pitched_vs._Low-Pitched	1.440	-1.07	1.426	-1.11	1.840	0.375
159	Hope Enthusiasm Optimismvoiceclap_attribute:Hope_Enthusiasm_Optimism	0.874	+0.43	0.887	+0.46	0.705	0.396
160	Impatience and Irritabilityvoiceclap_attribute:Impatience_and_Irritability	0.764	-0.53	0.731	-0.59	1.052	0.541
161	Infatuationvoiceclap_attribute:Infatuation	0.881	+0.82	0.842	+0.70	0.608	0.332
162	Interestvoiceclap_attribute:Interest	1.731	+0.30	1.818	+0.50	1.598	0.440
163	Intoxication Altered States of Consciousnessvoiceclap_attribute:Intoxication_Altered_States_of_Consciousness	0.513	+0.02	0.296	-0.44	0.502	0.463
164	Jealousy & Envyvoiceclap_attribute:Jealousy_&_Envy	0.969	+1.82	0.965	+1.81	0.523	0.245
165	Longingvoiceclap_attribute:Longing	0.859	+1.46	0.879	+1.55	0.538	0.220
166	Malevolence Malicevoiceclap_attribute:Malevolence_Malice	0.631	-0.58	0.653	-0.52	0.833	0.346
167	Monotone vs. Expressivevoiceclap_attribute:Monotone_vs._Expressive	1.971	+0.33	1.980	+0.34	1.775	0.594
168	Painvoiceclap_attribute:Pain	0.759	+1.73	0.742	+1.65	0.381	0.218
169	Pleasure Ecstasyvoiceclap_attribute:Pleasure_Ecstasy	0.526	+0.08	0.494	-0.03	0.503	0.301
170	Pridevoiceclap_attribute:Pride	0.588	-0.55	0.550	-0.66	0.780	0.349
171	Recording Qualityvoiceclap_attribute:Recording_Quality	2.679	+1.12	2.725	+1.26	2.313	0.328
172	Reliefvoiceclap_attribute:Relief	1.875	+2.05	1.586	+1.35	1.025	0.415
173	Sadnessvoiceclap_attribute:Sadness	1.193	+1.41	1.115	+1.16	0.752	0.313
174	Serious vs. Humorousvoiceclap_attribute:Serious_vs._Humorous	0.679	-0.22	0.587	-0.38	0.803	0.568
175	Sexual Lustvoiceclap_attribute:Sexual_Lust	0.554	-0.19	0.717	+0.20	0.635	0.419
176	Shamevoiceclap_attribute:Shame	1.123	+2.11	1.145	+2.19	0.526	0.283
177	Soft vs. Harshvoiceclap_attribute:Soft_vs._Harsh	0.610	+1.25	0.574	+1.15	0.160	0.360
178	Sournessvoiceclap_attribute:Sourness	0.553	-0.53	0.464	-0.83	0.706	0.291
179	Submissive vs. Dominantvoiceclap_attribute:Submissive_vs._Dominant	0.160	-1.29	0.183	-1.23	0.623	0.359
180	Teasingvoiceclap_attribute:Teasing	0.387	-0.40	0.304	-0.62	0.540	0.379
181	Thankfulness Gratitudevoiceclap_attribute:Thankfulness_Gratitude	1.629	+0.46	1.579	+0.37	1.384	0.529
182	Triumphvoiceclap_attribute:Triumph	0.781	+0.18	0.682	-0.09	0.716	0.359
183	Valencevoiceclap_attribute:Valence	-0.069	-0.10	-0.044	-0.06	-0.007	0.635
184	Vulnerable vs. Emotionally Detachedvoiceclap_attribute:Vulnerable_vs._Emotionally_Detached	1.379	-0.47	1.447	-0.34	1.638	0.556
185	Warm vs. Coldvoiceclap_attribute:Warm_vs._Cold	0.146	+0.53	0.082	+0.37	-0.066	0.400
186	durationvoiceclap_attribute:duration	11.199	+0.04	10.578	-0.05	10.914	6.354
187	score background qualityvoiceclap_attribute:score_background_quality	3.474	+0.46	3.362	+0.24	3.245	0.498
188	score content enjoymentvoiceclap_attribute:score_content_enjoyment	4.753	+0.66	4.739	+0.56	4.656	0.147
189	score overall qualityvoiceclap_attribute:score_overall_quality	2.841	+0.50	2.824	+0.46	2.635	0.412
190	score speech qualityvoiceclap_attribute:score_speech_quality	1.875	-0.23	1.850	-0.59	1.891	0.069
191	talking speedvoiceclap_attribute:talking_speed	10.801	+0.47	11.446	+0.64	9.028	3.756

All Orange embedding components

The cosine above is the meaningful vector-level comparison; component values have no standalone semantic label.

Timbre — all 128 vector components

Dimension	Tiny	Base	Orange teacher
0	0.0831	-0.0076	-0.0588
1	0.1233	0.1225	0.0989
2	0.0738	0.1425	0.1511
3	-0.0671	-0.0783	-0.0825
4	-0.0764	-0.0677	-0.0765
5	-0.1055	-0.1155	-0.1030
6	0.1189	0.0556	0.0494
7	0.2633	0.2936	0.2554
8	0.0163	0.0144	-0.0577
9	0.0007	0.0038	0.0381
10	-0.0559	-0.0718	0.0187
11	-0.0543	-0.0885	-0.0952
12	-0.0952	-0.1090	-0.0818
13	-0.1016	-0.0804	-0.0594
14	0.0313	0.0513	0.0925
15	0.0578	0.0677	0.0388
16	-0.0415	-0.0950	-0.0761
17	-0.1163	-0.0874	-0.0846
18	-0.0518	-0.0939	-0.0166
19	-0.0914	-0.0783	-0.0770
20	0.0709	0.0613	-0.0205
21	0.0642	0.0173	-0.0034
22	-0.0188	-0.0389	-0.0136
23	-0.0572	-0.0934	-0.0963
24	-0.0336	-0.0103	0.0137
25	-0.0543	-0.0424	-0.0715
26	-0.0655	-0.0712	-0.0763
27	-0.0374	-0.0683	-0.0759
28	-0.0984	-0.1106	-0.0896
29	0.1240	0.1403	0.0810
30	0.0486	0.0367	-0.0382
31	-0.0786	-0.0691	-0.0228
32	0.1790	0.2008	0.1400
33	0.0895	0.0386	-0.0255
34	-0.0658	-0.0594	-0.0729
35	0.1738	0.1500	0.1022
36	-0.1138	-0.0842	-0.0875
37	-0.0032	-0.0119	-0.0963
38	0.0063	0.0252	0.1288
39	-0.0305	-0.0240	-0.0820
40	-0.0162	0.0510	0.0477
41	0.0364	0.0125	-0.0501
42	-0.0863	-0.0874	-0.0821
43	-0.0553	0.0079	-0.0107
44	0.1304	0.0362	-0.0077
45	-0.0006	-0.0066	0.0428
46	0.1738	0.1662	0.0689
47	-0.0812	-0.0842	-0.0823
48	-0.0946	-0.0864	-0.0795
49	0.0010	-0.0629	-0.0364
50	0.0971	0.0869	0.0224
51	0.0036	0.0788	0.0983
52	-0.0169	-0.0537	-0.0667
53	0.0162	0.0318	-0.0525
54	-0.0959	-0.1020	-0.0911
55	0.0024	-0.0540	0.0078
56	-0.0674	-0.0847	-0.0771
57	-0.0674	-0.0356	-0.0815
58	-0.0447	-0.0572	0.0646
59	0.0393	0.0448	0.1351
60	0.1246	0.1457	0.0638
61	0.1943	0.2310	0.1831
62	0.0079	0.0526	0.0392
63	0.0038	-0.0251	-0.0517
64	0.0725	0.0718	0.0304
65	-0.0837	-0.0793	-0.0663
66	0.0454	-0.0327	0.1222
67	-0.0748	-0.0891	-0.0784
68	0.0588	0.0723	0.0456
69	0.0690	0.0604	0.1361
70	0.0296	0.0118	0.0084
71	0.2467	0.2537	0.2203
72	-0.0524	-0.0518	0.0130
73	0.0505	0.0231	0.0092
74	-0.0751	-0.0144	0.0575
75	0.2429	0.1544	0.2014
76	0.0844	0.0831	0.1512
77	-0.0585	-0.0837	-0.0743
78	-0.0761	-0.0702	-0.0724
79	-0.0094	0.0313	-0.0348
80	-0.0483	-0.0491	-0.0580
81	0.2531	0.2353	0.2664
82	-0.0388	-0.0277	-0.0779
83	0.0623	0.1063	0.1764
84	-0.0844	-0.1025	-0.0804
85	0.0155	0.0766	0.0552
86	0.1214	-0.0537	0.0643
87	-0.1029	-0.1446	-0.0939
88	-0.0559	-0.0353	-0.0331
89	-0.0677	-0.0604	-0.0746
90	0.0428	0.0297	0.0368
91	0.0091	-0.0008	0.0334
92	-0.0876	-0.0316	-0.0352
93	-0.0169	-0.0564	-0.0351
94	0.0313	0.0124	-0.0168
95	-0.0291	-0.0982	-0.0874
96	-0.0978	-0.0766	-0.0697
97	0.0796	0.0971	0.1711
98	-0.0645	-0.0389	-0.0682
99	0.0991	0.0896	0.1105
100	0.0492	0.0294	0.1428
101	-0.0296	-0.0212	-0.0756
102	-0.0179	0.0289	0.0634
103	-0.1048	-0.1036	-0.0859
104	0.0984	0.0564	0.0128
105	-0.0550	-0.0977	-0.0784
106	-0.0119	0.0119	0.0775
107	-0.0626	-0.0847	-0.0758
108	-0.0684	-0.0917	-0.0883
109	-0.0171	-0.0645	-0.0332
110	0.0096	-0.0192	-0.0354
111	0.0032	0.0036	0.1302
112	-0.0377	-0.0478	-0.0802
113	-0.0620	-0.0907	-0.0684
114	0.1387	0.1457	0.1082
115	0.1841	0.1889	0.1560
116	0.0617	0.0497	0.0927
117	-0.0267	-0.0137	0.0291
118	-0.0751	-0.0777	-0.0792
119	0.1221	0.0772	-0.0239
120	0.0991	0.1198	0.1127
121	-0.0066	0.0015	0.0535
122	-0.0168	-0.0486	-0.0711
123	-0.0585	-0.0529	-0.0320
124	0.0837	0.0351	0.0701
125	-0.0863	-0.0783	-0.0811
126	-0.0537	-0.0583	-0.0701
127	0.1604	0.0793	0.0350

Identity — all 250 vector components

Dimension	Tiny	Base	Orange teacher
0	-0.0523	-0.0197	-0.0278
1	-0.0446	-0.0334	-0.0386
2	-0.0729	-0.0625	-0.0491
3	-0.0446	-0.0198	-0.0387
4	0.0571	0.0648	0.1344
5	0.0049	0.0193	-0.0417
6	0.0945	0.1423	0.0683
7	0.0383	0.0585	0.1210
8	0.1125	0.0642	0.0305
9	0.0213	0.0318	0.0522
10	-0.0691	-0.0394	-0.0419
11	-0.0708	-0.0244	-0.0540
12	0.0410	0.0705	0.0523
13	0.0629	0.1164	0.2114
14	-0.0228	-0.0200	-0.0272
15	0.1004	0.1157	0.1958
16	0.0149	0.0725	-0.0195
17	0.0000	0.0170	-0.0479
18	0.0579	0.0456	0.1665
19	-0.0800	-0.0984	-0.0633
20	0.0034	-0.0195	-0.0087
21	-0.0115	-0.0264	-0.0370
22	0.0198	0.0552	0.0511
23	-0.0750	-0.0998	-0.0386
24	0.0337	-0.0106	-0.0341
25	0.0233	-0.0043	-0.0201
26	0.0583	0.0582	-0.0440
27	-0.0132	-0.0371	-0.0324
28	0.0200	0.0161	-0.0432
29	-0.0348	-0.0281	0.0399
30	-0.0385	-0.0174	0.0116
31	-0.0387	0.0695	0.0959
32	0.1649	0.1197	0.1041
33	0.0646	0.0735	0.0144
34	0.1791	0.2009	0.1536
35	0.0654	0.0168	0.0249
36	0.0754	0.0469	0.0511
37	-0.0991	-0.1151	-0.0276
38	-0.0554	-0.0016	-0.0477
39	0.0073	-0.0456	-0.0594
40	0.0256	0.0104	0.0358
41	-0.0107	0.0264	-0.0275
42	0.1141	0.1011	0.0688
43	0.0317	0.0256	0.0007
44	0.0003	-0.0039	-0.0268
45	-0.1133	-0.1111	-0.0385
46	-0.0741	-0.1104	-0.0586
47	-0.0414	-0.0765	-0.0472
48	0.0229	-0.0223	0.0884
49	0.0176	-0.0077	0.0425
50	-0.0068	0.0329	0.0496
51	-0.0350	0.0258	0.0607
52	0.0437	0.0411	-0.0220
53	-0.0523	-0.0384	-0.0386
54	0.0741	0.0695	0.0325
55	-0.0030	0.0314	-0.0323
56	-0.0203	-0.0155	0.0565
57	0.0458	0.0944	0.0876
58	-0.0491	-0.0103	-0.0383
59	0.0708	0.0668	0.0706
60	0.0312	0.0436	0.0085
61	-0.0385	-0.0346	-0.0370
62	0.0131	0.0495	-0.0337
63	-0.0113	-0.0121	0.0601
64	-0.0845	-0.0891	-0.0444
65	0.0629	0.0394	0.1215
66	0.0754	0.1124	0.1377
67	0.0228	-0.0210	-0.0420
68	-0.0429	-0.0313	-0.0124
69	0.0452	0.0835	0.1010
70	0.0500	0.0835	0.0359
71	-0.0253	-0.0078	-0.0418
72	-0.0675	-0.0565	-0.0442
73	0.1016	0.1197	0.0641
74	-0.0708	-0.0898	-0.0431
75	0.0531	0.0805	0.1130
76	0.1083	0.1124	0.1051
77	-0.0646	-0.0439	-0.0102
78	0.0583	0.0635	0.0106
79	-0.0650	-0.0885	-0.0427
80	-0.0650	-0.0595	-0.0170
81	-0.0108	0.0095	-0.0422
82	0.0023	-0.0288	-0.0182
83	-0.0410	-0.0542	-0.0354
84	0.0213	0.0333	0.0306
85	0.0300	0.0324	0.0150
86	0.0500	0.0140	-0.0381
87	0.0068	-0.0209	-0.0340
88	0.0733	0.1104	0.1746
89	0.0458	0.0612	0.0628
90	0.0612	0.0386	0.0468
91	0.0145	-0.0082	0.1179
92	-0.0059	-0.0009	-0.0190
93	-0.0571	-0.0042	-0.0484
94	-0.0410	-0.0555	-0.0690
95	0.1316	0.1663	0.1619
96	-0.0152	0.0098	0.1174
97	-0.0883	-0.0269	0.0300
98	-0.0446	0.0575	0.0734
99	-0.0379	0.0109	0.0418
100	0.1774	0.1304	0.1234
101	0.1258	0.0705	0.0259
102	-0.0331	-0.0589	-0.0426
103	0.1058	0.0821	0.0563
104	-0.0354	-0.0781	-0.0555
105	-0.0637	-0.0898	-0.0554
106	-0.0537	-0.0185	-0.0328
107	0.0381	0.0229	0.0043
108	0.0358	0.0224	-0.0317
109	-0.0427	0.0130	-0.0410
110	-0.0331	-0.0519	-0.0507
111	0.2316	0.1915	0.2098
112	-0.0030	-0.0110	0.0170
113	0.0008	-0.1111	-0.0442
114	-0.0741	-0.0274	-0.0594
115	-0.0766	-0.0404	-0.0302
116	0.0298	0.0384	0.0336
117	0.0367	0.0356	0.0556
118	0.0155	-0.0308	-0.0191
119	0.1000	0.1077	0.1247
120	-0.0271	0.0120	-0.0543
121	0.0608	0.0071	0.0128
122	-0.0469	-0.0251	-0.0402
123	0.0024	0.0241	0.0349
124	0.0625	0.0429	0.0569
125	0.1599	0.1423	0.1061
126	0.1050	0.0675	0.0719
127	-0.0483	-0.0449	-0.0267
128	-0.0298	-0.0248	-0.0274
129	-0.0354	-0.0645	-0.0452
130	0.0691	0.0801	0.0346
131	-0.0479	-0.0539	-0.0373
132	0.1100	0.0609	0.1318
133	0.0285	0.0449	-0.0421
134	0.0933	0.0569	-0.0243
135	-0.0354	-0.0402	-0.0369
136	-0.0099	-0.0321	-0.0457
137	0.0387	0.0354	-0.0199
138	-0.0416	-0.0619	-0.0376
139	0.0402	0.0256	-0.0436
140	0.0262	0.0662	0.0114
141	0.1274	0.0752	-0.0063
142	-0.0441	-0.0429	-0.0368
143	-0.0072	-0.0397	-0.0370
144	0.0002	0.0243	-0.0289
145	-0.0900	-0.0998	-0.0541
146	-0.0140	-0.0249	0.0280
147	-0.0762	-0.0752	-0.0378
148	0.0103	0.0288	-0.0470
149	0.0721	0.0845	0.0856
150	-0.0167	-0.0099	-0.0149
151	-0.0406	-0.0367	0.0100
152	-0.0554	-0.0271	-0.0472
153	0.0121	0.0269	-0.0062
154	0.0687	0.0382	0.0388
155	0.0633	0.0891	0.1648
156	0.0190	-0.0032	-0.0427
157	0.1308	0.1969	0.0620
158	0.0962	0.0411	0.0341
159	0.0281	0.0175	0.0446
160	-0.0479	-0.0426	0.0128
161	-0.0150	0.0264	-0.0307
162	-0.1054	-0.0865	-0.0494
163	0.0177	-0.0170	-0.0474
164	0.0255	0.0010	-0.0374
165	-0.0158	0.0519	0.0826
166	0.0113	0.0150	-0.0258
167	0.0858	0.0223	-0.0054
168	-0.0317	-0.0200	0.0394
169	0.0816	0.0978	0.0511
170	-0.0285	-0.0542	-0.0399
171	0.0248	0.0108	-0.0160
172	-0.0245	-0.0136	-0.0213
173	0.1241	0.1051	0.0858
174	-0.0400	-0.0082	-0.0359
175	-0.0491	-0.0755	-0.0701
176	0.0024	-0.0166	-0.0362
177	-0.0431	-0.0412	-0.0351
178	0.0133	0.0745	0.0275
179	-0.0186	0.0211	-0.0525
180	0.0044	-0.0479	-0.0119
181	0.0037	0.0329	-0.0235
182	-0.0224	-0.0269	-0.0368
183	-0.0128	-0.0294	-0.0859
184	0.0104	0.0022	-0.0433
185	-0.0144	0.0339	0.0093
186	-0.0508	-0.0442	-0.0514
187	-0.0733	-0.0328	0.0685
188	0.0039	0.0362	0.0472
189	0.0262	0.0452	0.0033
190	0.0862	0.0555	-0.0007
191	0.0020	-0.0076	-0.0184
192	-0.0051	-0.0010	-0.0083
193	-0.0829	-0.0432	-0.0449
194	-0.0596	-0.0251	-0.0552
195	-0.0654	-0.0111	-0.0405
196	0.0362	0.0502	0.0536
197	-0.0076	0.0532	-0.0080
198	-0.0381	-0.0662	-0.0412
199	-0.0937	-0.0991	-0.0468
200	-0.0138	-0.0379	-0.0492
201	0.0533	0.0964	0.1035
202	-0.0142	0.0436	-0.0122
203	-0.0129	-0.0394	-0.0531
204	-0.0369	0.0286	0.0515
205	0.0646	0.0692	0.0837
206	0.1308	0.1144	0.1085
207	-0.0086	0.0145	0.0365
208	-0.0171	-0.0185	-0.0442
209	-0.0477	-0.0343	0.0174
210	-0.0120	-0.0414	-0.0554
211	-0.0398	-0.0092	0.0220
212	-0.0259	-0.0308	0.0132
213	0.1808	0.1576	0.1536
214	0.0381	0.0371	0.0718
215	0.0637	0.0153	0.0337
216	0.2432	0.1969	0.1761
217	0.0554	0.1137	0.0634
218	-0.1391	-0.1357	-0.0494
219	-0.0502	-0.0050	-0.0554
220	-0.0558	-0.0492	-0.0470
221	0.0224	-0.0115	-0.0365
222	-0.0448	-0.0688	-0.0326
223	-0.0541	0.0010	0.0523
224	-0.0069	0.0079	0.0714
225	-0.0360	-0.0459	0.0425
226	0.0791	0.0559	0.0495
227	0.0273	-0.0101	0.0993
228	-0.0163	-0.0582	-0.0689
229	0.0746	0.0589	0.0447
230	-0.0331	0.0074	-0.0434
231	0.0571	0.1004	0.0010
232	0.0258	0.0362	0.0048
233	-0.0246	-0.0429	0.0494
234	0.0312	0.0841	-0.0310
235	0.0011	0.0429	0.0256
236	-0.0296	-0.0284	-0.0366
237	-0.0239	-0.0192	-0.0435
238	-0.0056	0.0028	0.0160
239	-0.0175	-0.0485	-0.0440
240	-0.0820	-0.0429	-0.0434
241	0.0920	0.0808	0.1407
242	-0.0641	-0.0602	-0.0627
243	-0.0712	-0.0645	-0.0547
244	0.0502	0.0768	0.0565
245	0.0154	0.0296	0.0955
246	-0.0261	-0.0210	-0.0241
247	0.0077	-0.0191	-0.0359
248	-0.1020	-0.1024	-0.0487
249	-0.0162	-0.0376	-0.0033

Source: HUMANENESS_SMALL_VOICE_IDENTITY_R1_R2_2026-10-02_anime_000.html · SHA-256 f177f287bee08aa4…

g12GermanAnime voice study

anime_000 · de · 50/50

Generated TTS prediction · Rank 1 qv · 14.3 s

Ein perfekt trainierter Jagdsaker im Traum zu besitzen, deutet darauf hin, dass du Macht übernimmst oder schlimmer noch, zu einem Tyrannen wirst. Es spricht von einer schleichenden Ungerechtigkeit, einer spirituellen Blindheit, der du dich stellen musst.

Tiny Base · values are model estimates, not ground truth

Strongest emotions relative to training

Contemplation

z +1.60 / +1.90raw 1.04 / 1.22

Concentration

z +1.37 / +1.75raw 1.65 / 1.93

Hope Enthusiasm Optimism

z +1.54 / +1.41raw 1.29 / 1.19

Contentment

z +1.37 / +0.77raw 0.70 / 0.40

Awe

z +1.29 / +1.14raw 0.55 / 0.49

Interest

z +1.07 / +1.23raw 2.56 / 2.71

Fear

z +0.50 / +1.12raw 0.32 / 0.70

The center of each bar is the S9 teacher median. Positive z is to the right; negative z is to the left. Ranking uses z, not raw teacher units.

Strongest VoiceNet dimensions relative to training

Narrator style (S_NARR)

z +2.66 / +2.88raw 5.15 / 5.47

Vocal register (REGS)

z +2.27 / +2.34raw 4.07 / 4.17

Storytelling style (S_STRY)

z +1.94 / +1.83raw 5.13 / 4.99

Whispered talking style (S_WHIS)

z +1.60 / +1.55raw 4.18 / 4.10

Dramatic style (S_DRAM)

z +1.42 / +1.37raw 4.35 / 4.29

ASMR style (S_ASMR)

z +1.13 / +1.32raw 2.97 / 3.23

Pitch range (RANG)

z +1.19 / +1.29raw 3.98 / 4.07

All 57 VoiceNet predictions, including raw units, are in the full table below. These seven are ranked by z; the top values may differ from the strongest raw dimensions.

Voice, speed and quality scores in context

Genuineness (0–6)z -0.68 / -0.68raw 1.23 / 1.23

Vocal-burst blend (0–10)z -0.77 / -0.83raw 4.56 / 4.41

Content enjoyment (CE)z +0.95 / +1.34raw 5.77 / 6.17

Production quality (PQ)z +0.27 / +0.33raw 7.28 / 7.34

Speech signal quality, calibratedz +0.03 / +0.07raw 3.50 / 3.53

Background quality, calibratedz +0.40 / +0.58raw 3.76 / 3.92

Overall quality, calibratedz +0.41 / +0.57raw 3.09 / 3.19

P.808 MOS estimatez +0.47 / +0.36raw 3.66 / 3.60

score content enjoymentz +1.08 / +0.97raw 4.84 / 4.80

score overall qualityz +0.55 / +0.53raw 2.93 / 2.92

Background Noisez -0.95 / -0.99raw 0.56 / 0.55

Tempo (TEMP)z +0.76 / +0.79raw 3.02 / 3.05

Arousal (AROU)z -0.25 / -0.39raw 2.07 / 1.91

Valence (VALN)z -0.43 / -0.59raw 1.85 / 1.67

Recording quality (RCQL)z +0.93 / +1.04raw 3.58 / 3.68

Background noise (BKGN)z +0.76 / +0.80raw 3.28 / 3.31

talking speedz +0.55 / +0.74raw 11.10 / 11.81

Characters per second (CPS): 17.79 raw · z +2.33

Orange speaker embedding reconstruction

Cosine against Orange on this same clip (higher means closer to that teacher vector):

Embedding	Tiny	Base
Timbre · 128D	0.833	0.861
Identity · 250D	0.689	0.774

Vocal-burst regions

Tiny

Base

0 s14.3 s

Verified burst intervals are unavailable for this clip.

Tiny: 0 regions, count-head estimate 0.03; Base: 0 regions, count-head estimate 0.12.

Exact predicted start and end times

Model	Region	Start (s)	End (s)	Duration (s)

All 192 score slots · raw and z values

#	Target	Tiny raw	Tiny z	Base raw	Base z	Train median	Train SD
Emotion scores Forty clip-level Empathic Insight emotion teacher outputs. Each row evaluates one named emotion score.
0	Affectionemo_Affection	0.564	+0.98	0.325	+0.56	0.007	0.570
1	Amusementemo_Amusement	0.149	+0.17	0.007	+0.01	-0.001	0.885
2	Angeremo_Anger	0.134	+0.21	0.166	+0.26	0.004	0.613
3	Astonishment Surpriseemo_Astonishment_Surprise	0.277	+0.48	0.140	+0.23	0.005	0.572
4	Aweemo_Awe	0.551	+1.29	0.487	+1.14	0.000	0.427
5	Bitternessemo_Bitterness	-0.013	-0.06	-0.011	-0.06	0.013	0.415
6	Concentrationemo_Concentration	1.647	+1.37	1.932	+1.75	0.634	0.741
7	Confusionemo_Confusion	0.109	+0.20	0.138	+0.25	0.001	0.540
8	Contemplationemo_Contemplation	1.042	+1.60	1.219	+1.90	0.082	0.598
9	Contemptemo_Contempt	0.037	+0.08	0.033	+0.07	-0.000	0.464
10	Contentmentemo_Contentment	0.705	+1.37	0.398	+0.77	0.000	0.514
11	Disappointmentemo_Disappointment	0.109	+0.16	0.180	+0.26	0.000	0.700
12	Disgustemo_Disgust	0.033	+0.05	0.021	+0.03	0.007	0.489
13	Distressemo_Distress	0.050	+0.06	0.111	+0.14	0.000	0.821
14	Doubtemo_Doubt	0.185	+0.39	0.448	+0.95	0.006	0.466
15	Elationemo_Elation	0.370	+0.49	0.166	+0.21	0.012	0.728
16	Embarrassmentemo_Embarrassment	-0.037	-0.19	-0.032	-0.17	0.043	0.430
17	Emotional Numbnessemo_Emotional_Numbness	0.225	+0.24	0.109	+0.11	0.004	0.917
18	Fatigue Exhaustionemo_Fatigue_Exhaustion	0.010	-0.03	0.027	-0.00	0.028	0.539
19	Fearemo_Fear	0.322	+0.50	0.699	+1.12	0.015	0.610
20	Helplessnessemo_Helplessness	0.005	+0.01	0.112	+0.17	-0.004	0.696
21	Hope Enthusiasm Optimismemo_Hope_Enthusiasm_Optimism	1.292	+1.54	1.188	+1.41	0.117	0.760
22	Impatience and Irritabilityemo_Impatience_and_Irritability	0.028	-0.17	0.182	+0.05	0.149	0.705
23	Infatuationemo_Infatuation	0.073	+0.16	0.001	+0.03	-0.015	0.533
24	Interestemo_Interest	2.556	+1.07	2.706	+1.23	1.589	0.907
25	Intoxication Altered States of Consciousnessemo_Intoxication_Altered_States_of_Consciousness	-0.001	+0.04	-0.011	+0.02	-0.025	0.559
26	Jealousy and Envyemo_Jealousy_and_Envy	0.103	+0.10	0.056	-0.01	0.059	0.442
27	Longingemo_Longing	0.287	+0.32	0.226	+0.22	0.087	0.632
28	Malevolence Maliceemo_Malevolence_Malice	0.176	+0.23	0.203	+0.28	0.055	0.534
29	Painemo_Pain	-0.028	-0.05	-0.019	-0.03	-0.002	0.579
30	Pleasure Ecstasyemo_Pleasure_Ecstasy	0.336	+0.52	0.128	+0.18	0.017	0.614
31	Prideemo_Pride	0.112	+0.22	0.104	+0.20	0.002	0.509
32	Reliefemo_Relief	0.084	+0.07	0.032	-0.00	0.033	0.681
33	Sadnessemo_Sadness	0.196	+0.26	0.262	+0.35	0.000	0.759
34	Sexual Lustemo_Sexual_Lust	0.142	+0.23	0.132	+0.21	0.030	0.494
35	Shameemo_Shame	-0.024	-0.07	-0.013	-0.05	0.013	0.510
36	Sournessemo_Sourness	0.342	+0.79	0.183	+0.43	-0.005	0.439
37	Teasingemo_Teasing	0.461	+0.85	0.367	+0.67	0.000	0.545
38	Thankfulness Gratitudeemo_Thankfulness_Gratitude	0.176	+0.19	0.068	+0.04	0.041	0.697
39	Triumphemo_Triumph	0.034	+0.08	0.016	+0.04	-0.007	0.521
VoiceNet dimensions Fifty-seven VoiceNet voice, delivery, style, and recording dimensions. Codes are expanded in the target column.
40	Perceived voice age (AGEV)vn_AGEV_reg	3.567	+0.47	3.622	+0.51	2.984	1.238
41	Arousal (AROU)vn_AROU_reg	2.071	-0.25	1.909	-0.39	2.359	1.147
42	Arousal shift (ARSH)vn_ARSH_reg	1.852	-0.84	1.568	-1.17	2.580	0.867
43	Vocal attack (ATCK)vn_ATCK_reg	1.481	-0.53	1.633	-0.41	2.162	1.295
44	Background noise (BKGN)vn_BKGN_reg	3.281	+0.76	3.311	+0.80	2.703	0.761
45	Brightness (BRGT)vn_BRGT_reg	2.263	+0.33	2.279	+0.35	1.991	0.813
46	Speech chunking (CHNK)vn_CHNK_reg	2.408	+0.45	2.598	+0.61	1.847	1.239
47	Articulation clarity (CLRT)vn_CLRT_reg	2.754	+0.78	2.803	+0.83	2.018	0.945
48	Cognitive load (COGL)vn_COGL_reg	2.402	+0.29	2.483	+0.37	2.094	1.061
49	Dynamic arc (DARC)vn_DARC_reg	1.541	-0.05	1.331	-0.21	1.615	1.380
50	Disfluency (DFLU)vn_DFLU_reg	1.320	-0.99	1.159	-1.12	2.488	1.184
51	Emphasis (EMPH)vn_EMPH_reg	3.264	+0.43	3.338	+0.48	2.607	1.524
52	Esthetics (ESTH)vn_ESTH_reg	3.231	+1.06	3.347	+1.21	2.402	0.782
53	Content appropriateness (EXPL)vn_EXPL_reg	0.156	+0.22	0.090	+0.01	0.086	0.322
54	Focus (FOCS)vn_FOCS_reg	3.173	+0.75	2.978	+0.58	2.344	1.102
55	Fullness (FULL)vn_FULL_reg	1.799	+0.02	1.859	+0.09	1.778	0.889
56	Perceived gender (GEND)vn_GEND_reg	0.734	-2.09	0.858	-2.01	4.055	1.588
57	Harmonicity (HARM)vn_HARM_reg	1.172	-1.57	1.172	-1.57	2.480	0.836
58	Metallic character (METL)vn_METL_reg	0.629	-1.04	0.517	-1.15	1.621	0.958
59	Pitch range (RANG)vn_RANG_reg	3.978	+1.19	4.069	+1.29	2.914	0.897
60	Recording quality (RCQL)vn_RCQL_reg	3.578	+0.93	3.680	+1.04	2.754	0.888
61	Vocal register (REGS)vn_REGS_reg	4.072	+2.27	4.170	+2.34	1.198	1.268
62	Respiration (RESP)vn_RESP_reg	3.569	+0.84	3.406	+0.69	2.680	1.056
63	Roughness (ROUG)vn_ROUG_reg	1.454	-0.65	1.262	-0.87	2.033	0.887
64	Chest resonance (R_CHST)vn_R_CHST_reg	1.060	-1.27	1.166	-1.15	2.135	0.844
65	Head resonance (R_HEAD)vn_R_HEAD_reg	3.070	+1.12	3.115	+1.18	2.148	0.822
66	Mask resonance (R_MASK)vn_R_MASK_reg	2.239	+0.33	2.149	+0.24	1.908	1.005
67	Mixed resonance (R_MIXD)vn_R_MIXD_reg	0.781	-0.78	0.765	-0.80	1.436	0.841
68	Nasal resonance (R_NASL)vn_R_NASL_reg	3.196	+0.39	2.969	+0.17	2.791	1.047
69	Oral resonance (R_ORAL)vn_R_ORAL_reg	1.603	-0.78	1.484	-0.94	2.184	0.741
70	Throat resonance (R_THRT)vn_R_THRT_reg	1.464	-0.76	1.691	-0.47	2.070	0.803
71	Smoothness (SMTH)vn_SMTH_reg	2.922	+0.71	3.026	+0.81	2.143	1.093
72	Stance (STNC)vn_STNC_reg	1.778	-0.75	1.791	-0.74	2.633	1.137
73	Speech structure (STRU)vn_STRU_reg	2.692	+0.58	2.715	+0.60	2.137	0.958
74	ASMR style (S_ASMR)vn_S_ASMR_reg	2.971	+1.13	3.235	+1.32	1.370	1.411
75	Authoritative style (S_AUTH)vn_S_AUTH_reg	1.059	-0.03	1.089	+0.00	1.088	1.043
76	Cartoonish style (S_CART)vn_S_CART_reg	2.765	+0.86	2.573	+0.72	1.560	1.401
77	Casual style (S_CASU)vn_S_CASU_reg	3.167	-0.49	3.003	-0.62	3.793	1.278
78	Conversational style (S_CONV)vn_S_CONV_reg	2.419	-0.13	2.429	-0.13	2.594	1.318
79	Dramatic style (S_DRAM)vn_S_DRAM_reg	4.355	+1.42	4.292	+1.37	2.721	1.148
80	Formal style (S_FORM)vn_S_FORM_reg	2.427	+1.21	2.443	+1.22	1.195	1.021
81	Monologue style (S_MONO)vn_S_MONO_reg	4.087	+0.98	4.217	+1.08	2.824	1.284
82	Narrator style (S_NARR)vn_S_NARR_reg	5.153	+2.66	5.467	+2.88	1.307	1.446
83	Newsreader style (S_NEWS)vn_S_NEWS_reg	0.550	+0.25	0.743	+0.59	0.408	0.568
84	Playful style (S_PLAY)vn_S_PLAY_reg	2.802	+0.34	2.501	+0.11	2.352	1.315
85	Ranting or angry style (S_RANT)vn_S_RANT_reg	2.167	+0.74	1.776	+0.44	1.213	1.289
86	Storytelling style (S_STRY)vn_S_STRY_reg	5.129	+1.94	4.988	+1.83	2.480	1.366
87	Teacher or didactic style (S_TECH)vn_S_TECH_reg	1.097	+0.37	0.773	+0.10	0.646	1.227
88	Whispered talking style (S_WHIS)vn_S_WHIS_reg	4.177	+1.60	4.102	+1.55	1.597	1.618
89	Tempo (TEMP)vn_TEMP_reg	3.025	+0.76	3.053	+0.79	2.117	1.190
90	Tension (TENS)vn_TENS_reg	1.742	+0.21	1.574	+0.02	1.559	0.852
91	Valence (VALN)vn_VALN_reg	1.851	-0.43	1.665	-0.59	2.328	1.118
92	Valence shift (VALS)vn_VALS_reg	1.955	-0.52	2.054	-0.43	2.518	1.079
93	Velocity flux (VFLX)vn_VFLX_reg	2.029	-0.19	1.825	-0.36	2.256	1.208
94	Volatility (VOLT)vn_VOLT_reg	3.410	+0.93	3.271	+0.77	2.586	0.886
95	Vulnerability (VULN)vn_VULN_reg	3.587	+0.95	3.723	+1.09	2.648	0.984
96	Warmth (WARM)vn_WARM_reg	2.691	+0.12	2.593	+0.02	2.578	0.909
Genuineness, blend, and legacy quality Genuineness and vocal-burst blend are predicted. R_quality has Ladder training labels but no valid P3 test labels.
97	Genuineness (0–6)genuineness_0_6	1.231	-0.68	1.231	-0.68	2.332	1.621
98	Vocal-burst blend (0–10)blend_0_10	4.563	-0.77	4.414	-0.83	6.676	2.738
99	Legacy R_quality (no P3 test labels)R_quality	0.673	-1.25	0.655	-1.30	1.095	0.338
Empathic Insight Plus extra scores Nineteen additional clip-level teacher scores, including background noise and content enjoyment.
100	Ageeiv_extra:Age	3.185	-0.22	3.255	+0.01	3.250	0.293
101	Arousaleiv_extra:Arousal	1.678	+0.89	1.755	+1.07	1.289	0.435
102	Authenticityeiv_extra:Authenticity	2.992	+2.13	2.998	+2.17	2.667	0.153
103	Background Noiseeiv_extra:Background_Noise	0.556	-0.95	0.545	-0.99	0.808	0.264
104	Confident vs. Hesitanteiv_extra:Confident_vs._Hesitant	1.046	+0.02	1.161	+0.40	1.040	0.303
105	Gendereiv_extra:Gender	1.263	+1.88	1.185	+1.81	-0.621	0.999
106	High-Pitched vs. Low-Pitchedeiv_extra:High-Pitched_vs._Low-Pitched	1.759	-0.27	1.725	-0.41	1.827	0.250
107	Monotone vs. Expressiveeiv_extra:Monotone_vs._Expressive	2.308	+0.95	2.232	+0.79	1.859	0.470
108	Recording Qualityeiv_extra:Recording_Quality	2.699	+1.67	2.728	+1.76	2.144	0.332
109	Serious vs. Humorouseiv_extra:Serious_vs._Humorous	0.843	-0.25	0.689	-0.71	0.929	0.340
110	Soft vs. Harsheiv_extra:Soft_vs._Harsh	0.612	+1.03	0.542	+0.82	0.281	0.320
111	Submissive vs. Dominanteiv_extra:Submissive_vs._Dominant	0.473	+0.30	0.510	+0.42	0.376	0.324
112	Valenceeiv_extra:Valence	0.166	+0.42	0.260	+0.67	0.005	0.380
113	Vulnerable vs. Emotionally Detachedeiv_extra:Vulnerable_vs._Emotionally_Detached	1.671	-0.10	1.618	-0.22	1.715	0.437
114	Warm vs. Coldeiv_extra:Warm_vs._Cold	0.260	+0.70	0.220	+0.56	0.051	0.300
115	score background qualityeiv_extra:score_background_quality	3.478	+0.25	3.496	+0.28	3.301	0.693
116	score content enjoymenteiv_extra:score_content_enjoyment	4.836	+1.08	4.800	+0.97	4.507	0.303
117	score overall qualityeiv_extra:score_overall_quality	2.931	+0.55	2.919	+0.53	2.652	0.507
118	score speech qualityeiv_extra:score_speech_quality	1.765	-0.29	1.761	-0.32	1.808	0.146
Meta AudioBox Aesthetics Four AudioBox aesthetic teacher outputs. Expansions follow the official Meta model card.
119	Content enjoyment (CE)audiobox:CE	5.768	+0.95	6.166	+1.34	4.799	1.018
120	Content usefulness (CU)audiobox:CU	6.136	+0.49	6.475	+0.83	5.649	1.001
121	Production complexity (PC)audiobox:PC	1.852	-0.30	1.833	-0.31	2.331	1.617
122	Production quality (PQ)audiobox:PQ	7.279	+0.27	7.335	+0.33	7.044	0.879
Microsoft DNSMOS Seven DNSMOS teacher outputs: raw and calibrated SIG/BAK/OVRL estimates plus P.808 MOS.
123	Speech signal quality, rawdnsmos:SIG_raw	3.929	+0.04	3.977	+0.12	3.900	0.669
124	Background quality, rawdnsmos:BAK_raw	3.837	+0.56	4.034	+0.73	3.211	1.124
125	Overall quality, rawdnsmos:OVRL_raw	3.478	+0.48	3.630	+0.67	3.085	0.812
126	Speech signal quality, calibrateddnsmos:SIG	3.505	+0.03	3.525	+0.07	3.488	0.501
127	Background quality, calibrateddnsmos:BAK	3.760	+0.40	3.923	+0.58	3.389	0.928
128	Overall quality, calibrateddnsmos:OVRL	3.089	+0.41	3.188	+0.57	2.840	0.606
129	P.808 MOS estimatednsmos:P808_MOS	3.655	+0.47	3.602	+0.36	3.421	0.496
Vocal-burst count The regression target is log(1 + count). A separate table also reports count error after inverse transformation.
130	Vocal-burst count, log(1 + count)burst_count_log1p	0.030	+0.05	0.109	+0.17	0.000	0.647
VoiceCLAP attributes Sixty-one individual VoiceCLAP attribute teacher scores. The raw 768D VoiceCLAP embedding is stored in sidecars but is not a model output.
131	Affectionvoiceclap_attribute:Affection	1.063	+0.21	0.936	-0.02	0.947	0.554
132	Agevoiceclap_attribute:Age	3.230	+0.00	3.396	+0.31	3.229	0.547
133	Amusementvoiceclap_attribute:Amusement	0.418	+0.05	0.308	-0.15	0.392	0.572
134	Angervoiceclap_attribute:Anger	1.019	+0.05	0.818	-0.35	0.992	0.506
135	Arousalvoiceclap_attribute:Arousal	1.747	+0.53	1.748	+0.53	1.420	0.622
136	Astonishment Surprisevoiceclap_attribute:Astonishment_Surprise	0.911	+0.84	1.018	+1.06	0.509	0.479
137	Authenticityvoiceclap_attribute:Authenticity	3.245	+2.84	3.319	+3.29	2.770	0.167
138	Awevoiceclap_attribute:Awe	0.669	+0.50	0.833	+1.13	0.539	0.259
139	Background Noisevoiceclap_attribute:Background_Noise	0.424	-0.54	0.425	-0.54	0.567	0.264
140	Bitternessvoiceclap_attribute:Bitterness	0.544	-0.21	0.519	-0.31	0.592	0.236
141	Concentrationvoiceclap_attribute:Concentration	1.391	+0.33	1.477	+0.50	1.214	0.531
142	Confident vs. Hesitantvoiceclap_attribute:Confident_vs._Hesitant	1.069	+0.00	1.296	+0.48	1.069	0.468
143	Confusionvoiceclap_attribute:Confusion	0.805	+0.48	0.860	+0.65	0.643	0.334
144	Contemplationvoiceclap_attribute:Contemplation	0.863	+0.20	1.074	+0.73	0.780	0.406
145	Contemptvoiceclap_attribute:Contempt	0.592	-0.35	0.408	-0.89	0.709	0.339
146	Contentmentvoiceclap_attribute:Contentment	0.675	+0.28	0.654	+0.21	0.588	0.307
147	Disappointmentvoiceclap_attribute:Disappointment	0.968	+0.72	1.017	+0.88	0.760	0.291
148	Disgustvoiceclap_attribute:Disgust	0.692	+0.33	0.647	+0.11	0.625	0.207
149	Distressvoiceclap_attribute:Distress	1.186	+0.74	1.320	+1.12	0.927	0.350
150	Doubtvoiceclap_attribute:Doubt	0.575	+0.21	0.631	+0.51	0.535	0.188
151	Elationvoiceclap_attribute:Elation	0.600	+0.15	0.640	+0.25	0.539	0.397
152	Embarrassmentvoiceclap_attribute:Embarrassment	0.282	-0.08	0.344	+0.12	0.307	0.314
153	Emotional Numbnessvoiceclap_attribute:Emotional_Numbness	0.686	+0.08	0.566	-0.37	0.664	0.266
154	Fatigue Exhaustionvoiceclap_attribute:Fatigue_Exhaustion	0.364	-0.37	0.486	+0.09	0.462	0.261
155	Fearvoiceclap_attribute:Fear	1.009	+1.84	1.186	+2.68	0.618	0.212
156	Gendervoiceclap_attribute:Gender	1.458	+1.60	1.623	+1.76	-0.151	1.005
157	Helplessnessvoiceclap_attribute:Helplessness	1.036	+1.41	1.099	+1.64	0.658	0.268
158	High-Pitched vs. Low-Pitchedvoiceclap_attribute:High-Pitched_vs._Low-Pitched	1.650	-0.51	1.614	-0.60	1.840	0.375
159	Hope Enthusiasm Optimismvoiceclap_attribute:Hope_Enthusiasm_Optimism	1.021	+0.80	0.956	+0.63	0.705	0.396
160	Impatience and Irritabilityvoiceclap_attribute:Impatience_and_Irritability	0.882	-0.31	0.697	-0.66	1.052	0.541
161	Infatuationvoiceclap_attribute:Infatuation	0.697	+0.27	0.729	+0.37	0.608	0.332
162	Interestvoiceclap_attribute:Interest	2.069	+1.07	2.117	+1.18	1.598	0.440
163	Intoxication Altered States of Consciousnessvoiceclap_attribute:Intoxication_Altered_States_of_Consciousness	0.182	-0.69	0.078	-0.91	0.502	0.463
164	Jealousy & Envyvoiceclap_attribute:Jealousy_&_Envy	0.983	+1.88	1.020	+2.03	0.523	0.245
165	Longingvoiceclap_attribute:Longing	0.735	+0.90	0.877	+1.54	0.538	0.220
166	Malevolence Malicevoiceclap_attribute:Malevolence_Malice	0.781	-0.15	0.583	-0.72	0.833	0.346
167	Monotone vs. Expressivevoiceclap_attribute:Monotone_vs._Expressive	2.086	+0.52	2.123	+0.59	1.775	0.594
168	Painvoiceclap_attribute:Pain	0.650	+1.23	0.750	+1.69	0.381	0.218
169	Pleasure Ecstasyvoiceclap_attribute:Pleasure_Ecstasy	0.505	+0.01	0.513	+0.03	0.503	0.301
170	Pridevoiceclap_attribute:Pride	0.702	-0.22	0.595	-0.53	0.780	0.349
171	Recording Qualityvoiceclap_attribute:Recording_Quality	2.902	+1.80	2.912	+1.83	2.313	0.328
172	Reliefvoiceclap_attribute:Relief	1.583	+1.35	1.586	+1.35	1.025	0.415
173	Sadnessvoiceclap_attribute:Sadness	0.926	+0.56	1.006	+0.81	0.752	0.313
174	Serious vs. Humorousvoiceclap_attribute:Serious_vs._Humorous	0.422	-0.67	0.385	-0.74	0.803	0.568
175	Sexual Lustvoiceclap_attribute:Sexual_Lust	0.490	-0.35	0.444	-0.46	0.635	0.419
176	Shamevoiceclap_attribute:Shame	0.934	+1.44	1.072	+1.93	0.526	0.283
177	Soft vs. Harshvoiceclap_attribute:Soft_vs._Harsh	0.533	+1.04	0.571	+1.14	0.160	0.360
178	Sournessvoiceclap_attribute:Sourness	0.777	+0.25	0.645	-0.21	0.706	0.291
179	Submissive vs. Dominantvoiceclap_attribute:Submissive_vs._Dominant	0.394	-0.64	0.185	-1.22	0.623	0.359
180	Teasingvoiceclap_attribute:Teasing	0.577	+0.10	0.399	-0.37	0.540	0.379
181	Thankfulness Gratitudevoiceclap_attribute:Thankfulness_Gratitude	1.459	+0.14	1.331	-0.10	1.384	0.529
182	Triumphvoiceclap_attribute:Triumph	0.675	-0.11	0.668	-0.13	0.716	0.359
183	Valencevoiceclap_attribute:Valence	-0.097	-0.14	-0.001	+0.01	-0.007	0.635
184	Vulnerable vs. Emotionally Detachedvoiceclap_attribute:Vulnerable_vs._Emotionally_Detached	1.514	-0.22	1.329	-0.56	1.638	0.556
185	Warm vs. Coldvoiceclap_attribute:Warm_vs._Cold	-0.013	+0.13	0.094	+0.40	-0.066	0.400
186	durationvoiceclap_attribute:duration	13.466	+0.40	14.802	+0.61	10.914	6.354
187	score background qualityvoiceclap_attribute:score_background_quality	3.534	+0.58	3.519	+0.55	3.245	0.498
188	score content enjoymentvoiceclap_attribute:score_content_enjoyment	4.882	+1.54	4.866	+1.43	4.656	0.147
189	score overall qualityvoiceclap_attribute:score_overall_quality	2.847	+0.51	2.895	+0.63	2.635	0.412
190	score speech qualityvoiceclap_attribute:score_speech_quality	1.855	-0.52	1.841	-0.71	1.891	0.069
191	talking speedvoiceclap_attribute:talking_speed	11.101	+0.55	11.812	+0.74	9.028	3.756

All Orange embedding components

The cosine above is the meaningful vector-level comparison; component values have no standalone semantic label.

Timbre — all 128 vector components

Dimension	Tiny	Base	Orange teacher
0	0.0530	0.0218	-0.0332
1	0.0924	0.1012	0.0636
2	0.1033	0.1719	0.1589
3	-0.0705	-0.0800	-0.0786
4	-0.0776	-0.0686	-0.0729
5	-0.1394	-0.1175	-0.0981
6	0.1410	0.0544	-0.0193
7	0.2492	0.2917	0.2291
8	-0.0307	-0.0683	-0.0636
9	0.0500	0.0506	0.1155
10	-0.0721	-0.0751	0.0196
11	-0.0582	-0.0623	-0.0907
12	-0.0973	-0.0963	-0.0780
13	0.0037	-0.0014	-0.0387
14	0.1017	0.0811	0.1641
15	-0.0079	0.0756	0.0213
16	-0.0552	-0.0805	-0.0961
17	-0.0924	-0.0631	-0.0806
18	-0.0776	-0.0920	-0.0308
19	-0.0973	-0.0838	-0.0734
20	-0.0112	-0.0035	-0.0776
21	0.0307	0.0215	-0.0208
22	-0.0265	-0.0672	-0.0729
23	-0.0831	-0.0843	-0.0917
24	0.0098	-0.0049	0.0708
25	-0.0516	-0.0482	-0.0681
26	-0.0675	-0.0822	-0.0728
27	-0.0399	-0.0724	-0.0723
28	-0.0858	-0.1061	-0.0854
29	0.0935	0.1355	0.0883
30	0.0238	0.0318	-0.0351
31	-0.0924	-0.0702	-0.0303
32	0.2110	0.3069	0.2078
33	0.0413	-0.0143	-0.0780
34	-0.0853	-0.0713	-0.0695
35	0.1443	0.1534	0.0721
36	-0.0913	-0.0963	-0.0834
37	-0.0519	-0.0427	-0.0919
38	0.0732	0.0601	0.1635
39	-0.0612	-0.0465	-0.0782
40	0.0547	0.1366	0.0624
41	0.0148	-0.0156	-0.0667
42	-0.0956	-0.0990	-0.0782
43	-0.0536	0.0170	-0.0115
44	0.0710	0.0351	0.0094
45	0.0005	-0.0260	0.0310
46	0.1432	0.1774	0.0809
47	-0.1006	-0.0936	-0.0784
48	-0.0989	-0.0930	-0.0757
49	0.0228	-0.0490	-0.0476
50	0.0989	0.0887	0.0278
51	0.0056	0.0555	0.0831
52	-0.0522	-0.0952	-0.0881
53	-0.0434	-0.0392	-0.0791
54	-0.1022	-0.0985	-0.0868
55	0.0068	-0.0724	-0.0136
56	-0.0864	-0.0974	-0.0735
57	-0.0492	-0.0800	-0.0804
58	0.0008	-0.0066	0.1025
59	0.0607	0.1012	0.0822
60	0.0492	0.0789	0.0392
61	0.1350	0.1388	0.1570
62	0.0002	0.0463	0.0803
63	0.0782	0.0438	-0.0024
64	0.0484	0.0422	0.0058
65	-0.0749	-0.0784	-0.0633
66	0.1202	0.0443	0.1741
67	-0.0393	-0.0658	-0.0748
68	0.0924	0.1137	0.0712
69	0.0689	0.0465	0.0835
70	0.0366	0.0033	-0.0019
71	0.2754	0.2383	0.1801
72	-0.0174	-0.0284	0.0124
73	0.0686	0.0197	0.0377
74	-0.0541	0.0049	0.0735
75	0.2864	0.2340	0.1991
76	0.1273	0.0914	0.1700
77	-0.0721	-0.1045	-0.0709
78	-0.0754	-0.0650	-0.0690
79	-0.0072	-0.0212	-0.0673
80	-0.0721	-0.0501	-0.0066
81	0.2164	0.1377	0.1962
82	-0.0710	-0.0686	-0.0742
83	0.1388	0.1328	0.2120
84	-0.0147	-0.0642	-0.0962
85	0.0242	0.0476	0.0183
86	0.0896	-0.0292	0.0255
87	-0.0199	-0.0865	-0.0696
88	-0.0495	-0.0182	0.0177
89	-0.0967	-0.0547	-0.0712
90	0.0623	0.0283	0.0185
91	0.0150	-0.0226	-0.0047
92	-0.0568	-0.0087	-0.0041
93	-0.0443	-0.0525	-0.0385
94	0.0440	-0.0231	-0.0074
95	-0.0128	-0.0735	-0.0754
96	-0.0609	-0.0729	-0.0615
97	0.1563	0.1447	0.1787
98	-0.0287	-0.0403	-0.0289
99	0.1284	0.0656	0.1306
100	0.1383	0.0773	0.1915
101	-0.0283	-0.0212	-0.0750
102	-0.0240	0.0276	0.0391
103	-0.0743	-0.0985	-0.0818
104	0.0978	0.0729	-0.0008
105	-0.0675	-0.0833	-0.0748
106	0.0002	0.0286	0.0533
107	-0.0598	-0.0996	-0.0207
108	-0.1066	-0.0974	-0.0842
109	-0.0038	-0.0446	-0.0300
110	0.0514	0.0386	-0.0156
111	0.0301	0.0325	0.0983
112	-0.0329	-0.0555	-0.0765
113	-0.0269	-0.0729	-0.0464
114	0.0664	0.0465	0.0253
115	0.1727	0.1709	0.1705
116	0.1137	0.0441	0.0965
117	0.0063	0.0072	0.0312
118	-0.0754	-0.1001	-0.0755
119	0.0284	-0.0223	-0.0750
120	0.0858	0.1115	0.0989
121	0.0776	0.0242	0.0979
122	-0.0187	0.0099	-0.0434
123	0.0111	0.0316	0.0173
124	0.0279	0.0229	0.0771
125	-0.0902	-0.0683	-0.0773
126	-0.0579	-0.0838	-0.0668
127	0.1301	0.0604	0.0191

Identity — all 250 vector components

Dimension	Tiny	Base	Orange teacher
0	-0.0557	-0.0252	-0.0417
1	-0.0691	-0.0294	-0.0367
2	-0.0628	-0.0238	-0.0466
3	-0.0485	-0.0558	-0.0594
4	0.0242	0.0768	0.1180
5	0.0720	0.0871	-0.0396
6	0.1538	0.0979	0.0649
7	-0.0199	0.0381	0.1372
8	0.0826	0.0129	0.0047
9	-0.0076	0.0092	0.0628
10	-0.0775	0.0206	-0.0398
11	-0.0468	-0.0100	-0.0383
12	0.0723	0.0410	0.0373
13	0.1440	0.1957	0.2305
14	-0.0430	-0.0535	-0.0541
15	0.1733	0.1809	0.2202
16	0.0901	0.0629	-0.0236
17	-0.0422	0.0299	-0.0455
18	0.0528	0.0472	0.1243
19	-0.0697	-0.0922	-0.0602
20	0.0082	0.0404	0.0306
21	-0.0237	-0.0404	-0.0352
22	0.0577	0.0504	0.0889
23	-0.0663	-0.0762	-0.0367
24	-0.0231	-0.0040	-0.0324
25	-0.0714	-0.0052	-0.0271
26	0.0195	0.0606	-0.0418
27	-0.0313	0.0198	-0.0308
28	-0.0107	-0.0063	-0.0410
29	-0.0505	-0.0297	0.0467
30	-0.0130	0.0046	0.0660
31	-0.0271	0.0464	0.1030
32	0.1836	0.1457	0.0922
33	-0.0053	0.0543	-0.0340
34	0.1767	0.2071	0.1143
35	0.0271	0.0257	0.0381
36	0.0092	0.0277	-0.0091
37	-0.0519	-0.0248	-0.0262
38	-0.0405	-0.0279	-0.0490
39	-0.0471	-0.0256	-0.0565
40	-0.0060	0.0181	0.0226
41	-0.0283	0.0552	0.0198
42	0.0757	0.0489	0.0789
43	0.0752	0.0558	0.0315
44	-0.0204	0.0043	-0.0457
45	-0.0683	-0.0560	-0.0362
46	-0.0866	-0.1058	-0.0557
47	0.0337	-0.0242	-0.0479
48	0.0356	0.0242	0.0676
49	-0.0186	-0.0387	0.0234
50	0.0580	0.0825	0.0458
51	0.0288	0.0592	0.0548
52	-0.0337	0.0017	0.0010
53	-0.0390	-0.0211	-0.0367
54	0.0456	0.0384	0.0552
55	0.0522	0.0159	-0.0545
56	-0.0005	0.0034	0.0745
57	0.0597	0.0455	0.0667
58	-0.0450	0.0119	-0.0364
59	0.0219	0.0343	0.0726
60	0.0694	0.0606	0.0414
61	-0.0290	-0.0364	-0.0352
62	-0.0076	0.0734	-0.0333
63	0.0113	0.0153	0.0582
64	-0.0792	-0.0643	-0.0422
65	0.0832	0.0592	0.0820
66	0.0608	0.1235	0.1089
67	-0.0217	-0.0780	-0.0399
68	-0.0105	0.0074	-0.0275
69	0.0666	0.1218	0.1050
70	0.0122	0.0413	0.0713
71	-0.0217	-0.0250	-0.0397
72	-0.0786	-0.0566	-0.0420
73	0.0935	0.0629	0.0428
74	-0.0674	-0.0859	-0.0409
75	0.0677	0.0589	0.1045
76	0.1004	0.1235	0.1038
77	0.0101	0.0091	0.0337
78	0.0270	0.0100	-0.0208
79	-0.0534	-0.0734	-0.0406
80	-0.0387	-0.0356	0.0040
81	0.0153	0.0512	-0.0148
82	0.0089	-0.0226	-0.0364
83	-0.0545	-0.0053	-0.0337
84	0.0048	0.0329	0.0347
85	0.0275	0.0450	0.0341
86	0.0069	0.0163	-0.0362
87	-0.0565	-0.0213	-0.0323
88	0.0343	0.0634	0.1255
89	0.0248	0.0407	0.0742
90	0.0924	0.0142	-0.0219
91	0.0088	0.0334	0.0696
92	-0.0582	-0.0092	-0.0350
93	-0.0219	0.0185	-0.0212
94	-0.0379	0.0216	-0.0314
95	0.1584	0.2287	0.1869
96	0.0202	0.0572	0.0963
97	-0.0597	0.0435	0.1025
98	0.0160	0.1206	0.1429
99	0.0554	0.0444	0.0766
100	0.1308	0.1041	0.1364
101	0.0798	0.0671	0.0342
102	-0.0614	-0.0814	-0.0452
103	0.1153	0.0334	0.0392
104	-0.0448	-0.0586	-0.0528
105	-0.0689	-0.0669	-0.0527
106	-0.0110	-0.0165	-0.0312
107	0.0077	-0.0024	-0.0247
108	0.0110	-0.0084	-0.0301
109	-0.0482	0.0367	-0.0389
110	-0.0280	-0.0447	-0.0482
111	0.1595	0.2037	0.1934
112	-0.0108	0.0192	0.0255
113	-0.0763	-0.1349	-0.0690
114	-0.0689	-0.0164	-0.0565
115	-0.0792	-0.0045	-0.0287
116	0.0505	0.0252	0.0395
117	0.0336	0.0230	0.0498
118	0.0176	0.0023	0.0080
119	0.0614	0.0871	0.0740
120	-0.0350	0.0229	-0.0516
121	0.0234	0.0245	0.0266
122	-0.0363	-0.0180	-0.0382
123	0.0384	0.0289	0.0682
124	0.0706	0.0213	-0.0212
125	0.1417	0.1405	0.1068
126	0.1171	0.0563	0.0557
127	-0.0502	-0.0632	-0.0291
128	-0.0384	-0.0413	-0.0244
129	-0.0164	-0.0802	-0.0429
130	0.0861	0.1218	0.0638
131	-0.0436	-0.0498	-0.0354
132	0.0901	0.0506	0.1261
133	0.0821	0.1019	0.0125
134	0.0422	0.0444	-0.0202
135	-0.0531	0.0032	-0.0407
136	-0.0207	-0.0404	-0.0434
137	-0.0076	0.0432	0.0068
138	-0.0430	-0.0518	-0.0357
139	-0.0146	-0.0044	-0.0414
140	0.0214	0.0671	0.0554
141	0.0654	0.0657	0.0390
142	-0.0663	-0.0334	-0.0350
143	0.0018	0.0069	-0.0065
144	-0.0468	0.0038	-0.0422
145	-0.0763	-0.0646	-0.0515
146	0.0147	0.0316	0.0461
147	-0.0691	-0.0620	-0.0360
148	0.0021	0.0049	-0.0446
149	0.1561	0.1212	0.0786
150	-0.0029	-0.0015	-0.0399
151	-0.0373	-0.0064	0.0203
152	-0.0476	-0.0427	-0.0449
153	0.0729	0.0296	0.0041
154	0.0031	0.0370	-0.0169
155	0.1664	0.1309	0.1390
156	-0.0445	-0.0220	-0.0406
157	0.0924	0.1559	0.0764
158	0.0360	-0.0349	-0.0267
159	-0.0393	-0.0119	-0.0107
160	-0.0711	-0.0216	-0.0181
161	-0.0006	0.0535	-0.0234
162	-0.0585	-0.0313	-0.0464
163	-0.0597	-0.0084	-0.0451
164	-0.0208	-0.0090	-0.0356
165	-0.0384	0.0240	0.0927
166	0.0067	0.0063	-0.0294
167	0.0141	0.0364	-0.0307
168	0.0064	0.0260	0.0756
169	0.1027	0.0603	0.0165
170	-0.0732	-0.0569	-0.0246
171	0.0331	0.0506	0.0027
172	-0.0330	-0.0098	-0.0320
173	0.0740	0.0723	0.0842
174	-0.0482	-0.0370	0.0395
175	-0.0640	-0.0643	-0.0671
176	-0.0093	-0.0452	-0.0344
177	-0.0666	-0.0350	-0.0334
178	0.0042	0.1218	0.0072
179	-0.0465	0.0266	-0.0499
180	0.0032	0.0108	0.0001
181	0.0232	0.0025	-0.0001
182	-0.0516	-0.0415	-0.0350
183	-0.0468	-0.0637	-0.0817
184	-0.0062	0.0277	-0.0411
185	0.0251	0.0142	0.0508
186	-0.0221	-0.0179	-0.0149
187	0.0029	0.0475	0.1191
188	0.0241	0.0225	0.0202
189	-0.0089	0.0314	0.0074
190	0.0574	0.0438	-0.0078
191	0.0051	-0.0189	-0.0541
192	-0.0402	-0.0173	-0.0477
193	-0.0709	-0.0161	-0.0077
194	-0.0700	-0.0270	-0.0307
195	-0.0832	-0.0115	-0.0385
196	0.0329	0.0376	-0.0158
197	0.0347	0.0927	0.0428
198	-0.0416	-0.0814	-0.0391
199	-0.0551	-0.0945	-0.0445
200	-0.0855	-0.0415	-0.0087
201	0.0711	0.0910	0.1005
202	0.0453	0.0634	0.0111
203	0.0337	-0.0114	-0.0505
204	-0.0016	0.0802	0.0954
205	0.0146	0.0447	0.0835
206	0.1084	0.1155	0.0657
207	-0.0425	0.0156	0.0414
208	-0.0390	-0.0073	-0.0420
209	-0.0640	-0.0435	-0.0078
210	-0.0798	-0.0615	-0.0527
211	-0.0131	0.0062	0.0365
212	-0.0161	-0.0452	-0.0015
213	0.2284	0.1775	0.1530
214	-0.0037	0.0239	0.0811
215	-0.0113	0.0171	0.0621
216	0.1538	0.1457	0.1265
217	0.1033	0.0836	0.0891
218	-0.1274	-0.0495	-0.0470
219	-0.0740	-0.0152	-0.0527
220	0.0096	-0.0136	-0.0447
221	0.0085	0.0026	-0.0250
222	-0.0344	-0.0283	-0.0242
223	-0.0367	0.0580	0.0853
224	-0.0170	0.0140	0.0621
225	0.0393	-0.0006	0.0282
226	0.0889	0.0905	0.1033
227	-0.0184	-0.0255	0.0914
228	-0.0442	-0.0336	-0.0655
229	0.0288	0.0538	-0.0055
230	-0.0680	-0.0067	-0.0412
231	0.0402	0.0657	0.0155
232	-0.0031	-0.0326	-0.0245
233	0.1193	0.0666	0.0511
234	0.0930	0.0899	-0.0102
235	0.0459	0.0609	0.0372
236	-0.0290	-0.0307	-0.0348
237	-0.0184	-0.0266	-0.0413
238	0.0195	0.0360	0.0696
239	-0.0562	-0.0694	-0.0418
240	-0.0792	-0.0344	-0.0413
241	0.0390	0.0819	0.1503
242	-0.0775	-0.0802	-0.0596
243	-0.0471	-0.0728	-0.0520
244	0.1469	0.1866	0.1290
245	-0.0014	-0.0294	0.1075
246	-0.0230	-0.0188	-0.0328
247	0.0159	-0.0292	-0.0341
248	-0.0519	-0.0575	-0.0463
249	-0.0050	-0.0095	-0.0210

Source: HUMANENESS_SMALL_VOICE_IDENTITY_R1_R2_2026-10-02_anime_000.html · SHA-256 0bd8b4976ce0ed25…

e01GermanEmolia / Emilia

Emolia DE · DE_B00000_S00000_W000042

Natural speech · Original speech · 11.7 s

Und man arbeitet an Rabenkrieg. Das heißt, ich nehme an, die Zähne des Kamans werden dann der Anfang sein. Oder man baut vielleicht direkt die ganze Kampagne in einem nach, aber ich kann's mir fast nicht vorstellen.

Tiny Base · values are model estimates, not ground truth

Strongest emotions relative to training

Contemplation

z +1.72 / +1.80raw 1.11 / 1.16

Concentration

z +1.60 / +1.53raw 1.82 / 1.77

Doubt

z +1.11 / +1.43raw 0.52 / 0.67

Fatigue Exhaustion

z +0.46 / +0.97raw 0.28 / 0.55

Impatience and Irritability

z +0.72 / +0.89raw 0.66 / 0.78

Anger

z +0.76 / +0.86raw 0.47 / 0.53

Emotional Numbness

z +0.66 / +0.60raw 0.61 / 0.55

The center of each bar is the S9 teacher median. Positive z is to the right; negative z is to the left. Ranking uses z, not raw teacher units.

Strongest VoiceNet dimensions relative to training

Mixed resonance (R_MIXD)

z +2.23 / +2.37raw 3.31 / 3.43

Formal style (S_FORM)

z +1.57 / +1.72raw 2.80 / 2.95

Authoritative style (S_AUTH)

z +1.36 / +1.50raw 2.50 / 2.66

Teacher or didactic style (S_TECH)

z +1.20 / +1.48raw 2.12 / 2.46

Newsreader style (S_NEWS)

z +1.18 / +1.47raw 1.08 / 1.24

Throat resonance (R_THRT)

z +1.38 / +1.35raw 3.18 / 3.16

Fullness (FULL)

z +1.30 / +1.34raw 2.93 / 2.97

All 57 VoiceNet predictions, including raw units, are in the full table below. These seven are ranked by z; the top values may differ from the strongest raw dimensions.

Voice, speed and quality scores in context

Genuineness (0–6)z +0.60 / +0.54raw 3.31 / 3.21

Vocal-burst blend (0–10)z -2.21 / -2.24raw 0.63 / 0.55

Content enjoyment (CE)z +0.26 / +0.54raw 5.07 / 5.35

Production quality (PQ)z -0.18 / +0.01raw 6.88 / 7.05

Speech signal quality, calibratedz +0.13 / +0.03raw 3.55 / 3.50

Background quality, calibratedz +0.45 / +0.47raw 3.80 / 3.83

Overall quality, calibratedz +0.48 / +0.52raw 3.13 / 3.16

P.808 MOS estimatez +0.78 / +0.96raw 3.81 / 3.90

score content enjoymentz +0.61 / +0.77raw 4.69 / 4.74

score overall qualityz +0.58 / +0.65raw 2.95 / 2.98

Background Noisez -0.50 / -0.84raw 0.68 / 0.58

Tempo (TEMP)z +0.06 / +0.01raw 2.19 / 2.12

Arousal (AROU)z +0.17 / +0.12raw 2.55 / 2.50

Valence (VALN)z +0.38 / +0.39raw 2.75 / 2.76

Recording quality (RCQL)z +0.25 / +0.13raw 2.97 / 2.87

Background noise (BKGN)z +0.35 / +0.48raw 2.97 / 3.07

talking speedz +2.31 / +1.96raw 17.69 / 16.37

Characters per second (CPS): 18.41 raw · z +2.50

Orange speaker embedding reconstruction

Cosine against Orange on this same clip (higher means closer to that teacher vector):

Embedding	Tiny	Base
Timbre · 128D	0.896	0.900
Identity · 250D	0.824	0.844

Vocal-burst regions

Tiny

Base

0 s11.7 s

Verified burst intervals are unavailable for this clip.

Tiny: 1 regions, count-head estimate 1.08; Base: 1 regions, count-head estimate 0.97.

Exact predicted start and end times

Model	Region	Start (s)	End (s)	Duration (s)
Tiny	1	4.94	5.28	0.34
Base	1	4.94	5.26	0.32

All 192 score slots · raw and z values

#	Target	Tiny raw	Tiny z	Base raw	Base z	Train median	Train SD
Emotion scores Forty clip-level Empathic Insight emotion teacher outputs. Each row evaluates one named emotion score.
0	Affectionemo_Affection	-0.003	-0.02	0.051	+0.08	0.007	0.570
1	Amusementemo_Amusement	0.090	+0.10	0.064	+0.07	-0.001	0.885
2	Angeremo_Anger	0.467	+0.76	0.531	+0.86	0.004	0.613
3	Astonishment Surpriseemo_Astonishment_Surprise	0.031	+0.04	-0.013	-0.03	0.005	0.572
4	Aweemo_Awe	0.023	+0.05	-0.004	-0.01	0.000	0.427
5	Bitternessemo_Bitterness	0.185	+0.41	0.220	+0.50	0.013	0.415
6	Concentrationemo_Concentration	1.824	+1.60	1.772	+1.53	0.634	0.741
7	Confusionemo_Confusion	0.336	+0.62	0.219	+0.40	0.001	0.540
8	Contemplationemo_Contemplation	1.108	+1.72	1.159	+1.80	0.082	0.598
9	Contemptemo_Contempt	0.080	+0.17	0.077	+0.17	-0.000	0.464
10	Contentmentemo_Contentment	0.241	+0.47	0.192	+0.37	0.000	0.514
11	Disappointmentemo_Disappointment	0.214	+0.31	0.424	+0.61	0.000	0.700
12	Disgustemo_Disgust	0.177	+0.35	0.188	+0.37	0.007	0.489
13	Distressemo_Distress	0.098	+0.12	0.186	+0.23	0.000	0.821
14	Doubtemo_Doubt	0.523	+1.11	0.671	+1.43	0.006	0.466
15	Elationemo_Elation	0.000	-0.02	0.037	+0.03	0.012	0.728
16	Embarrassmentemo_Embarrassment	-0.013	-0.13	-0.032	-0.17	0.043	0.430
17	Emotional Numbnessemo_Emotional_Numbness	0.612	+0.66	0.552	+0.60	0.004	0.917
18	Fatigue Exhaustionemo_Fatigue_Exhaustion	0.277	+0.46	0.550	+0.97	0.028	0.539
19	Fearemo_Fear	0.131	+0.19	0.146	+0.22	0.015	0.610
20	Helplessnessemo_Helplessness	0.121	+0.18	0.235	+0.34	-0.004	0.696
21	Hope Enthusiasm Optimismemo_Hope_Enthusiasm_Optimism	0.039	-0.10	0.080	-0.05	0.117	0.760
22	Impatience and Irritabilityemo_Impatience_and_Irritability	0.657	+0.72	0.779	+0.89	0.149	0.705
23	Infatuationemo_Infatuation	-0.035	-0.04	-0.021	-0.01	-0.015	0.533
24	Interestemo_Interest	2.124	+0.59	2.063	+0.52	1.589	0.907
25	Intoxication Altered States of Consciousnessemo_Intoxication_Altered_States_of_Consciousness	-0.052	-0.05	-0.035	-0.02	-0.025	0.559
26	Jealousy and Envyemo_Jealousy_and_Envy	0.091	+0.07	0.064	+0.01	0.059	0.442
27	Longingemo_Longing	0.147	+0.10	0.344	+0.41	0.087	0.632
28	Malevolence Maliceemo_Malevolence_Malice	0.064	+0.02	0.051	-0.01	0.055	0.534
29	Painemo_Pain	0.010	+0.02	0.012	+0.02	-0.002	0.579
30	Pleasure Ecstasyemo_Pleasure_Ecstasy	0.020	+0.01	0.004	-0.02	0.017	0.614
31	Prideemo_Pride	-0.012	-0.03	0.001	-0.00	0.002	0.509
32	Reliefemo_Relief	0.026	-0.01	0.036	+0.00	0.033	0.681
33	Sadnessemo_Sadness	0.107	+0.14	0.271	+0.36	0.000	0.759
34	Sexual Lustemo_Sexual_Lust	-0.019	-0.10	-0.037	-0.13	0.030	0.494
35	Shameemo_Shame	0.002	-0.02	0.000	-0.02	0.013	0.510
36	Sournessemo_Sourness	0.199	+0.46	0.206	+0.48	-0.005	0.439
37	Teasingemo_Teasing	0.020	+0.04	-0.005	-0.01	0.000	0.545
38	Thankfulness Gratitudeemo_Thankfulness_Gratitude	-0.015	-0.08	0.031	-0.01	0.041	0.697
39	Triumphemo_Triumph	-0.036	-0.06	-0.034	-0.05	-0.007	0.521
VoiceNet dimensions Fifty-seven VoiceNet voice, delivery, style, and recording dimensions. Codes are expanded in the target column.
40	Perceived voice age (AGEV)vn_AGEV_reg	3.289	+0.25	3.346	+0.29	2.984	1.238
41	Arousal (AROU)vn_AROU_reg	2.554	+0.17	2.499	+0.12	2.359	1.147
42	Arousal shift (ARSH)vn_ARSH_reg	2.613	+0.04	2.535	-0.05	2.580	0.867
43	Vocal attack (ATCK)vn_ATCK_reg	2.125	-0.03	2.204	+0.03	2.162	1.295
44	Background noise (BKGN)vn_BKGN_reg	2.971	+0.35	3.066	+0.48	2.703	0.761
45	Brightness (BRGT)vn_BRGT_reg	2.622	+0.78	2.496	+0.62	1.991	0.813
46	Speech chunking (CHNK)vn_CHNK_reg	3.060	+0.98	2.992	+0.92	1.847	1.239
47	Articulation clarity (CLRT)vn_CLRT_reg	1.952	-0.07	2.198	+0.19	2.018	0.945
48	Cognitive load (COGL)vn_COGL_reg	2.277	+0.17	2.343	+0.23	2.094	1.061
49	Dynamic arc (DARC)vn_DARC_reg	1.741	+0.09	1.732	+0.08	1.615	1.380
50	Disfluency (DFLU)vn_DFLU_reg	3.309	+0.69	3.249	+0.64	2.488	1.184
51	Emphasis (EMPH)vn_EMPH_reg	2.997	+0.26	3.055	+0.29	2.607	1.524
52	Esthetics (ESTH)vn_ESTH_reg	2.824	+0.54	2.988	+0.75	2.402	0.782
53	Content appropriateness (EXPL)vn_EXPL_reg	0.123	+0.12	0.115	+0.09	0.086	0.322
54	Focus (FOCS)vn_FOCS_reg	2.006	-0.31	2.011	-0.30	2.344	1.102
55	Fullness (FULL)vn_FULL_reg	2.931	+1.30	2.973	+1.34	1.778	0.889
56	Perceived gender (GEND)vn_GEND_reg	3.501	-0.35	3.406	-0.41	4.055	1.588
57	Harmonicity (HARM)vn_HARM_reg	2.722	+0.29	2.758	+0.33	2.480	0.836
58	Metallic character (METL)vn_METL_reg	1.490	-0.14	1.508	-0.12	1.621	0.958
59	Pitch range (RANG)vn_RANG_reg	2.380	-0.60	2.279	-0.71	2.914	0.897
60	Recording quality (RCQL)vn_RCQL_reg	2.973	+0.25	2.866	+0.13	2.754	0.888
61	Vocal register (REGS)vn_REGS_reg	0.588	-0.48	0.544	-0.52	1.198	1.268
62	Respiration (RESP)vn_RESP_reg	2.044	-0.60	2.019	-0.63	2.680	1.056
63	Roughness (ROUG)vn_ROUG_reg	1.627	-0.46	1.558	-0.54	2.033	0.887
64	Chest resonance (R_CHST)vn_R_CHST_reg	2.157	+0.03	2.178	+0.05	2.135	0.844
65	Head resonance (R_HEAD)vn_R_HEAD_reg	2.436	+0.35	2.415	+0.32	2.148	0.822
66	Mask resonance (R_MASK)vn_R_MASK_reg	2.387	+0.48	2.423	+0.51	1.908	1.005
67	Mixed resonance (R_MIXD)vn_R_MIXD_reg	3.312	+2.23	3.429	+2.37	1.436	0.841
68	Nasal resonance (R_NASL)vn_R_NASL_reg	2.146	-0.62	2.103	-0.66	2.791	1.047
69	Oral resonance (R_ORAL)vn_R_ORAL_reg	2.963	+1.05	2.957	+1.04	2.184	0.741
70	Throat resonance (R_THRT)vn_R_THRT_reg	3.182	+1.38	3.156	+1.35	2.070	0.803
71	Smoothness (SMTH)vn_SMTH_reg	3.209	+0.98	3.200	+0.97	2.143	1.093
72	Stance (STNC)vn_STNC_reg	2.278	-0.31	2.440	-0.17	2.633	1.137
73	Speech structure (STRU)vn_STRU_reg	2.892	+0.79	3.023	+0.92	2.137	0.958
74	ASMR style (S_ASMR)vn_S_ASMR_reg	1.337	-0.02	1.318	-0.04	1.370	1.411
75	Authoritative style (S_AUTH)vn_S_AUTH_reg	2.502	+1.36	2.656	+1.50	1.088	1.043
76	Cartoonish style (S_CART)vn_S_CART_reg	-0.802	-1.69	-0.759	-1.66	1.560	1.401
77	Casual style (S_CASU)vn_S_CASU_reg	3.337	-0.36	3.304	-0.38	3.793	1.278
78	Conversational style (S_CONV)vn_S_CONV_reg	2.714	+0.09	2.570	-0.02	2.594	1.318
79	Dramatic style (S_DRAM)vn_S_DRAM_reg	1.587	-0.99	1.604	-0.97	2.721	1.148
80	Formal style (S_FORM)vn_S_FORM_reg	2.797	+1.57	2.947	+1.72	1.195	1.021
81	Monologue style (S_MONO)vn_S_MONO_reg	3.968	+0.89	3.894	+0.83	2.824	1.284
82	Narrator style (S_NARR)vn_S_NARR_reg	2.854	+1.07	2.877	+1.09	1.307	1.446
83	Newsreader style (S_NEWS)vn_S_NEWS_reg	1.077	+1.18	1.241	+1.47	0.408	0.568
84	Playful style (S_PLAY)vn_S_PLAY_reg	0.816	-1.17	0.572	-1.35	2.352	1.315
85	Ranting or angry style (S_RANT)vn_S_RANT_reg	-0.938	-1.67	-1.197	-1.87	1.213	1.289
86	Storytelling style (S_STRY)vn_S_STRY_reg	1.718	-0.56	1.569	-0.67	2.480	1.366
87	Teacher or didactic style (S_TECH)vn_S_TECH_reg	2.118	+1.20	2.460	+1.48	0.646	1.227
88	Whispered talking style (S_WHIS)vn_S_WHIS_reg	1.578	-0.01	1.802	+0.13	1.597	1.618
89	Tempo (TEMP)vn_TEMP_reg	2.191	+0.06	2.125	+0.01	2.117	1.190
90	Tension (TENS)vn_TENS_reg	1.051	-0.60	1.182	-0.44	1.559	0.852
91	Valence (VALN)vn_VALN_reg	2.751	+0.38	2.764	+0.39	2.328	1.118
92	Valence shift (VALS)vn_VALS_reg	2.873	+0.33	2.809	+0.27	2.518	1.079
93	Velocity flux (VFLX)vn_VFLX_reg	1.547	-0.59	1.632	-0.52	2.256	1.208
94	Volatility (VOLT)vn_VOLT_reg	1.266	-1.49	1.192	-1.57	2.586	0.886
95	Vulnerability (VULN)vn_VULN_reg	2.338	-0.32	2.307	-0.35	2.648	0.984
96	Warmth (WARM)vn_WARM_reg	2.264	-0.35	2.213	-0.40	2.578	0.909
Genuineness, blend, and legacy quality Genuineness and vocal-burst blend are predicted. R_quality has Ladder training labels but no valid P3 test labels.
97	Genuineness (0–6)genuineness_0_6	3.309	+0.60	3.211	+0.54	2.332	1.621
98	Vocal-burst blend (0–10)blend_0_10	0.635	-2.21	0.550	-2.24	6.676	2.738
99	Legacy R_quality (no P3 test labels)R_quality	0.627	-1.39	0.593	-1.49	1.095	0.338
Empathic Insight Plus extra scores Nineteen additional clip-level teacher scores, including background noise and content enjoyment.
100	Ageeiv_extra:Age	3.375	+0.42	3.383	+0.45	3.250	0.293
101	Arousaleiv_extra:Arousal	1.033	-0.59	1.108	-0.42	1.289	0.435
102	Authenticityeiv_extra:Authenticity	2.727	+0.39	2.802	+0.88	2.667	0.153
103	Background Noiseeiv_extra:Background_Noise	0.676	-0.50	0.584	-0.84	0.808	0.264
104	Confident vs. Hesitanteiv_extra:Confident_vs._Hesitant	1.311	+0.90	1.184	+0.48	1.040	0.303
105	Gendereiv_extra:Gender	-1.044	-0.42	-1.017	-0.40	-0.621	0.999
106	High-Pitched vs. Low-Pitchedeiv_extra:High-Pitched_vs._Low-Pitched	2.118	+1.16	2.225	+1.59	1.827	0.250
107	Monotone vs. Expressiveeiv_extra:Monotone_vs._Expressive	1.824	-0.07	1.715	-0.31	1.859	0.470
108	Recording Qualityeiv_extra:Recording_Quality	2.186	+0.13	2.294	+0.45	2.144	0.332
109	Serious vs. Humorouseiv_extra:Serious_vs._Humorous	0.966	+0.11	0.956	+0.08	0.929	0.340
110	Soft vs. Harsheiv_extra:Soft_vs._Harsh	0.091	-0.59	0.125	-0.49	0.281	0.320
111	Submissive vs. Dominanteiv_extra:Submissive_vs._Dominant	0.387	+0.04	0.507	+0.41	0.376	0.324
112	Valenceeiv_extra:Valence	-0.009	-0.04	0.027	+0.06	0.005	0.380
113	Vulnerable vs. Emotionally Detachedeiv_extra:Vulnerable_vs._Emotionally_Detached	2.089	+0.86	2.208	+1.13	1.715	0.437
114	Warm vs. Coldeiv_extra:Warm_vs._Cold	-0.031	-0.27	-0.056	-0.36	0.051	0.300
115	score background qualityeiv_extra:score_background_quality	3.561	+0.38	3.616	+0.45	3.301	0.693
116	score content enjoymenteiv_extra:score_content_enjoyment	4.691	+0.61	4.741	+0.77	4.507	0.303
117	score overall qualityeiv_extra:score_overall_quality	2.947	+0.58	2.982	+0.65	2.652	0.507
118	score speech qualityeiv_extra:score_speech_quality	1.847	+0.27	1.874	+0.46	1.808	0.146
Meta AudioBox Aesthetics Four AudioBox aesthetic teacher outputs. Expansions follow the official Meta model card.
119	Content enjoyment (CE)audiobox:CE	5.068	+0.26	5.347	+0.54	4.799	1.018
120	Content usefulness (CU)audiobox:CU	5.694	+0.05	5.654	+0.01	5.649	1.001
121	Production complexity (PC)audiobox:PC	1.770	-0.35	1.845	-0.30	2.331	1.617
122	Production quality (PQ)audiobox:PQ	6.883	-0.18	7.054	+0.01	7.044	0.879
Microsoft DNSMOS Seven DNSMOS teacher outputs: raw and calibrated SIG/BAK/OVRL estimates plus P.808 MOS.
123	Speech signal quality, rawdnsmos:SIG_raw	4.025	+0.19	3.960	+0.09	3.900	0.669
124	Background quality, rawdnsmos:BAK_raw	3.907	+0.62	3.973	+0.68	3.211	1.124
125	Overall quality, rawdnsmos:OVRL_raw	3.538	+0.56	3.599	+0.63	3.085	0.812
126	Speech signal quality, calibrateddnsmos:SIG	3.555	+0.13	3.502	+0.03	3.488	0.501
127	Background quality, calibrateddnsmos:BAK	3.803	+0.45	3.825	+0.47	3.389	0.928
128	Overall quality, calibrateddnsmos:OVRL	3.131	+0.48	3.155	+0.52	2.840	0.606
129	P.808 MOS estimatednsmos:P808_MOS	3.810	+0.78	3.899	+0.96	3.421	0.496
Vocal-burst count The regression target is log(1 + count). A separate table also reports count error after inverse transformation.
130	Vocal-burst count, log(1 + count)burst_count_log1p	0.732	+1.13	0.676	+1.04	0.000	0.647
VoiceCLAP attributes Sixty-one individual VoiceCLAP attribute teacher scores. The raw 768D VoiceCLAP embedding is stored in sidecars but is not a model output.
131	Affectionvoiceclap_attribute:Affection	0.414	-0.96	0.344	-1.09	0.947	0.554
132	Agevoiceclap_attribute:Age	3.241	+0.02	3.396	+0.31	3.229	0.547
133	Amusementvoiceclap_attribute:Amusement	0.086	-0.54	-0.069	-0.81	0.392	0.572
134	Angervoiceclap_attribute:Anger	0.678	-0.62	0.525	-0.92	0.992	0.506
135	Arousalvoiceclap_attribute:Arousal	1.078	-0.55	0.866	-0.89	1.420	0.622
136	Astonishment Surprisevoiceclap_attribute:Astonishment_Surprise	-0.041	-1.15	0.056	-0.94	0.509	0.479
137	Authenticityvoiceclap_attribute:Authenticity	2.682	-0.53	2.741	-0.18	2.770	0.167
138	Awevoiceclap_attribute:Awe	-0.008	-2.11	0.168	-1.43	0.539	0.259
139	Background Noisevoiceclap_attribute:Background_Noise	0.431	-0.52	0.284	-1.07	0.567	0.264
140	Bitternessvoiceclap_attribute:Bitterness	0.365	-0.97	0.382	-0.90	0.592	0.236
141	Concentrationvoiceclap_attribute:Concentration	2.076	+1.62	2.093	+1.65	1.214	0.531
142	Confident vs. Hesitantvoiceclap_attribute:Confident_vs._Hesitant	1.471	+0.86	1.125	+0.12	1.069	0.468
143	Confusionvoiceclap_attribute:Confusion	0.688	+0.13	0.532	-0.33	0.643	0.334
144	Contemplationvoiceclap_attribute:Contemplation	1.532	+1.85	1.510	+1.80	0.780	0.406
145	Contemptvoiceclap_attribute:Contempt	0.375	-0.99	0.353	-1.05	0.709	0.339
146	Contentmentvoiceclap_attribute:Contentment	0.318	-0.88	0.278	-1.01	0.588	0.307
147	Disappointmentvoiceclap_attribute:Disappointment	0.454	-1.05	0.563	-0.68	0.760	0.291
148	Disgustvoiceclap_attribute:Disgust	0.345	-1.35	0.322	-1.46	0.625	0.207
149	Distressvoiceclap_attribute:Distress	0.620	-0.88	0.319	-1.74	0.927	0.350
150	Doubtvoiceclap_attribute:Doubt	0.635	+0.53	0.629	+0.50	0.535	0.188
151	Elationvoiceclap_attribute:Elation	0.237	-0.76	0.078	-1.16	0.539	0.397
152	Embarrassmentvoiceclap_attribute:Embarrassment	0.078	-0.73	0.023	-0.90	0.307	0.314
153	Emotional Numbnessvoiceclap_attribute:Emotional_Numbness	0.897	+0.87	0.773	+0.41	0.664	0.266
154	Fatigue Exhaustionvoiceclap_attribute:Fatigue_Exhaustion	0.582	+0.46	0.501	+0.15	0.462	0.261
155	Fearvoiceclap_attribute:Fear	0.596	-0.10	0.339	-1.32	0.618	0.212
156	Gendervoiceclap_attribute:Gender	-1.038	-0.88	-1.171	-1.01	-0.151	1.005
157	Helplessnessvoiceclap_attribute:Helplessness	0.598	-0.22	0.345	-1.17	0.658	0.268
158	High-Pitched vs. Low-Pitchedvoiceclap_attribute:High-Pitched_vs._Low-Pitched	2.138	+0.79	2.278	+1.17	1.840	0.375
159	Hope Enthusiasm Optimismvoiceclap_attribute:Hope_Enthusiasm_Optimism	0.364	-0.86	0.321	-0.97	0.705	0.396
160	Impatience and Irritabilityvoiceclap_attribute:Impatience_and_Irritability	0.510	-1.00	0.498	-1.02	1.052	0.541
161	Infatuationvoiceclap_attribute:Infatuation	0.274	-1.01	0.126	-1.45	0.608	0.332
162	Interestvoiceclap_attribute:Interest	1.997	+0.91	2.028	+0.98	1.598	0.440
163	Intoxication Altered States of Consciousnessvoiceclap_attribute:Intoxication_Altered_States_of_Consciousness	-0.063	-1.22	0.042	-0.99	0.502	0.463
164	Jealousy & Envyvoiceclap_attribute:Jealousy_&_Envy	0.207	-1.29	0.162	-1.47	0.523	0.245
165	Longingvoiceclap_attribute:Longing	0.510	-0.12	0.444	-0.43	0.538	0.220
166	Malevolence Malicevoiceclap_attribute:Malevolence_Malice	0.438	-1.14	0.192	-1.85	0.833	0.346
167	Monotone vs. Expressivevoiceclap_attribute:Monotone_vs._Expressive	1.514	-0.44	1.253	-0.88	1.775	0.594
168	Painvoiceclap_attribute:Pain	0.254	-0.58	0.190	-0.88	0.381	0.218
169	Pleasure Ecstasyvoiceclap_attribute:Pleasure_Ecstasy	0.048	-1.51	-0.030	-1.77	0.503	0.301
170	Pridevoiceclap_attribute:Pride	0.470	-0.89	0.245	-1.53	0.780	0.349
171	Recording Qualityvoiceclap_attribute:Recording_Quality	2.250	-0.19	2.386	+0.22	2.313	0.328
172	Reliefvoiceclap_attribute:Relief	0.636	-0.94	0.488	-1.29	1.025	0.415
173	Sadnessvoiceclap_attribute:Sadness	0.685	-0.21	0.486	-0.85	0.752	0.313
174	Serious vs. Humorousvoiceclap_attribute:Serious_vs._Humorous	0.627	-0.31	0.529	-0.48	0.803	0.568
175	Sexual Lustvoiceclap_attribute:Sexual_Lust	0.226	-0.98	-0.045	-1.62	0.635	0.419
176	Shamevoiceclap_attribute:Shame	0.583	+0.20	0.285	-0.85	0.526	0.283
177	Soft vs. Harshvoiceclap_attribute:Soft_vs._Harsh	0.036	-0.34	-0.024	-0.51	0.160	0.360
178	Sournessvoiceclap_attribute:Sourness	0.367	-1.17	0.324	-1.31	0.706	0.291
179	Submissive vs. Dominantvoiceclap_attribute:Submissive_vs._Dominant	0.462	-0.45	0.411	-0.59	0.623	0.359
180	Teasingvoiceclap_attribute:Teasing	0.155	-1.02	0.149	-1.03	0.540	0.379
181	Thankfulness Gratitudevoiceclap_attribute:Thankfulness_Gratitude	0.883	-0.95	0.548	-1.58	1.384	0.529
182	Triumphvoiceclap_attribute:Triumph	0.302	-1.15	0.330	-1.07	0.716	0.359
183	Valencevoiceclap_attribute:Valence	-0.184	-0.28	-0.022	-0.02	-0.007	0.635
184	Vulnerable vs. Emotionally Detachedvoiceclap_attribute:Vulnerable_vs._Emotionally_Detached	2.369	+1.31	2.469	+1.49	1.638	0.556
185	Warm vs. Coldvoiceclap_attribute:Warm_vs._Cold	-0.116	-0.13	-0.031	+0.09	-0.066	0.400
186	durationvoiceclap_attribute:duration	11.267	+0.06	12.371	+0.23	10.914	6.354
187	score background qualityvoiceclap_attribute:score_background_quality	3.608	+0.73	3.517	+0.55	3.245	0.498
188	score content enjoymentvoiceclap_attribute:score_content_enjoyment	4.680	+0.17	4.747	+0.62	4.656	0.147
189	score overall qualityvoiceclap_attribute:score_overall_quality	2.969	+0.81	2.948	+0.76	2.635	0.412
190	score speech qualityvoiceclap_attribute:score_speech_quality	1.938	+0.68	1.928	+0.53	1.891	0.069
191	talking speedvoiceclap_attribute:talking_speed	17.690	+2.31	16.371	+1.96	9.028	3.756

All Orange embedding components

The cosine above is the meaningful vector-level comparison; component values have no standalone semantic label.

Timbre — all 128 vector components

Dimension	Tiny	Base	Orange teacher
0	0.1045	0.0970	0.0977
1	-0.0435	-0.0225	-0.0852
2	-0.0829	-0.0832	-0.1006
3	0.0807	0.1109	0.0690
4	0.1244	0.0943	0.0501
5	-0.0676	-0.0773	-0.1185
6	-0.1059	-0.1153	-0.0930
7	0.1920	0.1985	0.1698
8	0.1568	0.1006	0.1071
9	0.0834	0.0832	0.1127
10	0.0789	0.0769	0.1265
11	0.0653	0.0805	0.1608
12	-0.0372	-0.0512	-0.0331
13	-0.0928	-0.0849	-0.1013
14	-0.0229	-0.0254	-0.0290
15	0.1820	0.1994	0.1032
16	-0.1613	-0.1395	-0.1271
17	0.1478	0.1024	0.1161
18	-0.0182	-0.0050	-0.0201
19	0.0329	-0.0158	-0.0327
20	0.0946	0.0894	-0.0008
21	0.0358	0.0186	0.0123
22	-0.1050	-0.0903	-0.0965
23	-0.0475	0.0139	0.0411
24	-0.0061	-0.0449	-0.0183
25	-0.0295	-0.0288	-0.0406
26	-0.0982	-0.1252	-0.0963
27	-0.0137	-0.0653	-0.0552
28	-0.0179	-0.0353	-0.0520
29	0.0575	0.0742	0.0665
30	0.0775	0.0782	0.1683
31	-0.0545	-0.0427	-0.0947
32	0.0757	0.0653	0.1501
33	-0.0401	-0.0098	-0.0271
34	-0.0075	-0.0353	-0.0329
35	0.1163	0.1207	0.0942
36	-0.1361	-0.1225	-0.1103
37	-0.0428	-0.0434	-0.0889
38	-0.0847	-0.0452	-0.0847
39	-0.0388	-0.0693	-0.0594
40	0.1478	0.1243	0.1368
41	-0.0367	-0.0662	-0.0217
42	0.0058	-0.0478	-0.0066
43	0.1009	0.0899	0.1175
44	0.2055	0.1931	0.1456
45	-0.1163	-0.1127	-0.0357
46	0.0829	0.1037	0.0967
47	-0.0996	-0.1144	-0.1038
48	-0.0123	-0.0168	-0.0353
49	-0.0502	-0.0532	-0.0509
50	-0.0595	-0.0849	-0.0714
51	-0.0838	-0.0639	-0.0755
52	0.0428	0.0890	0.0232
53	-0.0518	-0.0697	-0.0402
54	-0.0960	-0.0617	-0.0787
55	-0.0748	-0.0675	-0.0987
56	0.0351	0.0329	0.0170
57	-0.0451	-0.0791	-0.1125
58	0.0271	0.0429	0.0978
59	-0.0676	-0.0532	-0.1030
60	-0.0969	-0.1296	-0.0989
61	0.1902	0.2137	0.2139
62	-0.0489	-0.0402	-0.0358
63	0.0667	0.0617	0.0360
64	-0.1099	-0.1180	-0.0859
65	-0.0568	-0.0608	-0.0837
66	-0.1397	-0.1350	-0.1420
67	-0.1023	-0.0894	-0.0946
68	0.1199	0.1341	0.1384
69	-0.1072	-0.0939	-0.0940
70	0.1911	0.1368	0.1465
71	-0.0534	-0.0469	-0.0798
72	-0.0771	-0.0581	-0.0993
73	-0.0453	-0.1144	-0.0445
74	-0.0453	-0.0249	-0.1121
75	0.0514	0.0559	0.0593
76	-0.0462	-0.0382	-0.0222
77	-0.0178	0.0030	-0.0938
78	0.0462	0.0487	0.0571
79	-0.0784	-0.0791	-0.0890
80	0.0008	0.0274	0.0168
81	-0.0978	-0.1015	-0.0930
82	-0.0964	-0.1051	-0.0982
83	0.0834	0.0429	0.0140
84	-0.0743	-0.1006	-0.0770
85	-0.0516	-0.0572	-0.0680
86	0.0924	0.1359	-0.0167
87	-0.0514	-0.0552	-0.0195
88	0.1460	0.1484	0.1113
89	-0.0037	0.0101	-0.0194
90	-0.1460	-0.1279	-0.1113
91	0.0043	0.0249	-0.0008
92	-0.0694	-0.0492	-0.0930
93	0.0680	0.0494	0.0829
94	-0.0053	-0.0382	0.0685
95	-0.1199	-0.1153	-0.1102
96	-0.1325	-0.1493	-0.1349
97	-0.0237	-0.0326	-0.0224
98	0.0852	0.0590	0.0160
99	-0.0229	-0.0440	0.0564
100	-0.0543	-0.1073	-0.0539
101	-0.0128	0.0042	0.0131
102	0.0365	0.0075	0.0126
103	-0.0888	-0.0952	-0.1083
104	-0.0561	-0.0796	-0.0701
105	0.0027	-0.0393	-0.0339
106	-0.0170	-0.0324	-0.0087
107	-0.0213	-0.0121	-0.0119
108	0.1117	0.0773	0.0565
109	0.0304	0.0088	0.0157
110	-0.0108	0.0331	0.0452
111	-0.1140	-0.1068	-0.1190
112	-0.1104	-0.1037	-0.1011
113	-0.0825	-0.0800	-0.0327
114	-0.0865	-0.0729	-0.0898
115	0.1920	0.2289	0.2644
116	-0.0852	-0.0885	-0.0880
117	0.0064	-0.0024	0.0174
118	0.0266	0.0151	0.0033
119	-0.0991	-0.0966	-0.0992
120	-0.0906	-0.1001	-0.1055
121	-0.0109	-0.0358	0.0128
122	-0.0415	-0.0380	-0.0730
123	0.0928	0.1413	0.1311
124	0.0030	-0.0250	-0.0240
125	0.2298	0.1699	0.0850
126	0.0216	0.0525	0.0869
127	0.0847	0.0465	0.0798

Identity — all 250 vector components

Dimension	Tiny	Base	Orange teacher
0	-0.0831	-0.0677	-0.0550
1	0.0179	0.0415	0.0176
2	0.0527	0.0784	0.0210
3	0.0184	0.0489	0.0292
4	0.0114	0.0084	-0.0455
5	0.0226	0.0156	-0.0064
6	0.0123	0.0649	0.0355
7	-0.0268	-0.0591	-0.0506
8	-0.0350	0.0085	0.0321
9	-0.0035	-0.0191	-0.0640
10	-0.0068	-0.0150	-0.0423
11	0.0324	0.0423	0.0589
12	-0.0556	-0.0484	-0.0547
13	-0.0382	-0.0593	-0.0441
14	-0.0942	-0.0769	-0.0714
15	0.0928	0.1049	0.0621
16	0.0633	0.0499	0.1235
17	0.0272	0.0243	0.0023
18	0.0138	-0.0092	-0.0292
19	-0.1305	-0.0927	-0.0410
20	0.0338	0.0354	0.0098
21	-0.0527	-0.0599	-0.0464
22	0.0889	0.0871	0.1545
23	-0.0050	-0.0138	0.0086
24	0.1145	0.0723	0.0436
25	-0.0913	-0.0718	-0.0919
26	0.0336	0.0168	0.0994
27	0.1411	0.1436	0.1273
28	0.0773	0.1039	0.0614
29	0.0303	0.0325	-0.0062
30	0.0606	0.0446	-0.0131
31	0.0256	-0.0083	-0.0484
32	-0.0043	-0.0481	-0.0274
33	0.0561	0.0163	0.0195
34	0.0178	-0.0087	0.0168
35	-0.1189	-0.0876	-0.0644
36	0.0075	0.0379	-0.0210
37	0.0166	0.0003	-0.0066
38	-0.0633	-0.0639	-0.0651
39	-0.0185	-0.0413	-0.0138
40	-0.0242	-0.0146	-0.0105
41	0.0064	-0.0069	0.0626
42	-0.0573	-0.0637	-0.0497
43	-0.0396	-0.0621	-0.0163
44	0.0307	0.0400	0.0220
45	-0.0214	0.0083	-0.0502
46	-0.0255	-0.0312	-0.0734
47	0.1102	0.1187	0.1138
48	0.0611	0.0657	-0.0003
49	0.1107	0.0825	0.0443
50	-0.0056	-0.0171	-0.0160
51	0.0119	-0.0060	0.0298
52	-0.0266	-0.0266	-0.0493
53	0.1923	0.1518	0.1462
54	0.0140	0.0261	0.0297
55	0.2136	0.2669	0.2124
56	0.0030	0.0002	0.0464
57	0.0301	0.0456	0.0594
58	-0.0399	-0.0606	-0.0443
59	-0.0387	-0.0784	-0.0553
60	0.0205	0.0267	0.0768
61	-0.0532	-0.0621	-0.0464
62	0.0133	0.0182	0.0563
63	0.0633	0.0907	0.0457
64	0.0346	0.0173	0.0278
65	0.0536	0.0764	0.0320
66	0.0379	-0.0043	0.0158
67	0.0768	0.1080	0.1609
68	0.0353	0.0138	0.0483
69	0.0303	0.0423	0.0096
70	-0.0500	-0.0621	-0.0724
71	0.0996	0.1177	0.0933
72	-0.0691	-0.0683	-0.0554
73	-0.0156	0.0001	0.0069
74	-0.0459	-0.0331	-0.0269
75	0.1107	0.0891	0.1067
76	0.0184	-0.0038	-0.0476
77	0.0045	-0.0255	0.0328
78	0.0291	-0.0199	-0.0078
79	0.0242	-0.0015	0.0119
80	-0.0577	-0.0573	-0.0531
81	0.0312	0.0016	0.0363
82	0.0768	0.0634	0.1132
83	-0.0290	-0.0560	-0.0444
84	0.0185	0.0222	0.0307
85	0.0464	0.0118	0.0299
86	-0.0214	-0.0138	-0.0476
87	-0.0372	-0.0104	-0.0426
88	0.0764	0.0708	0.0359
89	0.1213	0.1080	0.1140
90	0.0281	0.0479	0.0400
91	0.0205	-0.0241	-0.0628
92	0.0014	-0.0120	-0.0287
93	0.1314	0.1253	0.1112
94	0.0064	-0.0287	-0.0140
95	0.0013	0.0021	0.0602
96	0.0437	0.0055	0.0206
97	-0.0288	-0.0367	-0.0226
98	0.0060	-0.0227	-0.0284
99	0.0053	0.0070	0.0468
100	-0.0112	0.0068	-0.0602
101	0.1479	0.1783	0.1555
102	0.0928	0.0693	0.0630
103	-0.0483	-0.0418	-0.0327
104	-0.0602	-0.0418	0.0019
105	-0.0706	-0.0677	-0.0694
106	-0.0541	-0.0428	-0.0411
107	0.0220	0.0136	0.0311
108	0.0846	0.1243	0.1508
109	0.0228	0.0140	0.0923
110	-0.0483	-0.0148	0.0092
111	0.1034	0.1365	0.1504
112	-0.0358	-0.0309	-0.0400
113	0.0205	0.0127	-0.0313
114	0.0587	0.0152	0.0635
115	0.0076	-0.0351	-0.0378
116	-0.0266	-0.0111	-0.0066
117	0.0744	0.0744	0.0615
118	-0.0152	-0.0571	-0.0696
119	0.0370	0.0471	0.0547
120	0.0788	0.0703	0.1071
121	-0.0515	-0.0599	-0.0550
122	0.0153	0.0132	0.0070
123	0.1759	0.1396	0.1593
124	0.0012	-0.0408	0.0366
125	0.0594	0.0588	0.0151
126	0.0582	0.0578	-0.0211
127	-0.0205	-0.0423	-0.0549
128	0.0575	0.0387	0.0646
129	-0.0108	-0.0183	-0.0157
130	-0.0783	-0.0790	-0.0536
131	0.0652	0.0309	0.0411
132	0.1266	0.1248	0.0676
133	0.0933	0.0652	0.0459
134	0.0662	0.1065	0.0545
135	0.0370	-0.0032	-0.0127
136	0.0580	0.0820	0.1052
137	0.1392	0.0820	0.1157
138	0.0188	0.0456	0.0349
139	-0.0587	-0.0596	-0.0416
140	-0.0382	-0.0134	-0.0180
141	-0.0967	-0.0591	-0.0528
142	-0.0377	-0.0461	-0.0461
143	-0.0005	0.0231	0.0301
144	-0.0208	-0.0479	-0.0556
145	-0.0435	-0.0540	-0.0294
146	0.0268	0.0441	0.0548
147	0.0208	-0.0241	0.0241
148	0.0677	0.0520	0.0992
149	0.0126	-0.0013	0.0410
150	-0.0051	0.0031	-0.0410
151	-0.0326	-0.0073	-0.0392
152	0.0744	0.1039	0.0329
153	0.0404	0.0231	0.0482
154	0.0996	0.0443	0.0809
155	0.0232	0.0006	0.0077
156	0.0157	-0.0367	-0.0085
157	0.0202	0.0150	0.0236
158	0.0040	0.0134	0.0252
159	-0.0735	-0.0973	-0.0625
160	-0.0081	-0.0438	-0.0507
161	-0.0628	-0.0548	-0.0120
162	-0.0309	-0.0341	-0.0506
163	-0.1213	-0.0953	-0.0594
164	-0.0797	-0.0739	-0.0469
165	0.0706	0.0382	0.0014
166	-0.0154	-0.0087	-0.0089
167	0.0442	0.0754	0.0770
168	-0.0822	-0.0881	-0.0754
169	-0.0214	-0.0535	0.0367
170	0.0476	0.0237	-0.0113
171	-0.0077	0.0313	0.0129
172	-0.0389	-0.0525	-0.0618
173	0.0187	0.0441	0.0791
174	-0.0865	-0.0718	-0.0548
175	-0.0696	-0.0713	-0.0859
176	0.0739	0.0856	0.1174
177	-0.0343	-0.0234	-0.0440
178	0.0022	-0.0039	-0.0474
179	0.0749	0.0479	0.1012
180	-0.0281	-0.0402	-0.0611
181	-0.0274	-0.0349	-0.0715
182	-0.0355	-0.0558	-0.0461
183	0.0233	0.0341	0.0547
184	-0.0524	-0.0530	-0.0472
185	0.0491	0.0601	0.0179
186	-0.0404	-0.0349	-0.0477
187	0.0430	0.0830	0.0237
188	0.0662	0.1416	0.1471
189	-0.0372	-0.0474	-0.0016
190	0.0486	0.0525	0.0386
191	0.1556	0.1508	0.1680
192	-0.0602	-0.0677	-0.0646
193	0.0049	-0.0033	-0.0562
194	-0.0423	-0.0325	-0.0692
195	-0.0115	-0.0413	-0.0507
196	0.0025	0.0458	0.0467
197	0.0536	0.0039	-0.0746
198	0.0295	0.0216	0.0235
199	0.0841	0.0688	0.0786
200	-0.0851	-0.1009	-0.0617
201	0.0454	0.0942	0.0622
202	-0.0739	-0.0800	-0.0797
203	0.0822	0.0410	0.1179
204	0.2039	0.1915	0.1963
205	0.1054	0.1039	0.0665
206	0.0466	0.0400	-0.0550
207	-0.0312	-0.0292	0.0070
208	0.0253	0.0010	0.0302
209	0.0899	0.0907	0.0443
210	0.0744	0.0522	0.0226
211	-0.0309	-0.0334	-0.0251
212	0.0338	0.0260	0.0334
213	0.0996	0.0632	0.0512
214	0.0744	0.0453	0.0223
215	-0.0367	-0.0349	-0.0448
216	-0.1005	-0.0683	-0.0638
217	-0.0510	-0.0070	-0.0379
218	0.0619	0.0815	-0.0238
219	-0.0764	-0.0937	-0.0545
220	0.0365	0.0354	0.1053
221	-0.0045	0.0016	0.0242
222	-0.0298	-0.0349	-0.0346
223	0.0957	0.0942	0.0358
224	0.0071	-0.0033	0.0062
225	0.1314	0.0993	0.1349
226	0.0797	0.0856	0.0475
227	-0.0358	-0.0499	-0.0698
228	-0.0291	-0.0103	-0.0326
229	0.0558	0.0769	0.0230
230	-0.0529	-0.0395	0.0145
231	-0.0157	0.0334	0.0092
232	-0.0619	-0.0132	-0.0378
233	0.0681	0.0408	0.0155
234	0.1798	0.1650	0.1700
235	0.0180	0.0502	0.0181
236	-0.0457	-0.0583	-0.0458
237	0.0267	0.0446	-0.0279
238	0.0228	0.0400	-0.0320
239	-0.0592	-0.0476	-0.0551
240	-0.0677	-0.0759	-0.0544
241	0.0577	0.0492	0.0415
242	-0.0037	0.0364	0.0350
243	-0.0009	0.0034	-0.0195
244	-0.0411	-0.0820	-0.0567
245	0.0802	0.0749	-0.0419
246	-0.0007	0.0081	0.0188
247	-0.0476	-0.0362	-0.0449
248	-0.0193	-0.0304	-0.0610
249	-0.0623	-0.0266	-0.0528

Source: Emolia / Emilia source archive · SHA-256 ad5351ce396e0e93…

e02GermanEmolia / Emilia

Emolia DE · DE_B00000_S00170_W000025

Natural speech · Original speech · 12.4 s

Wie sehen die Zahlen, Entschuldigung, ich meine Menschen mit Hoffnungen, Träumen und Familien, am Ende dieser Tabellen aus? Bell hatte die Firma im letzten Oktober verlassen, nachdem er sich nach eigenen Angaben versichert hatte, dass die Zukunft des Studios jetzt gesichert sei.

Tiny Base · values are model estimates, not ground truth

Strongest emotions relative to training

Disappointment

z +1.38 / +2.09raw 0.97 / 1.46

Pride

z +1.50 / +1.12raw 0.76 / 0.57

Sadness

z +0.80 / +1.44raw 0.61 / 1.09

Contentment

z +1.39 / +1.08raw 0.71 / 0.55

Concentration

z +1.17 / +0.98raw 1.50 / 1.36

Relief

z +0.51 / +1.10raw 0.38 / 0.78

Bitterness

z +0.80 / +1.09raw 0.35 / 0.47

The center of each bar is the S9 teacher median. Positive z is to the right; negative z is to the left. Ranking uses z, not raw teacher units.

Strongest VoiceNet dimensions relative to training

Newsreader style (S_NEWS)

z +4.81 / +4.87raw 3.14 / 3.17

Formal style (S_FORM)

z +2.33 / +2.29raw 3.57 / 3.54

Teacher or didactic style (S_TECH)

z +2.26 / +2.32raw 3.42 / 3.50

Vocal register (REGS)

z +2.04 / +2.10raw 3.79 / 3.87

Authoritative style (S_AUTH)

z +2.02 / +2.06raw 3.19 / 3.24

Speech structure (STRU)

z +1.93 / +1.93raw 3.99 / 3.99

Articulation clarity (CLRT)

z +1.87 / +1.90raw 3.79 / 3.82

All 57 VoiceNet predictions, including raw units, are in the full table below. These seven are ranked by z; the top values may differ from the strongest raw dimensions.

Voice, speed and quality scores in context

Genuineness (0–6)z -1.10 / -1.12raw 0.55 / 0.52

Vocal-burst blend (0–10)z -2.39 / -2.30raw 0.13 / 0.38

Content enjoyment (CE)z +0.82 / +0.94raw 5.63 / 5.76

Production quality (PQ)z +0.34 / +0.51raw 7.35 / 7.49

Speech signal quality, calibratedz +0.25 / +0.19raw 3.61 / 3.58

Background quality, calibratedz +0.63 / +0.47raw 3.98 / 3.83

Overall quality, calibratedz +0.74 / +0.62raw 3.29 / 3.22

P.808 MOS estimatez +0.79 / +1.04raw 3.81 / 3.94

score content enjoymentz +1.16 / +1.22raw 4.86 / 4.88

score overall qualityz +0.60 / +0.75raw 2.96 / 3.03

Background Noisez -1.67 / -2.00raw 0.37 / 0.28

Tempo (TEMP)z +1.18 / +1.38raw 3.52 / 3.76

Arousal (AROU)z +0.49 / +0.48raw 2.92 / 2.91

Valence (VALN)z +0.45 / +0.56raw 2.83 / 2.96

Recording quality (RCQL)z +1.53 / +1.33raw 4.11 / 3.93

Background noise (BKGN)z +1.88 / +1.69raw 4.14 / 3.99

talking speedz +1.43 / +1.67raw 14.41 / 15.29

Characters per second (CPS): 22.45 raw · z +3.57

Orange speaker embedding reconstruction

Cosine against Orange on this same clip (higher means closer to that teacher vector):

Embedding	Tiny	Base
Timbre · 128D	0.851	0.877
Identity · 250D	0.735	0.820

Vocal-burst regions

Tiny

Base

0 s12.4 s

Verified burst intervals are unavailable for this clip.

Tiny: 0 regions, count-head estimate 0.01; Base: 0 regions, count-head estimate 0.01.

Exact predicted start and end times

Model	Region	Start (s)	End (s)	Duration (s)

All 192 score slots · raw and z values

#	Target	Tiny raw	Tiny z	Base raw	Base z	Train median	Train SD
Emotion scores Forty clip-level Empathic Insight emotion teacher outputs. Each row evaluates one named emotion score.
0	Affectionemo_Affection	0.434	+0.75	0.250	+0.43	0.007	0.570
1	Amusementemo_Amusement	0.178	+0.20	0.115	+0.13	-0.001	0.885
2	Angeremo_Anger	0.320	+0.52	0.338	+0.55	0.004	0.613
3	Astonishment Surpriseemo_Astonishment_Surprise	0.080	+0.13	0.170	+0.29	0.005	0.572
4	Aweemo_Awe	0.006	+0.01	0.014	+0.03	0.000	0.427
5	Bitternessemo_Bitterness	0.346	+0.80	0.467	+1.09	0.013	0.415
6	Concentrationemo_Concentration	1.504	+1.17	1.364	+0.98	0.634	0.741
7	Confusionemo_Confusion	0.094	+0.17	0.413	+0.76	0.001	0.540
8	Contemplationemo_Contemplation	0.677	+0.99	0.731	+1.09	0.082	0.598
9	Contemptemo_Contempt	0.267	+0.58	0.216	+0.47	-0.000	0.464
10	Contentmentemo_Contentment	0.714	+1.39	0.554	+1.08	0.000	0.514
11	Disappointmentemo_Disappointment	0.966	+1.38	1.460	+2.09	0.000	0.700
12	Disgustemo_Disgust	0.240	+0.48	0.114	+0.22	0.007	0.489
13	Distressemo_Distress	0.407	+0.50	0.694	+0.84	0.000	0.821
14	Doubtemo_Doubt	0.066	+0.13	0.259	+0.54	0.006	0.466
15	Elationemo_Elation	0.463	+0.62	0.197	+0.25	0.012	0.728
16	Embarrassmentemo_Embarrassment	0.103	+0.14	0.237	+0.45	0.043	0.430
17	Emotional Numbnessemo_Emotional_Numbness	0.176	+0.19	0.193	+0.21	0.004	0.917
18	Fatigue Exhaustionemo_Fatigue_Exhaustion	0.027	-0.00	0.042	+0.03	0.028	0.539
19	Fearemo_Fear	-0.001	-0.03	0.122	+0.18	0.015	0.610
20	Helplessnessemo_Helplessness	0.278	+0.41	0.436	+0.63	-0.004	0.696
21	Hope Enthusiasm Optimismemo_Hope_Enthusiasm_Optimism	0.924	+1.06	0.624	+0.67	0.117	0.760
22	Impatience and Irritabilityemo_Impatience_and_Irritability	0.440	+0.41	0.501	+0.50	0.149	0.705
23	Infatuationemo_Infatuation	-0.034	-0.04	-0.005	+0.02	-0.015	0.533
24	Interestemo_Interest	2.392	+0.89	2.217	+0.69	1.589	0.907
25	Intoxication Altered States of Consciousnessemo_Intoxication_Altered_States_of_Consciousness	-0.052	-0.05	-0.019	+0.01	-0.025	0.559
26	Jealousy and Envyemo_Jealousy_and_Envy	0.167	+0.24	0.304	+0.55	0.059	0.442
27	Longingemo_Longing	0.182	+0.15	0.271	+0.29	0.087	0.632
28	Malevolence Maliceemo_Malevolence_Malice	0.218	+0.30	0.138	+0.15	0.055	0.534
29	Painemo_Pain	0.005	+0.01	0.036	+0.06	-0.002	0.579
30	Pleasure Ecstasyemo_Pleasure_Ecstasy	0.231	+0.35	0.092	+0.12	0.017	0.614
31	Prideemo_Pride	0.765	+1.50	0.570	+1.12	0.002	0.509
32	Reliefemo_Relief	0.378	+0.51	0.779	+1.10	0.033	0.681
33	Sadnessemo_Sadness	0.608	+0.80	1.089	+1.44	0.000	0.759
34	Sexual Lustemo_Sexual_Lust	-0.004	-0.07	-0.031	-0.12	0.030	0.494
35	Shameemo_Shame	0.208	+0.38	0.514	+0.98	0.013	0.510
36	Sournessemo_Sourness	0.258	+0.60	0.387	+0.89	-0.005	0.439
37	Teasingemo_Teasing	0.142	+0.26	0.335	+0.61	0.000	0.545
38	Thankfulness Gratitudeemo_Thankfulness_Gratitude	0.401	+0.52	0.350	+0.44	0.041	0.697
39	Triumphemo_Triumph	0.284	+0.56	0.189	+0.38	-0.007	0.521
VoiceNet dimensions Fifty-seven VoiceNet voice, delivery, style, and recording dimensions. Codes are expanded in the target column.
40	Perceived voice age (AGEV)vn_AGEV_reg	3.223	+0.19	2.944	-0.03	2.984	1.238
41	Arousal (AROU)vn_AROU_reg	2.919	+0.49	2.910	+0.48	2.359	1.147
42	Arousal shift (ARSH)vn_ARSH_reg	3.621	+1.20	3.587	+1.16	2.580	0.867
43	Vocal attack (ATCK)vn_ATCK_reg	3.060	+0.69	3.405	+0.96	2.162	1.295
44	Background noise (BKGN)vn_BKGN_reg	4.136	+1.88	3.988	+1.69	2.703	0.761
45	Brightness (BRGT)vn_BRGT_reg	3.306	+1.62	3.300	+1.61	1.991	0.813
46	Speech chunking (CHNK)vn_CHNK_reg	3.674	+1.48	3.830	+1.60	1.847	1.239
47	Articulation clarity (CLRT)vn_CLRT_reg	3.786	+1.87	3.816	+1.90	2.018	0.945
48	Cognitive load (COGL)vn_COGL_reg	0.918	-1.11	0.770	-1.25	2.094	1.061
49	Dynamic arc (DARC)vn_DARC_reg	2.437	+0.60	2.432	+0.59	1.615	1.380
50	Disfluency (DFLU)vn_DFLU_reg	0.979	-1.27	0.665	-1.54	2.488	1.184
51	Emphasis (EMPH)vn_EMPH_reg	3.123	+0.34	3.068	+0.30	2.607	1.524
52	Esthetics (ESTH)vn_ESTH_reg	3.015	+0.78	3.058	+0.84	2.402	0.782
53	Content appropriateness (EXPL)vn_EXPL_reg	0.067	-0.06	0.022	-0.20	0.086	0.322
54	Focus (FOCS)vn_FOCS_reg	3.446	+1.00	3.342	+0.91	2.344	1.102
55	Fullness (FULL)vn_FULL_reg	3.125	+1.51	3.207	+1.61	1.778	0.889
56	Perceived gender (GEND)vn_GEND_reg	1.256	-1.76	1.368	-1.69	4.055	1.588
57	Harmonicity (HARM)vn_HARM_reg	3.552	+1.28	3.280	+0.96	2.480	0.836
58	Metallic character (METL)vn_METL_reg	2.118	+0.52	2.275	+0.68	1.621	0.958
59	Pitch range (RANG)vn_RANG_reg	3.393	+0.53	3.487	+0.64	2.914	0.897
60	Recording quality (RCQL)vn_RCQL_reg	4.109	+1.53	3.933	+1.33	2.754	0.888
61	Vocal register (REGS)vn_REGS_reg	3.788	+2.04	3.866	+2.10	1.198	1.268
62	Respiration (RESP)vn_RESP_reg	1.848	-0.79	1.815	-0.82	2.680	1.056
63	Roughness (ROUG)vn_ROUG_reg	1.968	-0.07	1.903	-0.15	2.033	0.887
64	Chest resonance (R_CHST)vn_R_CHST_reg	2.484	+0.41	2.701	+0.67	2.135	0.844
65	Head resonance (R_HEAD)vn_R_HEAD_reg	2.819	+0.82	2.825	+0.82	2.148	0.822
66	Mask resonance (R_MASK)vn_R_MASK_reg	2.858	+0.95	2.794	+0.88	1.908	1.005
67	Mixed resonance (R_MIXD)vn_R_MIXD_reg	2.874	+1.71	2.658	+1.45	1.436	0.841
68	Nasal resonance (R_NASL)vn_R_NASL_reg	2.817	+0.02	2.734	-0.05	2.791	1.047
69	Oral resonance (R_ORAL)vn_R_ORAL_reg	2.539	+0.48	2.513	+0.44	2.184	0.741
70	Throat resonance (R_THRT)vn_R_THRT_reg	2.842	+0.96	2.798	+0.91	2.070	0.803
71	Smoothness (SMTH)vn_SMTH_reg	3.382	+1.13	3.547	+1.29	2.143	1.093
72	Stance (STNC)vn_STNC_reg	3.352	+0.63	3.486	+0.75	2.633	1.137
73	Speech structure (STRU)vn_STRU_reg	3.986	+1.93	3.986	+1.93	2.137	0.958
74	ASMR style (S_ASMR)vn_S_ASMR_reg	-0.083	-1.03	-0.363	-1.23	1.370	1.411
75	Authoritative style (S_AUTH)vn_S_AUTH_reg	3.192	+2.02	3.241	+2.06	1.088	1.043
76	Cartoonish style (S_CART)vn_S_CART_reg	1.268	-0.21	1.270	-0.21	1.560	1.401
77	Casual style (S_CASU)vn_S_CASU_reg	3.195	-0.47	3.275	-0.41	3.793	1.278
78	Conversational style (S_CONV)vn_S_CONV_reg	3.161	+0.43	3.183	+0.45	2.594	1.318
79	Dramatic style (S_DRAM)vn_S_DRAM_reg	3.280	+0.49	3.126	+0.35	2.721	1.148
80	Formal style (S_FORM)vn_S_FORM_reg	3.569	+2.33	3.538	+2.29	1.195	1.021
81	Monologue style (S_MONO)vn_S_MONO_reg	3.223	+0.31	3.190	+0.29	2.824	1.284
82	Narrator style (S_NARR)vn_S_NARR_reg	2.933	+1.12	2.647	+0.93	1.307	1.446
83	Newsreader style (S_NEWS)vn_S_NEWS_reg	3.139	+4.81	3.174	+4.87	0.408	0.568
84	Playful style (S_PLAY)vn_S_PLAY_reg	2.858	+0.38	3.132	+0.59	2.352	1.315
85	Ranting or angry style (S_RANT)vn_S_RANT_reg	1.865	+0.51	2.152	+0.73	1.213	1.289
86	Storytelling style (S_STRY)vn_S_STRY_reg	2.658	+0.13	2.747	+0.20	2.480	1.366
87	Teacher or didactic style (S_TECH)vn_S_TECH_reg	3.421	+2.26	3.497	+2.32	0.646	1.227
88	Whispered talking style (S_WHIS)vn_S_WHIS_reg	-0.469	-1.28	-0.868	-1.52	1.597	1.618
89	Tempo (TEMP)vn_TEMP_reg	3.522	+1.18	3.756	+1.38	2.117	1.190
90	Tension (TENS)vn_TENS_reg	2.098	+0.63	1.929	+0.44	1.559	0.852
91	Valence (VALN)vn_VALN_reg	2.835	+0.45	2.958	+0.56	2.328	1.118
92	Valence shift (VALS)vn_VALS_reg	3.180	+0.61	3.189	+0.62	2.518	1.079
93	Velocity flux (VFLX)vn_VFLX_reg	3.070	+0.67	3.287	+0.85	2.256	1.208
94	Volatility (VOLT)vn_VOLT_reg	1.762	-0.93	1.877	-0.80	2.586	0.886
95	Vulnerability (VULN)vn_VULN_reg	1.726	-0.94	1.664	-1.00	2.648	0.984
96	Warmth (WARM)vn_WARM_reg	2.712	+0.15	2.690	+0.12	2.578	0.909
Genuineness, blend, and legacy quality Genuineness and vocal-burst blend are predicted. R_quality has Ladder training labels but no valid P3 test labels.
97	Genuineness (0–6)genuineness_0_6	0.553	-1.10	0.516	-1.12	2.332	1.621
98	Vocal-burst blend (0–10)blend_0_10	0.125	-2.39	0.380	-2.30	6.676	2.738
99	Legacy R_quality (no P3 test labels)R_quality	0.117	-2.90	0.133	-2.85	1.095	0.338
Empathic Insight Plus extra scores Nineteen additional clip-level teacher scores, including background noise and content enjoyment.
100	Ageeiv_extra:Age	3.312	+0.21	3.229	-0.07	3.250	0.293
101	Arousaleiv_extra:Arousal	1.548	+0.60	1.510	+0.51	1.289	0.435
102	Authenticityeiv_extra:Authenticity	3.002	+2.19	2.969	+1.98	2.667	0.153
103	Background Noiseeiv_extra:Background_Noise	0.367	-1.67	0.278	-2.00	0.808	0.264
104	Confident vs. Hesitanteiv_extra:Confident_vs._Hesitant	1.014	-0.08	1.210	+0.56	1.040	0.303
105	Gendereiv_extra:Gender	1.130	+1.75	1.294	+1.92	-0.621	0.999
106	High-Pitched vs. Low-Pitchedeiv_extra:High-Pitched_vs._Low-Pitched	1.789	-0.15	1.707	-0.48	1.827	0.250
107	Monotone vs. Expressiveeiv_extra:Monotone_vs._Expressive	2.271	+0.88	2.311	+0.96	1.859	0.470
108	Recording Qualityeiv_extra:Recording_Quality	2.757	+1.85	2.731	+1.77	2.144	0.332
109	Serious vs. Humorouseiv_extra:Serious_vs._Humorous	0.978	+0.14	0.944	+0.04	0.929	0.340
110	Soft vs. Harsheiv_extra:Soft_vs._Harsh	0.481	+0.62	0.509	+0.71	0.281	0.320
111	Submissive vs. Dominanteiv_extra:Submissive_vs._Dominant	0.632	+0.79	0.392	+0.05	0.376	0.324
112	Valenceeiv_extra:Valence	0.159	+0.41	-0.154	-0.42	0.005	0.380
113	Vulnerable vs. Emotionally Detachedeiv_extra:Vulnerable_vs._Emotionally_Detached	1.785	+0.16	1.505	-0.48	1.715	0.437
114	Warm vs. Coldeiv_extra:Warm_vs._Cold	0.186	+0.45	0.110	+0.20	0.051	0.300
115	score background qualityeiv_extra:score_background_quality	3.553	+0.36	3.621	+0.46	3.301	0.693
116	score content enjoymenteiv_extra:score_content_enjoyment	4.859	+1.16	4.878	+1.22	4.507	0.303
117	score overall qualityeiv_extra:score_overall_quality	2.957	+0.60	3.030	+0.75	2.652	0.507
118	score speech qualityeiv_extra:score_speech_quality	1.879	+0.49	1.887	+0.54	1.808	0.146
Meta AudioBox Aesthetics Four AudioBox aesthetic teacher outputs. Expansions follow the official Meta model card.
119	Content enjoyment (CE)audiobox:CE	5.629	+0.82	5.757	+0.94	4.799	1.018
120	Content usefulness (CU)audiobox:CU	6.120	+0.47	6.113	+0.46	5.649	1.001
121	Production complexity (PC)audiobox:PC	1.707	-0.39	1.719	-0.38	2.331	1.617
122	Production quality (PQ)audiobox:PQ	7.346	+0.34	7.493	+0.51	7.044	0.879
Microsoft DNSMOS Seven DNSMOS teacher outputs: raw and calibrated SIG/BAK/OVRL estimates plus P.808 MOS.
123	Speech signal quality, rawdnsmos:SIG_raw	4.134	+0.35	4.087	+0.28	3.900	0.669
124	Background quality, rawdnsmos:BAK_raw	4.135	+0.82	3.933	+0.64	3.211	1.124
125	Overall quality, rawdnsmos:OVRL_raw	3.773	+0.85	3.691	+0.75	3.085	0.812
126	Speech signal quality, calibrateddnsmos:SIG	3.612	+0.25	3.582	+0.19	3.488	0.501
127	Background quality, calibrateddnsmos:BAK	3.977	+0.63	3.829	+0.47	3.389	0.928
128	Overall quality, calibrateddnsmos:OVRL	3.288	+0.74	3.217	+0.62	2.840	0.606
129	P.808 MOS estimatednsmos:P808_MOS	3.814	+0.79	3.938	+1.04	3.421	0.496
Vocal-burst count The regression target is log(1 + count). A separate table also reports count error after inverse transformation.
130	Vocal-burst count, log(1 + count)burst_count_log1p	0.013	+0.02	0.010	+0.02	0.000	0.647
VoiceCLAP attributes Sixty-one individual VoiceCLAP attribute teacher scores. The raw 768D VoiceCLAP embedding is stored in sidecars but is not a model output.
131	Affectionvoiceclap_attribute:Affection	-0.002	-1.71	0.673	-0.49	0.947	0.554
132	Agevoiceclap_attribute:Age	3.476	+0.45	3.244	+0.03	3.229	0.547
133	Amusementvoiceclap_attribute:Amusement	0.292	-0.18	0.478	+0.15	0.392	0.572
134	Angervoiceclap_attribute:Anger	0.545	-0.88	0.629	-0.72	0.992	0.506
135	Arousalvoiceclap_attribute:Arousal	1.087	-0.53	1.610	+0.31	1.420	0.622
136	Astonishment Surprisevoiceclap_attribute:Astonishment_Surprise	0.383	-0.26	0.874	+0.76	0.509	0.479
137	Authenticityvoiceclap_attribute:Authenticity	2.948	+1.07	2.914	+0.86	2.770	0.167
138	Awevoiceclap_attribute:Awe	0.160	-1.46	0.266	-1.05	0.539	0.259
139	Background Noisevoiceclap_attribute:Background_Noise	0.278	-1.10	0.228	-1.29	0.567	0.264
140	Bitternessvoiceclap_attribute:Bitterness	0.381	-0.90	0.483	-0.46	0.592	0.236
141	Concentrationvoiceclap_attribute:Concentration	1.778	+1.06	1.222	+0.02	1.214	0.531
142	Confident vs. Hesitantvoiceclap_attribute:Confident_vs._Hesitant	1.083	+0.03	1.190	+0.26	1.069	0.468
143	Confusionvoiceclap_attribute:Confusion	0.380	-0.79	0.609	-0.10	0.643	0.334
144	Contemplationvoiceclap_attribute:Contemplation	0.752	-0.07	0.499	-0.69	0.780	0.406
145	Contemptvoiceclap_attribute:Contempt	0.655	-0.16	0.702	-0.02	0.709	0.339
146	Contentmentvoiceclap_attribute:Contentment	0.345	-0.79	0.486	-0.33	0.588	0.307
147	Disappointmentvoiceclap_attribute:Disappointment	0.510	-0.86	0.615	-0.50	0.760	0.291
148	Disgustvoiceclap_attribute:Disgust	0.468	-0.76	0.651	+0.13	0.625	0.207
149	Distressvoiceclap_attribute:Distress	0.122	-2.30	0.459	-1.34	0.927	0.350
150	Doubtvoiceclap_attribute:Doubt	0.344	-1.02	0.340	-1.04	0.535	0.188
151	Elationvoiceclap_attribute:Elation	0.352	-0.47	0.760	+0.56	0.539	0.397
152	Embarrassmentvoiceclap_attribute:Embarrassment	0.094	-0.68	0.413	+0.34	0.307	0.314
153	Emotional Numbnessvoiceclap_attribute:Emotional_Numbness	0.470	-0.73	0.561	-0.39	0.664	0.266
154	Fatigue Exhaustionvoiceclap_attribute:Fatigue_Exhaustion	0.010	-1.73	0.177	-1.09	0.462	0.261
155	Fearvoiceclap_attribute:Fear	0.335	-1.33	0.343	-1.30	0.618	0.212
156	Gendervoiceclap_attribute:Gender	1.136	+1.28	1.262	+1.41	-0.151	1.005
157	Helplessnessvoiceclap_attribute:Helplessness	0.141	-1.93	0.173	-1.81	0.658	0.268
158	High-Pitched vs. Low-Pitchedvoiceclap_attribute:High-Pitched_vs._Low-Pitched	1.704	-0.36	1.659	-0.48	1.840	0.375
159	Hope Enthusiasm Optimismvoiceclap_attribute:Hope_Enthusiasm_Optimism	0.604	-0.26	0.996	+0.73	0.705	0.396
160	Impatience and Irritabilityvoiceclap_attribute:Impatience_and_Irritability	0.413	-1.18	0.737	-0.58	1.052	0.541
161	Infatuationvoiceclap_attribute:Infatuation	-0.188	-2.40	0.291	-0.95	0.608	0.332
162	Interestvoiceclap_attribute:Interest	2.268	+1.52	2.199	+1.37	1.598	0.440
163	Intoxication Altered States of Consciousnessvoiceclap_attribute:Intoxication_Altered_States_of_Consciousness	-0.012	-1.11	0.213	-0.62	0.502	0.463
164	Jealousy & Envyvoiceclap_attribute:Jealousy_&_Envy	0.513	-0.04	0.525	+0.01	0.523	0.245
165	Longingvoiceclap_attribute:Longing	0.064	-2.16	0.246	-1.33	0.538	0.220
166	Malevolence Malicevoiceclap_attribute:Malevolence_Malice	0.373	-1.33	0.484	-1.01	0.833	0.346
167	Monotone vs. Expressivevoiceclap_attribute:Monotone_vs._Expressive	1.954	+0.30	2.282	+0.85	1.775	0.594
168	Painvoiceclap_attribute:Pain	-0.045	-1.96	0.159	-1.02	0.381	0.218
169	Pleasure Ecstasyvoiceclap_attribute:Pleasure_Ecstasy	0.079	-1.41	0.431	-0.24	0.503	0.301
170	Pridevoiceclap_attribute:Pride	0.551	-0.66	0.586	-0.56	0.780	0.349
171	Recording Qualityvoiceclap_attribute:Recording_Quality	2.881	+1.73	2.782	+1.43	2.313	0.328
172	Reliefvoiceclap_attribute:Relief	0.446	-1.40	0.759	-0.64	1.025	0.415
173	Sadnessvoiceclap_attribute:Sadness	0.261	-1.57	0.386	-1.17	0.752	0.313
174	Serious vs. Humorousvoiceclap_attribute:Serious_vs._Humorous	0.724	-0.14	1.087	+0.50	0.803	0.568
175	Sexual Lustvoiceclap_attribute:Sexual_Lust	-0.042	-1.62	0.111	-1.25	0.635	0.419
176	Shamevoiceclap_attribute:Shame	0.099	-1.51	0.335	-0.68	0.526	0.283
177	Soft vs. Harshvoiceclap_attribute:Soft_vs._Harsh	0.185	+0.07	0.292	+0.37	0.160	0.360
178	Sournessvoiceclap_attribute:Sourness	0.631	-0.26	0.740	+0.12	0.706	0.291
179	Submissive vs. Dominantvoiceclap_attribute:Submissive_vs._Dominant	0.452	-0.48	0.521	-0.29	0.623	0.359
180	Teasingvoiceclap_attribute:Teasing	0.544	+0.01	0.753	+0.56	0.540	0.379
181	Thankfulness Gratitudevoiceclap_attribute:Thankfulness_Gratitude	0.519	-1.63	0.722	-1.25	1.384	0.529
182	Triumphvoiceclap_attribute:Triumph	0.238	-1.33	0.514	-0.56	0.716	0.359
183	Valencevoiceclap_attribute:Valence	0.343	+0.55	0.143	+0.24	-0.007	0.635
184	Vulnerable vs. Emotionally Detachedvoiceclap_attribute:Vulnerable_vs._Emotionally_Detached	2.295	+1.18	1.758	+0.21	1.638	0.556
185	Warm vs. Coldvoiceclap_attribute:Warm_vs._Cold	0.161	+0.57	0.307	+0.93	-0.066	0.400
186	durationvoiceclap_attribute:duration	11.841	+0.15	13.986	+0.48	10.914	6.354
187	score background qualityvoiceclap_attribute:score_background_quality	3.671	+0.85	3.776	+1.07	3.245	0.498
188	score content enjoymentvoiceclap_attribute:score_content_enjoyment	5.087	+2.93	5.126	+3.20	4.656	0.147
189	score overall qualityvoiceclap_attribute:score_overall_quality	3.145	+1.24	3.196	+1.36	2.635	0.412
190	score speech qualityvoiceclap_attribute:score_speech_quality	1.945	+0.78	1.973	+1.18	1.891	0.069
191	talking speedvoiceclap_attribute:talking_speed	14.406	+1.43	15.286	+1.67	9.028	3.756

All Orange embedding components

The cosine above is the meaningful vector-level comparison; component values have no standalone semantic label.

Timbre — all 128 vector components

Dimension	Tiny	Base	Orange teacher
0	0.1872	0.1680	0.0958
1	0.1370	0.1545	0.1486
2	0.0123	0.0420	0.1549
3	0.0945	0.0922	0.1254
4	-0.0730	-0.0525	-0.0745
5	0.0103	-0.0589	-0.0386
6	0.0107	0.0467	0.0729
7	0.0202	0.0889	0.0725
8	0.0472	-0.0147	0.0322
9	-0.0541	-0.0016	-0.0375
10	-0.0758	-0.0836	-0.0736
11	-0.0772	-0.0600	-0.0554
12	-0.0730	-0.0671	-0.0797
13	0.0753	0.0525	0.1009
14	-0.1137	-0.0922	-0.0825
15	0.1990	0.2115	0.2020
16	-0.0886	-0.0619	0.0582
17	-0.0625	-0.0444	-0.0823
18	-0.0854	-0.0844	-0.0731
19	-0.0283	-0.0242	-0.0622
20	-0.0100	-0.0433	-0.0106
21	0.1433	0.2100	0.1520
22	0.1032	0.0952	0.0731
23	-0.0557	-0.0739	0.0747
24	0.1370	0.1125	0.0708
25	0.0365	0.0433	0.0409
26	-0.0730	-0.0907	-0.0743
27	0.0372	0.0221	0.0193
28	-0.0986	-0.0975	-0.0873
29	-0.1187	-0.1080	-0.0848
30	0.0463	0.0570	0.0722
31	-0.0735	-0.0675	-0.0731
32	0.0740	0.1155	0.0919
33	0.0301	0.0461	0.1200
34	-0.0835	-0.0832	-0.0710
35	0.0301	0.0341	-0.0366
36	-0.0418	-0.0536	-0.0512
37	0.0162	-0.0001	0.0377
38	0.0849	0.0866	0.0740
39	0.0735	0.0862	0.0726
40	-0.0088	-0.0433	-0.0764
41	0.0616	0.0892	0.0466
42	-0.1128	-0.0754	-0.0799
43	-0.0285	-0.0596	-0.0300
44	-0.0333	0.0215	-0.0475
45	-0.1155	-0.0780	-0.1065
46	-0.0170	-0.0031	-0.0073
47	0.0034	0.0377	0.0214
48	-0.0931	-0.0907	-0.0773
49	-0.0150	0.0092	-0.0090
50	-0.0881	-0.0806	-0.0298
51	0.1068	0.0716	0.0351
52	-0.0607	-0.0720	-0.0554
53	-0.0945	-0.0960	-0.0808
54	-0.1625	-0.1072	-0.0886
55	-0.0251	-0.0067	-0.0580
56	-0.1087	-0.0761	-0.0751
57	0.0758	0.0611	0.0331
58	-0.0209	0.0088	0.0065
59	0.0527	0.0641	0.1196
60	0.0139	0.0010	-0.0764
61	0.1315	0.1590	0.1292
62	0.0753	0.0529	0.0689
63	-0.0518	-0.0118	0.0373
64	0.1178	0.0851	0.1320
65	-0.0571	-0.0559	-0.0646
66	-0.0189	0.0405	0.0060
67	0.0150	0.0230	0.0501
68	0.0872	0.1035	0.1830
69	0.0463	0.0735	0.1824
70	0.2237	0.1785	0.0773
71	-0.0703	-0.0626	-0.0878
72	0.2337	0.2609	0.2448
73	0.0657	0.0478	0.0569
74	-0.0156	-0.0119	-0.0615
75	0.1297	0.1500	0.1654
76	-0.0304	0.0017	-0.0481
77	-0.1023	-0.0904	-0.0723
78	-0.0612	-0.0889	-0.0705
79	0.1488	0.0619	0.1211
80	-0.0931	-0.1237	-0.0717
81	0.0436	0.0896	0.1636
82	-0.0441	-0.0525	-0.0124
83	-0.1077	-0.0784	-0.0811
84	0.0374	0.0521	0.0010
85	-0.0694	-0.0915	-0.0841
86	0.0908	0.1912	0.1862
87	0.0047	0.0002	0.0426
88	-0.0963	-0.0952	-0.0735
89	-0.0849	-0.0885	-0.0727
90	0.1342	0.1080	0.0870
91	-0.0653	-0.0626	-0.0728
92	0.0000	0.0106	0.0154
93	-0.0589	-0.0276	-0.0774
94	0.1780	0.1305	0.1378
95	-0.0475	-0.0381	-0.0386
96	-0.1461	-0.1717	-0.0617
97	-0.0128	-0.0261	0.0136
98	-0.0991	-0.0791	-0.0760
99	0.0968	0.1267	0.0636
100	0.0128	-0.0186	-0.0070
101	-0.0313	-0.0506	-0.0494
102	0.0694	0.0472	0.0984
103	0.0509	0.0276	0.1089
104	0.1178	0.1042	0.1504
105	-0.0639	-0.0369	-0.0764
106	-0.0225	-0.0300	-0.0280
107	-0.1105	-0.0671	-0.0738
108	-0.1087	-0.1177	-0.0859
109	0.2903	0.3134	0.2322
110	-0.0735	-0.0347	-0.1019
111	-0.0308	-0.0352	-0.0282
112	-0.0260	-0.0149	0.0134
113	-0.0299	0.0042	-0.0287
114	0.0196	0.0255	-0.0268
115	0.0393	0.0309	-0.0052
116	0.0644	0.0712	0.1037
117	0.0227	-0.0119	0.0194
118	-0.0931	-0.0757	-0.0771
119	-0.0831	-0.0517	-0.0766
120	0.0817	0.1635	0.1370
121	-0.0525	-0.0206	-0.0260
122	-0.0972	-0.1072	-0.0814
123	0.0245	0.0160	-0.0404
124	0.0899	0.0701	0.1125
125	0.0908	0.0266	-0.0361
126	0.0954	0.0772	0.1259
127	-0.0374	-0.0469	-0.0840

Identity — all 250 vector components

Dimension	Tiny	Base	Orange teacher
0	-0.0526	-0.0827	-0.0514
1	-0.0082	0.0166	0.0226
2	0.0001	0.0097	0.0453
3	-0.1299	-0.1482	-0.0887
4	-0.0031	-0.0105	-0.0278
5	0.0701	0.0671	0.0020
6	-0.0062	0.0205	-0.0397
7	0.0070	-0.0354	-0.0473
8	-0.0721	-0.0634	-0.0731
9	0.0249	0.0405	0.0307
10	0.0081	0.0282	-0.0490
11	-0.0270	-0.0457	-0.0400
12	0.0567	0.0685	0.0653
13	0.1387	0.2170	0.1194
14	-0.0519	-0.0424	-0.0130
15	0.0673	0.0929	0.0658
16	-0.0106	0.0006	-0.0756
17	-0.0748	-0.0832	-0.0561
18	-0.0001	0.0274	0.0780
19	-0.1121	-0.0714	-0.0742
20	-0.0646	-0.0354	-0.0468
21	-0.0388	-0.0337	-0.0433
22	0.0017	0.0125	0.0087
23	0.0141	0.0068	0.0072
24	0.1490	0.1015	0.0295
25	-0.0194	-0.0049	0.0531
26	0.1073	0.1418	0.1169
27	0.0591	0.0318	0.0515
28	0.0168	0.0006	-0.0368
29	0.0308	-0.0035	-0.0450
30	-0.0384	-0.0478	-0.0406
31	-0.0331	-0.0491	-0.0587
32	0.0984	0.1058	0.0351
33	0.0560	0.0411	0.0629
34	0.0285	-0.0101	-0.0558
35	-0.0830	-0.0623	-0.0602
36	-0.0098	-0.0052	-0.0140
37	0.0916	0.0529	0.0301
38	-0.0998	-0.1117	-0.0648
39	0.0214	0.0524	0.0956
40	-0.0183	0.0478	0.0728
41	-0.0523	-0.0489	-0.0536
42	0.1025	0.1144	0.0581
43	-0.0451	0.0095	-0.0552
44	-0.0256	-0.0376	-0.0562
45	-0.0287	-0.0333	-0.0499
46	0.0189	0.0244	-0.0133
47	-0.0219	-0.0159	-0.0271
48	-0.0191	0.0070	-0.0148
49	0.0889	0.0334	0.0453
50	0.1025	0.1369	0.1289
51	0.0543	0.0057	-0.0102
52	-0.0448	-0.0526	-0.0461
53	0.0810	0.0275	-0.0175
54	-0.0059	-0.0127	-0.0668
55	0.0015	0.0077	-0.0315
56	-0.0308	-0.0153	-0.0598
57	0.0364	0.0222	0.0126
58	-0.0350	-0.0448	-0.0449
59	0.1695	0.1536	0.0827
60	0.0320	0.0849	0.0882
61	-0.0321	0.0184	0.0317
62	0.0605	0.0545	0.0833
63	-0.0936	-0.0529	-0.0508
64	0.0287	0.0005	0.0060
65	-0.1080	-0.1020	-0.0570
66	-0.0605	-0.0653	-0.0589
67	-0.0820	-0.0956	-0.0492
68	0.0249	0.0591	0.0574
69	0.0704	0.0553	0.0237
70	-0.0871	-0.0811	-0.0677
71	-0.0388	-0.0438	-0.0490
72	0.0224	0.0036	0.0004
73	0.0203	-0.0203	-0.0491
74	-0.0649	-0.0687	-0.0504
75	-0.0321	-0.0671	-0.0680
76	0.0660	0.0811	0.1647
77	0.0465	-0.0238	-0.0450
78	0.0461	0.0537	0.0842
79	-0.0161	0.0019	-0.0300
80	-0.0591	-0.0299	-0.0496
81	0.1005	0.0653	0.0641
82	0.0431	0.0201	0.0519
83	0.1333	0.1010	0.0515
84	-0.0502	-0.0725	-0.0703
85	-0.0236	-0.0360	-0.0499
86	-0.0197	-0.0108	-0.0365
87	-0.0762	-0.0924	-0.0398
88	-0.0666	-0.0295	-0.0493
89	0.0177	0.0653	0.0272
90	0.1510	0.1450	0.2108
91	0.0147	0.0130	0.0512
92	-0.0666	-0.0886	-0.0431
93	0.0101	-0.0228	-0.0566
94	0.0526	0.0650	0.0005
95	-0.0118	0.0247	0.1181
96	0.0564	0.0677	0.0303
97	-0.1422	-0.1327	-0.0588
98	0.0461	0.0142	-0.0527
99	-0.0496	-0.0142	-0.0624
100	0.1264	0.1472	0.1998
101	0.0190	0.0328	0.0368
102	0.0448	0.0505	0.0922
103	0.0724	0.0806	0.0866
104	-0.0218	0.0136	0.0660
105	-0.0731	-0.0510	0.0067
106	-0.0468	-0.0285	-0.0384
107	0.1688	0.1622	0.1348
108	-0.0226	-0.0337	-0.0371
109	0.0943	0.0446	0.0377
110	-0.0031	-0.0044	-0.0295
111	0.1299	0.1257	0.2178
112	0.0441	0.0977	0.1364
113	0.0181	-0.0720	-0.0366
114	0.0499	0.0381	0.0311
115	-0.0076	-0.0279	-0.0353
116	0.1340	0.1257	0.1287
117	0.0096	0.0298	0.0634
118	-0.0383	-0.0489	-0.0651
119	0.0871	0.0752	0.1263
120	-0.0248	-0.0311	-0.0276
121	-0.0465	-0.0137	-0.0292
122	-0.0475	-0.0177	-0.0471
123	0.0150	0.0041	-0.0515
124	0.0923	0.0784	0.0102
125	0.0639	0.0505	-0.0046
126	0.0646	0.0212	0.0240
127	-0.0425	-0.0647	-0.0513
128	0.0350	0.0752	0.0506
129	-0.0006	-0.0093	-0.0529
130	0.1545	0.1160	0.0806
131	-0.0357	-0.0569	-0.0437
132	-0.0067	0.0023	0.0295
133	0.0086	0.0188	-0.0493
134	0.0690	0.0332	0.0304
135	0.0390	-0.0042	-0.0199
136	0.1401	0.1590	0.1769
137	0.0690	0.0687	0.0737
138	-0.0625	-0.0698	-0.0440
139	0.0598	0.1015	0.1186
140	0.0793	0.0561	0.0576
141	0.0314	0.0293	0.0273
142	0.0020	-0.0346	-0.0431
143	-0.0680	-0.0478	-0.0231
144	0.0166	0.0008	0.0657
145	-0.0653	-0.0779	-0.0634
146	-0.0302	-0.0109	-0.0339
147	-0.0066	-0.0392	-0.0443
148	0.0625	0.0612	-0.0082
149	0.1237	0.0752	0.1094
150	-0.0711	-0.0741	-0.0491
151	-0.0349	-0.0184	0.0489
152	-0.0567	-0.0435	-0.0553
153	0.0313	-0.0152	-0.0244
154	0.0186	-0.0457	-0.0486
155	0.1422	0.0924	0.0673
156	0.0386	0.0139	-0.0500
157	0.0138	0.0286	-0.0194
158	-0.0212	-0.0655	-0.0107
159	-0.0557	-0.0892	-0.0584
160	0.1066	0.0438	0.0170
161	0.0622	0.0220	0.0233
162	0.0117	-0.0132	-0.0323
163	-0.0455	-0.0176	0.0396
164	0.0059	-0.0009	-0.0438
165	-0.0163	-0.0251	-0.0241
166	-0.0519	-0.0532	-0.0580
167	-0.0039	0.0704	0.0728
168	-0.0687	-0.1278	-0.0705
169	0.1005	0.0983	0.0166
170	0.0035	0.0105	-0.0099
171	0.0042	-0.0076	0.0929
172	-0.1476	-0.1772	-0.0578
173	-0.0127	0.0146	0.0035
174	-0.0359	-0.0397	-0.0512
175	-0.0376	-0.0626	-0.0689
176	-0.0502	-0.0119	-0.0424
177	-0.0649	-0.0682	-0.0411
178	-0.0163	0.0030	-0.0371
179	0.0070	0.0055	-0.0614
180	0.0793	0.0661	0.0266
181	-0.0299	-0.0103	-0.0168
182	-0.0455	-0.0532	-0.0431
183	-0.0759	-0.0763	-0.0822
184	-0.0074	0.0111	0.0284
185	0.0646	0.0607	0.0312
186	0.0261	-0.0011	-0.0276
187	0.0045	0.0134	-0.0368
188	0.0051	-0.0231	-0.0149
189	-0.0636	-0.0048	-0.0169
190	0.0354	0.0156	0.0496
191	0.0347	-0.0048	0.1057
192	-0.0174	-0.0074	-0.0604
193	-0.0289	-0.0419	-0.0526
194	-0.0827	-0.0674	-0.0647
195	-0.0513	-0.0459	-0.0474
196	0.0251	0.0232	0.0270
197	-0.0100	-0.0642	-0.0698
198	-0.0367	-0.0310	-0.0482
199	-0.0639	-0.1096	-0.0548
200	-0.0413	-0.0634	-0.0576
201	-0.0581	-0.0243	-0.0470
202	-0.0150	-0.0360	-0.1038
203	-0.0342	-0.0363	-0.0622
204	0.0571	0.0344	-0.0274
205	0.0492	0.0260	0.0638
206	-0.0284	-0.0526	-0.0514
207	-0.0752	-0.1004	-0.0674
208	0.0256	0.0036	0.0223
209	0.0198	-0.0146	-0.0276
210	0.1148	0.1241	0.0812
211	-0.0224	-0.0316	-0.0383
212	0.0721	0.0596	0.0909
213	0.1018	0.0693	0.0731
214	0.0663	0.0411	0.0292
215	-0.0560	-0.0422	-0.0419
216	0.1066	0.0806	0.1686
217	0.0061	0.0540	0.0914
218	0.0004	0.0267	0.0261
219	-0.0224	-0.0709	-0.0649
220	-0.0998	-0.0779	-0.0551
221	0.0557	0.1187	0.0386
222	-0.0301	-0.0104	-0.0585
223	-0.0601	-0.0588	-0.0400
224	-0.0048	-0.0329	-0.0455
225	0.1886	0.1139	0.0382
226	-0.0130	0.0138	-0.0236
227	-0.0772	-0.0784	-0.0659
228	-0.0509	-0.0757	-0.0808
229	-0.0601	-0.0200	-0.0131
230	0.0161	-0.0164	0.0224
231	0.0728	0.0376	0.0455
232	-0.0748	-0.0768	-0.0685
233	-0.0704	-0.0779	-0.0659
234	-0.0106	-0.0247	-0.0423
235	0.0001	-0.0193	-0.0410
236	-0.0203	-0.0340	-0.0386
237	0.0260	0.0267	0.0487
238	0.0205	0.0196	0.0408
239	-0.0584	-0.0502	-0.0515
240	-0.0584	-0.0908	-0.0508
241	0.0280	0.0457	0.0741
242	-0.0429	-0.0325	-0.0665
243	-0.0338	-0.0532	-0.0641
244	0.0114	0.0334	0.0421
245	0.1463	0.1600	0.1285
246	-0.0275	-0.0250	-0.0404
247	-0.0496	-0.0207	-0.0420
248	0.0296	0.0326	-0.0229
249	0.0550	0.0832	0.0890

Source: Emolia / Emilia source archive · SHA-256 4e2cf3bc760aeb10…

e03EnglishEmolia / Emilia

Emolia EN · EN_B00000_S00210_W000012

Natural speech · Original speech · 3.4 s

Great episode. Uh, never expected Robin to be fine.

Tiny Base · values are model estimates, not ground truth

Strongest emotions relative to training

Hope Enthusiasm Optimism

z +0.61 / +1.10raw 0.58 / 0.96

Elation

z +0.52 / +0.80raw 0.39 / 0.59

Contentment

z +0.48 / +0.61raw 0.25 / 0.32

Concentration

z +0.46 / +0.38raw 0.98 / 0.91

Pleasure Ecstasy

z +0.33 / +0.36raw 0.22 / 0.24

Astonishment Surprise

z +0.05 / +0.27raw 0.03 / 0.16

Pride

z +0.26 / +0.08raw 0.13 / 0.04

The center of each bar is the S9 teacher median. Positive z is to the right; negative z is to the left. Ranking uses z, not raw teacher units.

Strongest VoiceNet dimensions relative to training

Chest resonance (R_CHST)

z +1.41 / +1.37raw 3.32 / 3.29

Metallic character (METL)

z +1.19 / +1.35raw 2.76 / 2.92

Valence shift (VALS)

z +0.90 / +1.16raw 3.48 / 3.77

Oral resonance (R_ORAL)

z +1.15 / +1.08raw 3.03 / 2.98

Authoritative style (S_AUTH)

z +0.94 / +1.10raw 2.07 / 2.23

Arousal shift (ARSH)

z +0.72 / +1.03raw 3.21 / 3.47

Playful style (S_PLAY)

z +0.66 / +0.88raw 3.22 / 3.51

All 57 VoiceNet predictions, including raw units, are in the full table below. These seven are ranked by z; the top values may differ from the strongest raw dimensions.

Voice, speed and quality scores in context

Genuineness (0–6)z +1.24 / +1.20raw 4.34 / 4.28

Vocal-burst blend (0–10)z -1.61 / -1.70raw 2.27 / 2.01

Content enjoyment (CE)z -0.39 / +0.23raw 4.40 / 5.03

Production quality (PQ)z -1.23 / -0.75raw 5.96 / 6.39

Speech signal quality, calibratedz -0.27 / -0.15raw 3.35 / 3.41

Background quality, calibratedz +0.15 / +0.08raw 3.53 / 3.46

Overall quality, calibratedz -0.03 / +0.00raw 2.82 / 2.84

P.808 MOS estimatez +0.46 / +0.12raw 3.65 / 3.48

score content enjoymentz +0.04 / +0.03raw 4.52 / 4.52

score overall qualityz -0.18 / -0.36raw 2.56 / 2.47

Background Noisez -0.56 / -0.28raw 0.66 / 0.73

Tempo (TEMP)z +0.52 / +0.56raw 2.73 / 2.79

Arousal (AROU)z +0.52 / +0.51raw 2.96 / 2.94

Valence (VALN)z +0.58 / +0.73raw 2.98 / 3.14

Recording quality (RCQL)z -0.34 / -0.24raw 2.45 / 2.54

Background noise (BKGN)z +0.68 / +0.71raw 3.22 / 3.24

talking speedz +2.21 / +1.65raw 17.34 / 15.23

Characters per second (CPS): 14.80 raw · z +1.54

Orange speaker embedding reconstruction

Cosine against Orange on this same clip (higher means closer to that teacher vector):

Embedding	Tiny	Base
Timbre · 128D	0.669	0.667
Identity · 250D	0.564	0.610

Vocal-burst regions

Tiny

Base

0 s3.4 s

Verified burst intervals are unavailable for this clip.

Tiny: 1 regions, count-head estimate 1.06; Base: 1 regions, count-head estimate 1.19.

Exact predicted start and end times

Model	Region	Start (s)	End (s)	Duration (s)
Tiny	1	1.20	1.60	0.40
Base	1	1.20	1.62	0.42

All 192 score slots · raw and z values

#	Target	Tiny raw	Tiny z	Base raw	Base z	Train median	Train SD
Emotion scores Forty clip-level Empathic Insight emotion teacher outputs. Each row evaluates one named emotion score.
0	Affectionemo_Affection	0.031	+0.04	0.001	-0.01	0.007	0.570
1	Amusementemo_Amusement	0.074	+0.08	0.057	+0.07	-0.001	0.885
2	Angeremo_Anger	-0.018	-0.04	0.041	+0.06	0.004	0.613
3	Astonishment Surpriseemo_Astonishment_Surprise	0.032	+0.05	0.157	+0.27	0.005	0.572
4	Aweemo_Awe	0.007	+0.02	0.009	+0.02	0.000	0.427
5	Bitternessemo_Bitterness	0.034	+0.05	0.006	-0.02	0.013	0.415
6	Concentrationemo_Concentration	0.979	+0.46	0.913	+0.38	0.634	0.741
7	Confusionemo_Confusion	0.052	+0.09	0.001	-0.00	0.001	0.540
8	Contemplationemo_Contemplation	0.036	-0.08	0.002	-0.13	0.082	0.598
9	Contemptemo_Contempt	-0.020	-0.04	0.028	+0.06	-0.000	0.464
10	Contentmentemo_Contentment	0.245	+0.48	0.316	+0.61	0.000	0.514
11	Disappointmentemo_Disappointment	0.068	+0.10	0.057	+0.08	0.000	0.700
12	Disgustemo_Disgust	0.010	+0.01	0.040	+0.07	0.007	0.489
13	Distressemo_Distress	0.044	+0.05	0.037	+0.05	0.000	0.821
14	Doubtemo_Doubt	0.053	+0.10	0.059	+0.11	0.006	0.466
15	Elationemo_Elation	0.390	+0.52	0.592	+0.80	0.012	0.728
16	Embarrassmentemo_Embarrassment	0.117	+0.17	0.130	+0.20	0.043	0.430
17	Emotional Numbnessemo_Emotional_Numbness	0.129	+0.14	0.126	+0.13	0.004	0.917
18	Fatigue Exhaustionemo_Fatigue_Exhaustion	-0.002	-0.06	0.013	-0.03	0.028	0.539
19	Fearemo_Fear	-0.032	-0.08	-0.049	-0.10	0.015	0.610
20	Helplessnessemo_Helplessness	-0.014	-0.02	-0.048	-0.06	-0.004	0.696
21	Hope Enthusiasm Optimismemo_Hope_Enthusiasm_Optimism	0.578	+0.61	0.957	+1.10	0.117	0.760
22	Impatience and Irritabilityemo_Impatience_and_Irritability	0.031	-0.17	0.049	-0.14	0.149	0.705
23	Infatuationemo_Infatuation	0.034	+0.09	0.003	+0.03	-0.015	0.533
24	Interestemo_Interest	1.532	-0.06	1.671	+0.09	1.589	0.907
25	Intoxication Altered States of Consciousnessemo_Intoxication_Altered_States_of_Consciousness	-0.000	+0.04	-0.007	+0.03	-0.025	0.559
26	Jealousy and Envyemo_Jealousy_and_Envy	0.054	-0.01	0.019	-0.09	0.059	0.442
27	Longingemo_Longing	0.015	-0.11	-0.044	-0.21	0.087	0.632
28	Malevolence Maliceemo_Malevolence_Malice	0.067	+0.02	0.038	-0.03	0.055	0.534
29	Painemo_Pain	-0.000	+0.00	-0.007	-0.01	-0.002	0.579
30	Pleasure Ecstasyemo_Pleasure_Ecstasy	0.221	+0.33	0.237	+0.36	0.017	0.614
31	Prideemo_Pride	0.133	+0.26	0.044	+0.08	0.002	0.509
32	Reliefemo_Relief	0.076	+0.06	0.168	+0.20	0.033	0.681
33	Sadnessemo_Sadness	0.059	+0.08	0.002	+0.00	0.000	0.759
34	Sexual Lustemo_Sexual_Lust	-0.021	-0.10	-0.025	-0.11	0.030	0.494
35	Shameemo_Shame	0.010	-0.01	-0.003	-0.03	0.013	0.510
36	Sournessemo_Sourness	0.042	+0.11	0.007	+0.03	-0.005	0.439
37	Teasingemo_Teasing	0.028	+0.05	0.024	+0.04	0.000	0.545
38	Thankfulness Gratitudeemo_Thankfulness_Gratitude	0.130	+0.13	0.197	+0.22	0.041	0.697
39	Triumphemo_Triumph	0.020	+0.05	-0.023	-0.03	-0.007	0.521
VoiceNet dimensions Fifty-seven VoiceNet voice, delivery, style, and recording dimensions. Codes are expanded in the target column.
40	Perceived voice age (AGEV)vn_AGEV_reg	2.202	-0.63	2.143	-0.68	2.984	1.238
41	Arousal (AROU)vn_AROU_reg	2.958	+0.52	2.943	+0.51	2.359	1.147
42	Arousal shift (ARSH)vn_ARSH_reg	3.207	+0.72	3.471	+1.03	2.580	0.867
43	Vocal attack (ATCK)vn_ATCK_reg	2.515	+0.27	2.633	+0.36	2.162	1.295
44	Background noise (BKGN)vn_BKGN_reg	3.222	+0.68	3.240	+0.71	2.703	0.761
45	Brightness (BRGT)vn_BRGT_reg	2.272	+0.35	2.277	+0.35	1.991	0.813
46	Speech chunking (CHNK)vn_CHNK_reg	2.491	+0.52	2.330	+0.39	1.847	1.239
47	Articulation clarity (CLRT)vn_CLRT_reg	2.015	-0.00	2.092	+0.08	2.018	0.945
48	Cognitive load (COGL)vn_COGL_reg	2.419	+0.31	2.320	+0.21	2.094	1.061
49	Dynamic arc (DARC)vn_DARC_reg	1.684	+0.05	1.749	+0.10	1.615	1.380
50	Disfluency (DFLU)vn_DFLU_reg	3.156	+0.56	3.073	+0.49	2.488	1.184
51	Emphasis (EMPH)vn_EMPH_reg	2.853	+0.16	3.233	+0.41	2.607	1.524
52	Esthetics (ESTH)vn_ESTH_reg	2.733	+0.42	2.666	+0.34	2.402	0.782
53	Content appropriateness (EXPL)vn_EXPL_reg	0.306	+0.68	0.263	+0.55	0.086	0.322
54	Focus (FOCS)vn_FOCS_reg	2.391	+0.04	2.384	+0.04	2.344	1.102
55	Fullness (FULL)vn_FULL_reg	2.198	+0.47	2.434	+0.74	1.778	0.889
56	Perceived gender (GEND)vn_GEND_reg	4.939	+0.56	4.852	+0.50	4.055	1.588
57	Harmonicity (HARM)vn_HARM_reg	2.918	+0.52	2.819	+0.41	2.480	0.836
58	Metallic character (METL)vn_METL_reg	2.761	+1.19	2.918	+1.35	1.621	0.958
59	Pitch range (RANG)vn_RANG_reg	2.786	-0.14	2.801	-0.13	2.914	0.897
60	Recording quality (RCQL)vn_RCQL_reg	2.451	-0.34	2.541	-0.24	2.754	0.888
61	Vocal register (REGS)vn_REGS_reg	0.667	-0.42	0.878	-0.25	1.198	1.268
62	Respiration (RESP)vn_RESP_reg	1.510	-1.11	1.376	-1.23	2.680	1.056
63	Roughness (ROUG)vn_ROUG_reg	1.155	-0.99	1.585	-0.51	2.033	0.887
64	Chest resonance (R_CHST)vn_R_CHST_reg	3.321	+1.41	3.288	+1.37	2.135	0.844
65	Head resonance (R_HEAD)vn_R_HEAD_reg	2.613	+0.57	2.825	+0.82	2.148	0.822
66	Mask resonance (R_MASK)vn_R_MASK_reg	2.614	+0.70	2.722	+0.81	1.908	1.005
67	Mixed resonance (R_MIXD)vn_R_MIXD_reg	2.086	+0.77	2.069	+0.75	1.436	0.841
68	Nasal resonance (R_NASL)vn_R_NASL_reg	3.126	+0.32	3.095	+0.29	2.791	1.047
69	Oral resonance (R_ORAL)vn_R_ORAL_reg	3.033	+1.15	2.981	+1.08	2.184	0.741
70	Throat resonance (R_THRT)vn_R_THRT_reg	2.716	+0.80	2.744	+0.84	2.070	0.803
71	Smoothness (SMTH)vn_SMTH_reg	2.462	+0.29	2.497	+0.32	2.143	1.093
72	Stance (STNC)vn_STNC_reg	2.914	+0.25	3.072	+0.39	2.633	1.137
73	Speech structure (STRU)vn_STRU_reg	2.638	+0.52	2.618	+0.50	2.137	0.958
74	ASMR style (S_ASMR)vn_S_ASMR_reg	0.025	-0.95	0.268	-0.78	1.370	1.411
75	Authoritative style (S_AUTH)vn_S_AUTH_reg	2.072	+0.94	2.230	+1.10	1.088	1.043
76	Cartoonish style (S_CART)vn_S_CART_reg	0.391	-0.83	0.947	-0.44	1.560	1.401
77	Casual style (S_CASU)vn_S_CASU_reg	4.493	+0.55	4.473	+0.53	3.793	1.278
78	Conversational style (S_CONV)vn_S_CONV_reg	3.635	+0.79	3.589	+0.75	2.594	1.318
79	Dramatic style (S_DRAM)vn_S_DRAM_reg	0.866	-1.62	1.008	-1.49	2.721	1.148
80	Formal style (S_FORM)vn_S_FORM_reg	1.458	+0.26	1.484	+0.28	1.195	1.021
81	Monologue style (S_MONO)vn_S_MONO_reg	2.414	-0.32	2.369	-0.35	2.824	1.284
82	Narrator style (S_NARR)vn_S_NARR_reg	1.038	-0.19	0.998	-0.21	1.307	1.446
83	Newsreader style (S_NEWS)vn_S_NEWS_reg	0.463	+0.10	0.501	+0.16	0.408	0.568
84	Playful style (S_PLAY)vn_S_PLAY_reg	3.218	+0.66	3.508	+0.88	2.352	1.315
85	Ranting or angry style (S_RANT)vn_S_RANT_reg	0.258	-0.74	0.507	-0.55	1.213	1.289
86	Storytelling style (S_STRY)vn_S_STRY_reg	1.574	-0.66	1.659	-0.60	2.480	1.366
87	Teacher or didactic style (S_TECH)vn_S_TECH_reg	1.014	+0.30	0.971	+0.26	0.646	1.227
88	Whispered talking style (S_WHIS)vn_S_WHIS_reg	-0.094	-1.05	-0.144	-1.08	1.597	1.618
89	Tempo (TEMP)vn_TEMP_reg	2.734	+0.52	2.786	+0.56	2.117	1.190
90	Tension (TENS)vn_TENS_reg	1.687	+0.15	1.686	+0.15	1.559	0.852
91	Valence (VALN)vn_VALN_reg	2.976	+0.58	3.144	+0.73	2.328	1.118
92	Valence shift (VALS)vn_VALS_reg	3.485	+0.90	3.768	+1.16	2.518	1.079
93	Velocity flux (VFLX)vn_VFLX_reg	2.430	+0.14	2.570	+0.26	2.256	1.208
94	Volatility (VOLT)vn_VOLT_reg	2.026	-0.63	2.259	-0.37	2.586	0.886
95	Vulnerability (VULN)vn_VULN_reg	2.627	-0.02	2.538	-0.11	2.648	0.984
96	Warmth (WARM)vn_WARM_reg	2.388	-0.21	2.613	+0.04	2.578	0.909
Genuineness, blend, and legacy quality Genuineness and vocal-burst blend are predicted. R_quality has Ladder training labels but no valid P3 test labels.
97	Genuineness (0–6)genuineness_0_6	4.338	+1.24	4.275	+1.20	2.332	1.621
98	Vocal-burst blend (0–10)blend_0_10	2.270	-1.61	2.015	-1.70	6.676	2.738
99	Legacy R_quality (no P3 test labels)R_quality	0.961	-0.40	0.920	-0.52	1.095	0.338
Empathic Insight Plus extra scores Nineteen additional clip-level teacher scores, including background noise and content enjoyment.
100	Ageeiv_extra:Age	3.225	-0.09	3.249	-0.01	3.250	0.293
101	Arousaleiv_extra:Arousal	1.121	-0.38	1.356	+0.15	1.289	0.435
102	Authenticityeiv_extra:Authenticity	2.665	-0.01	2.676	+0.06	2.667	0.153
103	Background Noiseeiv_extra:Background_Noise	0.658	-0.56	0.734	-0.28	0.808	0.264
104	Confident vs. Hesitanteiv_extra:Confident_vs._Hesitant	1.051	+0.04	1.122	+0.27	1.040	0.303
105	Gendereiv_extra:Gender	-0.853	-0.23	-0.713	-0.09	-0.621	0.999
106	High-Pitched vs. Low-Pitchedeiv_extra:High-Pitched_vs._Low-Pitched	1.915	+0.35	1.823	-0.02	1.827	0.250
107	Monotone vs. Expressiveeiv_extra:Monotone_vs._Expressive	1.378	-1.02	1.655	-0.43	1.859	0.470
108	Recording Qualityeiv_extra:Recording_Quality	2.168	+0.07	2.125	-0.06	2.144	0.332
109	Serious vs. Humorouseiv_extra:Serious_vs._Humorous	1.089	+0.47	1.227	+0.87	0.929	0.340
110	Soft vs. Harsheiv_extra:Soft_vs._Harsh	0.088	-0.60	0.283	+0.01	0.281	0.320
111	Submissive vs. Dominanteiv_extra:Submissive_vs._Dominant	0.397	+0.07	0.355	-0.06	0.376	0.324
112	Valenceeiv_extra:Valence	-0.002	-0.02	0.227	+0.58	0.005	0.380
113	Vulnerable vs. Emotionally Detachedeiv_extra:Vulnerable_vs._Emotionally_Detached	2.215	+1.15	1.985	+0.62	1.715	0.437
114	Warm vs. Coldeiv_extra:Warm_vs._Cold	0.084	+0.11	0.226	+0.58	0.051	0.300
115	score background qualityeiv_extra:score_background_quality	3.507	+0.30	3.328	+0.04	3.301	0.693
116	score content enjoymenteiv_extra:score_content_enjoyment	4.519	+0.04	4.515	+0.03	4.507	0.303
117	score overall qualityeiv_extra:score_overall_quality	2.560	-0.18	2.468	-0.36	2.652	0.507
118	score speech qualityeiv_extra:score_speech_quality	2.016	+1.43	1.928	+0.83	1.808	0.146
Meta AudioBox Aesthetics Four AudioBox aesthetic teacher outputs. Expansions follow the official Meta model card.
119	Content enjoyment (CE)audiobox:CE	4.398	-0.39	5.034	+0.23	4.799	1.018
120	Content usefulness (CU)audiobox:CU	4.930	-0.72	5.839	+0.19	5.649	1.001
121	Production complexity (PC)audiobox:PC	1.915	-0.26	2.117	-0.13	2.331	1.617
122	Production quality (PQ)audiobox:PQ	5.961	-1.23	6.387	-0.75	7.044	0.879
Microsoft DNSMOS Seven DNSMOS teacher outputs: raw and calibrated SIG/BAK/OVRL estimates plus P.808 MOS.
123	Speech signal quality, rawdnsmos:SIG_raw	3.680	-0.33	3.774	-0.19	3.900	0.669
124	Background quality, rawdnsmos:BAK_raw	3.456	+0.22	3.368	+0.14	3.211	1.124
125	Overall quality, rawdnsmos:OVRL_raw	3.075	-0.01	3.095	+0.01	3.085	0.812
126	Speech signal quality, calibrateddnsmos:SIG	3.351	-0.27	3.415	-0.15	3.488	0.501
127	Background quality, calibrateddnsmos:BAK	3.528	+0.15	3.464	+0.08	3.389	0.928
128	Overall quality, calibrateddnsmos:OVRL	2.820	-0.03	2.842	+0.00	2.840	0.606
129	P.808 MOS estimatednsmos:P808_MOS	3.647	+0.46	3.480	+0.12	3.421	0.496
Vocal-burst count The regression target is log(1 + count). A separate table also reports count error after inverse transformation.
130	Vocal-burst count, log(1 + count)burst_count_log1p	0.725	+1.12	0.784	+1.21	0.000	0.647
VoiceCLAP attributes Sixty-one individual VoiceCLAP attribute teacher scores. The raw 768D VoiceCLAP embedding is stored in sidecars but is not a model output.
131	Affectionvoiceclap_attribute:Affection	0.396	-0.99	0.201	-1.35	0.947	0.554
132	Agevoiceclap_attribute:Age	3.126	-0.19	3.081	-0.27	3.229	0.547
133	Amusementvoiceclap_attribute:Amusement	0.287	-0.18	0.408	+0.03	0.392	0.572
134	Angervoiceclap_attribute:Anger	0.545	-0.88	0.292	-1.39	0.992	0.506
135	Arousalvoiceclap_attribute:Arousal	1.253	-0.27	1.295	-0.20	1.420	0.622
136	Astonishment Surprisevoiceclap_attribute:Astonishment_Surprise	0.693	+0.38	0.913	+0.84	0.509	0.479
137	Authenticityvoiceclap_attribute:Authenticity	2.656	-0.68	2.635	-0.81	2.770	0.167
138	Awevoiceclap_attribute:Awe	0.322	-0.84	0.415	-0.48	0.539	0.259
139	Background Noisevoiceclap_attribute:Background_Noise	0.375	-0.73	0.479	-0.33	0.567	0.264
140	Bitternessvoiceclap_attribute:Bitterness	0.367	-0.96	0.221	-1.57	0.592	0.236
141	Concentrationvoiceclap_attribute:Concentration	0.967	-0.47	0.868	-0.65	1.214	0.531
142	Confident vs. Hesitantvoiceclap_attribute:Confident_vs._Hesitant	1.498	+0.92	1.399	+0.70	1.069	0.468
143	Confusionvoiceclap_attribute:Confusion	0.675	+0.10	0.672	+0.08	0.643	0.334
144	Contemplationvoiceclap_attribute:Contemplation	0.347	-1.07	0.354	-1.05	0.780	0.406
145	Contemptvoiceclap_attribute:Contempt	0.407	-0.89	0.287	-1.24	0.709	0.339
146	Contentmentvoiceclap_attribute:Contentment	0.201	-1.26	0.249	-1.10	0.588	0.307
147	Disappointmentvoiceclap_attribute:Disappointment	0.248	-1.76	0.161	-2.06	0.760	0.291
148	Disgustvoiceclap_attribute:Disgust	0.353	-1.31	0.279	-1.67	0.625	0.207
149	Distressvoiceclap_attribute:Distress	0.431	-1.42	0.390	-1.53	0.927	0.350
150	Doubtvoiceclap_attribute:Doubt	0.574	+0.21	0.583	+0.25	0.535	0.188
151	Elationvoiceclap_attribute:Elation	0.506	-0.08	0.671	+0.33	0.539	0.397
152	Embarrassmentvoiceclap_attribute:Embarrassment	0.461	+0.49	0.352	+0.14	0.307	0.314
153	Emotional Numbnessvoiceclap_attribute:Emotional_Numbness	0.663	-0.00	0.664	+0.00	0.664	0.266
154	Fatigue Exhaustionvoiceclap_attribute:Fatigue_Exhaustion	0.434	-0.11	0.298	-0.63	0.462	0.261
155	Fearvoiceclap_attribute:Fear	0.190	-2.02	0.257	-1.70	0.618	0.212
156	Gendervoiceclap_attribute:Gender	-0.794	-0.64	-0.826	-0.67	-0.151	1.005
157	Helplessnessvoiceclap_attribute:Helplessness	0.328	-1.23	0.284	-1.39	0.658	0.268
158	High-Pitched vs. Low-Pitchedvoiceclap_attribute:High-Pitched_vs._Low-Pitched	1.947	+0.29	1.918	+0.21	1.840	0.375
159	Hope Enthusiasm Optimismvoiceclap_attribute:Hope_Enthusiasm_Optimism	0.612	-0.24	0.713	+0.02	0.705	0.396
160	Impatience and Irritabilityvoiceclap_attribute:Impatience_and_Irritability	0.722	-0.61	0.443	-1.13	1.052	0.541
161	Infatuationvoiceclap_attribute:Infatuation	0.230	-1.14	0.123	-1.46	0.608	0.332
162	Interestvoiceclap_attribute:Interest	1.327	-0.62	1.360	-0.54	1.598	0.440
163	Intoxication Altered States of Consciousnessvoiceclap_attribute:Intoxication_Altered_States_of_Consciousness	0.280	-0.48	0.292	-0.45	0.502	0.463
164	Jealousy & Envyvoiceclap_attribute:Jealousy_&_Envy	0.066	-1.86	0.033	-2.00	0.523	0.245
165	Longingvoiceclap_attribute:Longing	0.311	-1.03	0.271	-1.21	0.538	0.220
166	Malevolence Malicevoiceclap_attribute:Malevolence_Malice	0.260	-1.66	0.133	-2.03	0.833	0.346
167	Monotone vs. Expressivevoiceclap_attribute:Monotone_vs._Expressive	1.311	-0.78	1.364	-0.69	1.775	0.594
168	Painvoiceclap_attribute:Pain	0.186	-0.90	0.169	-0.98	0.381	0.218
169	Pleasure Ecstasyvoiceclap_attribute:Pleasure_Ecstasy	0.315	-0.63	0.437	-0.22	0.503	0.301
170	Pridevoiceclap_attribute:Pride	0.261	-1.49	0.340	-1.26	0.780	0.349
171	Recording Qualityvoiceclap_attribute:Recording_Quality	2.167	-0.45	2.170	-0.44	2.313	0.328
172	Reliefvoiceclap_attribute:Relief	0.621	-0.97	0.688	-0.81	1.025	0.415
173	Sadnessvoiceclap_attribute:Sadness	0.406	-1.11	0.381	-1.18	0.752	0.313
174	Serious vs. Humorousvoiceclap_attribute:Serious_vs._Humorous	1.016	+0.37	1.176	+0.65	0.803	0.568
175	Sexual Lustvoiceclap_attribute:Sexual_Lust	0.118	-1.24	0.000	-1.52	0.635	0.419
176	Shamevoiceclap_attribute:Shame	0.336	-0.67	0.294	-0.82	0.526	0.283
177	Soft vs. Harshvoiceclap_attribute:Soft_vs._Harsh	0.119	-0.11	0.106	-0.15	0.160	0.360
178	Sournessvoiceclap_attribute:Sourness	0.376	-1.13	0.326	-1.31	0.706	0.291
179	Submissive vs. Dominantvoiceclap_attribute:Submissive_vs._Dominant	0.309	-0.88	0.233	-1.09	0.623	0.359
180	Teasingvoiceclap_attribute:Teasing	0.423	-0.31	0.383	-0.42	0.540	0.379
181	Thankfulness Gratitudevoiceclap_attribute:Thankfulness_Gratitude	0.672	-1.34	0.507	-1.66	1.384	0.529
182	Triumphvoiceclap_attribute:Triumph	0.422	-0.82	0.539	-0.49	0.716	0.359
183	Valencevoiceclap_attribute:Valence	-0.347	-0.54	0.276	+0.45	-0.007	0.635
184	Vulnerable vs. Emotionally Detachedvoiceclap_attribute:Vulnerable_vs._Emotionally_Detached	2.282	+1.16	2.226	+1.06	1.638	0.556
185	Warm vs. Coldvoiceclap_attribute:Warm_vs._Cold	0.141	+0.52	0.087	+0.38	-0.066	0.400
186	durationvoiceclap_attribute:duration	4.807	-0.96	5.153	-0.91	10.914	6.354
187	score background qualityvoiceclap_attribute:score_background_quality	3.388	+0.29	3.306	+0.12	3.245	0.498
188	score content enjoymentvoiceclap_attribute:score_content_enjoyment	4.604	-0.35	4.594	-0.42	4.656	0.147
189	score overall qualityvoiceclap_attribute:score_overall_quality	2.411	-0.54	2.429	-0.50	2.635	0.412
190	score speech qualityvoiceclap_attribute:score_speech_quality	2.077	+2.68	2.040	+2.15	1.891	0.069
191	talking speedvoiceclap_attribute:talking_speed	17.338	+2.21	15.227	+1.65	9.028	3.756

All Orange embedding components

The cosine above is the meaningful vector-level comparison; component values have no standalone semantic label.

Timbre — all 128 vector components

Dimension	Tiny	Base	Orange teacher
0	0.0844	0.0171	-0.0802
1	0.0826	0.0768	-0.0732
2	-0.0413	-0.0449	-0.0533
3	-0.0150	0.0088	-0.0858
4	0.2381	0.2111	0.2002
5	0.0304	-0.0261	0.1136
6	-0.0966	-0.1254	-0.0788
7	0.0671	0.1254	0.1583
8	-0.0073	-0.0483	-0.0745
9	-0.0535	-0.0442	0.0908
10	-0.0498	-0.0523	-0.0173
11	-0.0686	-0.0436	0.0419
12	-0.1045	-0.1411	0.0018
13	-0.1233	-0.0998	-0.0858
14	-0.0235	-0.0460	0.0267
15	0.0205	0.0200	0.0271
16	-0.0011	-0.0111	-0.0062
17	0.0278	0.0758	0.1692
18	0.0375	0.0528	0.0576
19	0.2065	0.2184	0.1345
20	-0.0966	-0.0836	-0.0870
21	-0.0272	-0.0091	-0.0621
22	-0.1264	-0.1239	-0.0817
23	-0.1276	-0.1108	-0.1028
24	0.0302	-0.0105	0.0398
25	-0.0383	0.0234	0.0443
26	0.0450	0.0666	0.0648
27	-0.1069	-0.0862	-0.0811
28	-0.1124	-0.0737	-0.0950
29	0.0194	-0.0320	0.1702
30	0.1592	0.2038	0.1405
31	0.0966	0.1103	-0.0803
32	-0.0014	-0.0374	0.0682
33	0.0735	0.0638	0.0869
34	0.0416	0.0264	0.0962
35	-0.0790	-0.1145	-0.0231
36	-0.0257	0.0125	0.1246
37	0.0052	0.0163	-0.0581
38	-0.0738	-0.0337	-0.0867
39	-0.0178	-0.0690	0.0723
40	0.0333	-0.0109	0.1660
41	0.0168	0.0251	0.0128
42	-0.0177	0.0656	0.0770
43	-0.1057	-0.0066	0.0237
44	0.0114	-0.0027	-0.0046
45	0.0869	0.0711	0.0632
46	-0.0556	-0.0384	-0.0820
47	-0.1294	-0.1014	-0.0341
48	0.1798	0.1056	0.0569
49	-0.0954	-0.1118	-0.0878
50	0.0547	0.0504	0.0456
51	-0.0747	-0.1275	-0.0869
52	-0.0796	-0.1092	-0.0988
53	-0.1136	-0.1322	-0.0718
54	0.0174	0.0619	0.0904
55	0.0112	-0.0157	-0.0836
56	0.0583	0.0651	0.0642
57	0.0732	0.0554	-0.0328
58	-0.0802	-0.0517	0.0902
59	-0.0960	-0.0690	-0.0872
60	0.0477	-0.0153	0.1074
61	-0.0556	-0.0517	-0.0800
62	-0.0747	-0.0998	-0.0813
63	0.1652	0.2122	0.1826
64	-0.1075	-0.1411	-0.0882
65	-0.0693	-0.0747	-0.0709
66	0.1185	0.0758	-0.1130
67	-0.0905	-0.1134	0.0295
68	-0.0029	-0.0078	0.0390
69	-0.1245	-0.0909	-0.0797
70	0.0416	0.0536	0.1060
71	-0.0378	-0.1134	-0.0963
72	-0.0629	-0.0666	-0.0462
73	0.0089	0.0179	0.0063
74	-0.0623	-0.0653	-0.0950
75	0.0647	0.1254	-0.0271
76	0.1895	0.2310	0.2321
77	0.0759	0.0255	0.0142
78	0.0611	0.0679	0.1053
79	-0.0702	-0.0664	-0.0754
80	0.0492	0.1024	-0.0273
81	-0.0372	-0.0857	-0.0787
82	-0.0729	-0.1056	-0.0832
83	0.0431	-0.0171	0.0423
84	-0.1664	-0.1421	-0.1078
85	-0.1470	-0.1536	-0.0923
86	0.0228	-0.0199	-0.1183
87	-0.0483	-0.0178	-0.0526
88	0.0899	0.0617	0.0361
89	0.0571	0.0392	0.0867
90	-0.1251	-0.1359	-0.0942
91	0.0923	0.1192	-0.0289
92	-0.1233	-0.0606	-0.0766
93	0.1002	0.1165	0.2362
94	-0.0395	0.0463	-0.0241
95	-0.1221	-0.1192	-0.0934
96	-0.0863	-0.0648	-0.0943
97	0.1106	0.0972	0.0340
98	0.0024	0.1040	-0.0391
99	0.1130	0.0117	0.0207
100	0.0363	0.0593	-0.0602
101	-0.0802	-0.0572	-0.0840
102	-0.1355	-0.1087	-0.0930
103	-0.1051	-0.1150	-0.0917
104	-0.1306	-0.1108	-0.0850
105	-0.1470	-0.0779	-0.0838
106	-0.0905	-0.0293	-0.0580
107	0.2053	0.1704	0.1807
108	0.0245	0.0491	0.0423
109	0.0034	0.0013	-0.0726
110	0.0000	-0.0033	0.0901
111	-0.0893	-0.0962	-0.1008
112	-0.0680	-0.0685	-0.0324
113	0.0486	0.0541	0.0214
114	-0.1087	-0.1212	-0.0936
115	-0.0623	-0.0496	0.0451
116	-0.0240	-0.0530	-0.0745
117	-0.0984	-0.1092	-0.1011
118	-0.0276	-0.0967	-0.0482
119	-0.0024	-0.0144	-0.0840
120	0.1197	0.0510	0.0514
121	-0.1148	-0.1066	-0.0881
122	-0.1142	-0.0909	-0.0893
123	0.1008	0.0284	0.0792
124	-0.0450	0.0348	-0.1132
125	0.0893	0.0883	0.0254
126	-0.1027	-0.0826	-0.0749
127	-0.0076	-0.0909	-0.0803

Identity — all 250 vector components

Dimension	Tiny	Base	Orange teacher
0	-0.0107	0.0127	-0.0537
1	-0.0117	0.0335	0.1185
2	-0.0356	-0.0611	-0.0600
3	-0.0739	-0.0844	-0.0196
4	0.1008	0.0747	0.2224
5	-0.0093	-0.0795	-0.0510
6	0.0231	-0.0040	0.0681
7	-0.0981	-0.2029	-0.0494
8	-0.1319	-0.1388	-0.0423
9	0.0622	0.0371	-0.0575
10	-0.0228	-0.0015	-0.0512
11	0.0200	0.0284	0.0437
12	0.0884	0.1452	0.1318
13	0.0822	0.0110	0.0385
14	0.1112	0.0563	0.0246
15	0.0238	0.0137	-0.0054
16	0.1160	0.1623	0.0782
17	-0.1064	-0.0462	-0.0586
18	-0.0266	-0.0256	-0.0497
19	0.0069	0.0200	-0.0774
20	-0.0142	-0.0515	-0.0488
21	-0.0186	-0.0267	-0.0452
22	-0.0642	-0.0121	-0.0506
23	-0.0021	-0.0264	-0.0472
24	0.0528	0.0726	-0.0417
25	-0.1485	-0.1623	-0.0897
26	-0.0266	-0.0694	-0.0538
27	-0.0798	-0.0398	-0.0396
28	-0.0687	-0.0550	-0.0528
29	0.1257	0.1698	0.1732
30	-0.0089	0.0162	-0.0424
31	0.0104	0.0005	-0.0490
32	0.0018	-0.0243	-0.0502
33	-0.0988	-0.0577	-0.0438
34	0.2210	0.1463	0.1868
35	-0.0006	0.0212	-0.0628
36	-0.0206	-0.0238	-0.0515
37	-0.0656	-0.0398	-0.0337
38	0.0515	-0.0403	-0.0477
39	-0.0074	0.0662	0.0599
40	-0.0252	-0.0308	0.0012
41	0.0230	0.0101	-0.0360
42	-0.0275	-0.0088	-0.0485
43	0.0473	0.0408	-0.0576
44	-0.0323	-0.0416	-0.0587
45	-0.0463	-0.0699	-0.0560
46	0.0313	0.0507	-0.0717
47	-0.0435	-0.0014	-0.0638
48	0.0110	-0.0304	-0.0521
49	0.0155	-0.0141	-0.0104
50	-0.0084	0.0275	-0.0005
51	-0.1188	-0.0467	-0.0494
52	-0.0306	-0.0314	-0.0481
53	0.0036	-0.0214	0.0352
54	-0.0371	-0.0371	0.0948
55	0.0780	0.0590	0.1125
56	0.0235	-0.0096	-0.0671
57	0.1727	0.2392	0.0934
58	-0.0139	-0.0406	-0.0468
59	0.0521	0.0030	0.0522
60	0.0214	0.0705	0.0697
61	-0.0266	-0.0398	-0.0453
62	-0.0383	0.0080	-0.0429
63	-0.1367	-0.0769	-0.0472
64	0.1008	0.0988	0.0298
65	-0.0663	-0.0108	-0.0595
66	0.0003	-0.0232	-0.0356
67	0.0670	0.0153	-0.0169
68	-0.0406	-0.0627	-0.0525
69	-0.0092	-0.0432	-0.0634
70	-0.0421	-0.0095	-0.0406
71	-0.0387	0.0121	0.0095
72	0.0235	-0.0016	-0.0540
73	0.1112	0.0892	0.0956
74	-0.0608	-0.0606	-0.0526
75	-0.0268	-0.0340	-0.0673
76	0.0115	0.0168	-0.0464
77	-0.0004	0.0376	-0.0756
78	0.1664	0.0977	0.0562
79	-0.0815	-0.0822	-0.0522
80	0.0168	0.0260	-0.0518
81	-0.0912	-0.0683	-0.0584
82	-0.0570	-0.0790	-0.0468
83	0.0195	0.0029	0.0224
84	-0.0919	-0.0886	-0.0734
85	-0.0392	-0.0630	-0.0521
86	-0.0173	0.0406	-0.0465
87	-0.0142	-0.0638	-0.0416
88	0.0223	0.0139	0.0252
89	-0.0407	0.0136	-0.0471
90	0.1519	0.1858	-0.0516
91	0.0753	0.0758	-0.0515
92	0.0268	-0.0259	0.1105
93	-0.0642	-0.0897	-0.0401
94	-0.0780	-0.0539	-0.0517
95	-0.0539	-0.0758	-0.0544
96	-0.0155	-0.0336	-0.0207
97	-0.0618	-0.0758	-0.0613
98	0.0632	0.1046	0.0472
99	-0.0113	0.0523	0.0272
100	0.0587	0.0526	-0.0107
101	-0.1264	-0.0678	-0.0492
102	0.0035	0.0411	-0.0287
103	0.0732	0.0358	0.0035
104	-0.0756	-0.0459	-0.0679
105	-0.0435	-0.0483	-0.0677
106	-0.0525	0.0017	-0.0401
107	0.0846	0.0419	0.0989
108	0.0423	0.0902	0.1136
109	-0.0335	-0.0100	-0.0501
110	0.0178	0.0392	0.0067
111	0.0242	0.0472	0.1012
112	-0.0480	-0.0382	-0.0421
113	0.0660	-0.0763	-0.0888
114	-0.0319	0.0063	-0.0499
115	0.0891	0.1062	0.0023
116	0.0288	-0.0113	-0.0935
117	0.1699	0.1708	0.0889
118	0.0086	-0.0352	-0.0486
119	-0.0843	-0.0387	-0.0536
120	-0.0383	0.0355	0.1401
121	-0.0135	-0.0028	-0.0446
122	-0.0245	-0.0207	-0.0188
123	-0.0632	-0.0478	-0.0538
124	-0.0371	-0.0120	-0.0519
125	0.0846	0.1041	0.0376
126	0.0832	0.0518	0.0419
127	0.0041	0.0020	-0.0290
128	-0.0017	0.0510	-0.0433
129	0.0095	-0.0162	-0.0552
130	-0.0090	-0.0547	-0.0523
131	-0.0199	-0.0053	-0.0456
132	-0.0011	-0.0304	-0.0501
133	-0.0321	0.0109	0.0177
134	-0.0981	-0.0710	-0.0992
135	-0.0309	-0.0675	-0.0524
136	0.0067	-0.0371	0.0213
137	-0.0049	0.0120	-0.0351
138	0.0114	0.0400	0.0953
139	0.0092	0.0908	0.0291
140	-0.0856	-0.0646	-0.0614
141	0.0546	0.0513	0.0061
142	0.0604	0.0585	0.0435
143	-0.0501	0.0039	0.0436
144	0.0010	0.0069	0.0210
145	-0.0149	-0.0555	-0.0344
146	-0.0354	-0.0486	-0.0624
147	0.0139	0.0315	0.0257
148	0.0300	0.0478	-0.0574
149	-0.0079	-0.0219	-0.0670
150	0.0843	-0.0019	-0.0512
151	-0.0663	-0.0382	-0.0593
152	0.0281	0.0384	0.0576
153	0.0487	0.0395	-0.0577
154	-0.0912	-0.1009	-0.0508
155	0.1706	0.1409	0.0428
156	-0.0691	-0.0204	-0.0522
157	0.0953	0.0849	0.1953
158	-0.0237	-0.0483	-0.0648
159	-0.1077	-0.0737	-0.0610
160	-0.0430	-0.0795	-0.0495
161	-0.0960	-0.0239	-0.0258
162	0.0946	0.0838	0.1606
163	0.0172	0.0153	-0.0410
164	-0.0559	-0.0817	-0.0457
165	0.1630	0.1196	0.1509
166	-0.0104	-0.0531	-0.0606
167	-0.0345	0.0083	-0.0660
168	0.0698	0.0179	-0.0736
169	0.1133	0.1495	0.0538
170	-0.0656	-0.0483	-0.0487
171	-0.0171	-0.0395	-0.0458
172	-0.0794	-0.0566	-0.0603
173	-0.0432	-0.0196	-0.0538
174	0.0618	0.0258	0.0670
175	0.0445	0.0224	-0.0495
176	0.0722	0.1441	0.1768
177	-0.0223	0.0080	0.0036
178	0.0725	0.0929	0.0021
179	-0.0437	-0.0699	-0.0641
180	-0.0680	-0.0590	-0.0596
181	-0.0760	-0.0432	-0.0742
182	-0.0594	-0.0491	-0.0450
183	-0.0649	-0.0398	0.0266
184	-0.0096	-0.0326	-0.0529
185	0.0288	0.0665	-0.0084
186	-0.0525	-0.0523	-0.0628
187	0.0299	0.0451	-0.0592
188	-0.0656	-0.0606	-0.0489
189	0.0217	-0.0190	-0.0757
190	-0.1430	-0.1538	-0.0537
191	-0.0116	-0.0148	0.0575
192	0.0442	-0.0657	-0.0630
193	0.0618	0.0254	-0.0375
194	0.0649	0.0763	0.0433
195	0.0406	0.0363	-0.0495
196	0.0746	0.0542	-0.0319
197	0.0477	0.0763	0.0488
198	-0.0347	-0.0627	-0.0503
199	0.0497	0.0145	-0.0572
200	-0.0912	-0.0416	-0.0602
201	-0.0497	-0.0121	-0.0490
202	-0.0732	-0.0742	-0.1083
203	-0.0076	0.1057	0.1006
204	-0.0615	0.0849	-0.0609
205	-0.1209	-0.0865	-0.0906
206	-0.0110	-0.0210	-0.0051
207	-0.0608	-0.0382	-0.0347
208	-0.0556	-0.0507	-0.0540
209	0.0025	0.0131	0.0157
210	-0.0166	-0.0833	-0.0677
211	-0.0014	0.0304	0.0171
212	-0.0483	-0.0913	-0.0493
213	0.0825	0.0215	-0.0682
214	0.0919	-0.0137	0.0417
215	-0.0791	-0.0031	-0.0351
216	-0.0542	-0.1255	-0.0623
217	0.0171	0.0934	0.0715
218	-0.0470	-0.0472	-0.0604
219	-0.0221	-0.0275	0.0409
220	-0.0597	0.0012	-0.0575
221	0.0404	0.0326	0.0036
222	-0.0445	-0.0156	-0.0610
223	0.0570	0.0486	-0.0051
224	0.0122	-0.0360	-0.0475
225	0.0004	0.0039	-0.0433
226	-0.0622	-0.0338	-0.0841
227	0.0111	0.1057	-0.0099
228	-0.1361	-0.0587	-0.0843
229	0.0155	0.0505	-0.0571
230	-0.0125	-0.0087	-0.0133
231	-0.0099	0.0085	-0.0126
232	-0.0174	-0.0087	-0.0343
233	-0.0402	-0.0427	-0.0528
234	0.0542	0.0223	0.0149
235	-0.0147	-0.0472	-0.0428
236	-0.0774	-0.0521	-0.0447
237	-0.0193	0.0168	-0.0481
238	0.0190	0.0158	0.0190
239	-0.0173	-0.0619	-0.0538
240	-0.0387	-0.0545	-0.0531
241	-0.0656	-0.0137	0.0349
242	0.0017	-0.0025	-0.0269
243	0.0245	-0.0502	-0.0062
244	-0.0249	0.0662	0.0043
245	0.0539	-0.0203	-0.0495
246	0.0318	0.0019	0.0953
247	-0.0570	-0.0218	-0.0438
248	-0.0104	0.0066	0.1053
249	-0.0409	-0.0571	-0.0921

Source: Emolia / Emilia source archive · SHA-256 f8620d4ec74feea8…

e04EnglishEmolia / Emilia

Emolia EN · EN_B00000_S00280_W000023

Natural speech · Original speech · 7.3 s

Very perverted character and a few too many breast references that make it feel a little puerile but it still hits most of the marks.

Tiny Base · values are model estimates, not ground truth

Strongest emotions relative to training

Concentration

z +0.90 / +1.09raw 1.30 / 1.44

Contemplation

z +0.29 / +0.93raw 0.26 / 0.64

Contentment

z +0.74 / +0.25raw 0.38 / 0.13

Teasing

z +0.73 / +0.24raw 0.40 / 0.13

Emotional Numbness

z +0.28 / +0.59raw 0.26 / 0.54

Hope Enthusiasm Optimism

z +0.47 / -0.03raw 0.48 / 0.09

Interest

z +0.46 / +0.39raw 2.00 / 1.95

The center of each bar is the S9 teacher median. Positive z is to the right; negative z is to the left. Ranking uses z, not raw teacher units.

Strongest VoiceNet dimensions relative to training

Newsreader style (S_NEWS)

z +2.63 / +3.10raw 1.90 / 2.17

Fullness (FULL)

z +2.10 / +2.25raw 3.64 / 3.78

Authoritative style (S_AUTH)

z +1.83 / +2.06raw 3.00 / 3.23

Formal style (S_FORM)

z +1.96 / +1.79raw 3.20 / 3.03

Mixed resonance (R_MIXD)

z +1.84 / +1.95raw 2.98 / 3.08

Speech structure (STRU)

z +1.66 / +1.90raw 3.73 / 3.95

Background noise (BKGN)

z +1.68 / +1.78raw 3.98 / 4.06

All 57 VoiceNet predictions, including raw units, are in the full table below. These seven are ranked by z; the top values may differ from the strongest raw dimensions.

Voice, speed and quality scores in context

Genuineness (0–6)z -1.04 / -1.07raw 0.65 / 0.59

Vocal-burst blend (0–10)z -1.59 / -1.73raw 2.31 / 1.93

Content enjoyment (CE)z +1.54 / +1.51raw 6.37 / 6.34

Production quality (PQ)z +0.72 / +0.60raw 7.68 / 7.57

Speech signal quality, calibratedz +0.37 / +0.20raw 3.68 / 3.59

Background quality, calibratedz +0.42 / +0.51raw 3.78 / 3.86

Overall quality, calibratedz +0.66 / +0.68raw 3.24 / 3.25

P.808 MOS estimatez +1.22 / +1.22raw 4.03 / 4.03

score content enjoymentz +1.26 / +1.26raw 4.89 / 4.89

score overall qualityz +0.54 / +0.58raw 2.92 / 2.94

Background Noisez -1.92 / -2.60raw 0.30 / 0.12

Tempo (TEMP)z +0.83 / +1.09raw 3.11 / 3.42

Arousal (AROU)z +0.27 / +0.30raw 2.66 / 2.70

Valence (VALN)z +0.39 / +0.50raw 2.77 / 2.89

Recording quality (RCQL)z +1.36 / +1.36raw 3.96 / 3.96

Background noise (BKGN)z +1.68 / +1.78raw 3.98 / 4.06

talking speedz +2.23 / +2.82raw 17.40 / 19.62

Characters per second (CPS): 18.20 raw · z +2.44

Orange speaker embedding reconstruction

Cosine against Orange on this same clip (higher means closer to that teacher vector):

Embedding	Tiny	Base
Timbre · 128D	0.816	0.758
Identity · 250D	0.437	0.465

Vocal-burst regions

Tiny

Base

0 s7.3 s

Verified burst intervals are unavailable for this clip.

Tiny: 0 regions, count-head estimate 0.00; Base: 0 regions, count-head estimate 0.00.

Exact predicted start and end times

Model	Region	Start (s)	End (s)	Duration (s)

All 192 score slots · raw and z values

#	Target	Tiny raw	Tiny z	Base raw	Base z	Train median	Train SD
Emotion scores Forty clip-level Empathic Insight emotion teacher outputs. Each row evaluates one named emotion score.
0	Affectionemo_Affection	0.134	+0.22	-0.001	-0.01	0.007	0.570
1	Amusementemo_Amusement	0.305	+0.35	0.098	+0.11	-0.001	0.885
2	Angeremo_Anger	0.025	+0.03	-0.002	-0.01	0.004	0.613
3	Astonishment Surpriseemo_Astonishment_Surprise	0.074	+0.12	0.028	+0.04	0.005	0.572
4	Aweemo_Awe	0.024	+0.06	0.012	+0.03	0.000	0.427
5	Bitternessemo_Bitterness	0.014	+0.00	0.016	+0.01	0.013	0.415
6	Concentrationemo_Concentration	1.304	+0.90	1.441	+1.09	0.634	0.741
7	Confusionemo_Confusion	0.041	+0.07	0.058	+0.11	0.001	0.540
8	Contemplationemo_Contemplation	0.256	+0.29	0.637	+0.93	0.082	0.598
9	Contemptemo_Contempt	0.036	+0.08	0.027	+0.06	-0.000	0.464
10	Contentmentemo_Contentment	0.379	+0.74	0.131	+0.25	0.000	0.514
11	Disappointmentemo_Disappointment	0.090	+0.13	-0.003	-0.00	0.000	0.700
12	Disgustemo_Disgust	0.026	+0.04	0.007	-0.00	0.007	0.489
13	Distressemo_Distress	0.065	+0.08	0.009	+0.01	0.000	0.821
14	Doubtemo_Doubt	0.034	+0.06	0.154	+0.32	0.006	0.466
15	Elationemo_Elation	0.270	+0.35	0.062	+0.07	0.012	0.728
16	Embarrassmentemo_Embarrassment	-0.013	-0.13	-0.039	-0.19	0.043	0.430
17	Emotional Numbnessemo_Emotional_Numbness	0.265	+0.28	0.543	+0.59	0.004	0.917
18	Fatigue Exhaustionemo_Fatigue_Exhaustion	0.030	+0.00	0.002	-0.05	0.028	0.539
19	Fearemo_Fear	0.046	+0.05	0.061	+0.08	0.015	0.610
20	Helplessnessemo_Helplessness	0.008	+0.02	0.013	+0.02	-0.004	0.696
21	Hope Enthusiasm Optimismemo_Hope_Enthusiasm_Optimism	0.477	+0.47	0.092	-0.03	0.117	0.760
22	Impatience and Irritabilityemo_Impatience_and_Irritability	0.006	-0.20	0.025	-0.18	0.149	0.705
23	Infatuationemo_Infatuation	-0.013	+0.00	-0.024	-0.02	-0.015	0.533
24	Interestemo_Interest	2.003	+0.46	1.945	+0.39	1.589	0.907
25	Intoxication Altered States of Consciousnessemo_Intoxication_Altered_States_of_Consciousness	-0.047	-0.04	-0.045	-0.04	-0.025	0.559
26	Jealousy and Envyemo_Jealousy_and_Envy	0.041	-0.04	0.072	+0.03	0.059	0.442
27	Longingemo_Longing	-0.002	-0.14	0.005	-0.13	0.087	0.632
28	Malevolence Maliceemo_Malevolence_Malice	0.036	-0.04	0.024	-0.06	0.055	0.534
29	Painemo_Pain	0.032	+0.06	-0.004	-0.00	-0.002	0.579
30	Pleasure Ecstasyemo_Pleasure_Ecstasy	0.196	+0.29	0.016	-0.00	0.017	0.614
31	Prideemo_Pride	0.006	+0.01	0.017	+0.03	0.002	0.509
32	Reliefemo_Relief	0.051	+0.03	-0.017	-0.07	0.033	0.681
33	Sadnessemo_Sadness	0.056	+0.07	0.002	+0.00	0.000	0.759
34	Sexual Lustemo_Sexual_Lust	0.145	+0.23	-0.029	-0.12	0.030	0.494
35	Shameemo_Shame	0.010	-0.01	0.006	-0.01	0.013	0.510
36	Sournessemo_Sourness	0.018	+0.05	0.023	+0.06	-0.005	0.439
37	Teasingemo_Teasing	0.399	+0.73	0.131	+0.24	0.000	0.545
38	Thankfulness Gratitudeemo_Thankfulness_Gratitude	0.075	+0.05	0.052	+0.01	0.041	0.697
39	Triumphemo_Triumph	0.000	+0.01	-0.011	-0.01	-0.007	0.521
VoiceNet dimensions Fifty-seven VoiceNet voice, delivery, style, and recording dimensions. Codes are expanded in the target column.
40	Perceived voice age (AGEV)vn_AGEV_reg	3.469	+0.39	3.292	+0.25	2.984	1.238
41	Arousal (AROU)vn_AROU_reg	2.664	+0.27	2.702	+0.30	2.359	1.147
42	Arousal shift (ARSH)vn_ARSH_reg	3.190	+0.70	3.180	+0.69	2.580	0.867
43	Vocal attack (ATCK)vn_ATCK_reg	2.461	+0.23	2.376	+0.17	2.162	1.295
44	Background noise (BKGN)vn_BKGN_reg	3.982	+1.68	4.059	+1.78	2.703	0.761
45	Brightness (BRGT)vn_BRGT_reg	2.185	+0.24	2.382	+0.48	1.991	0.813
46	Speech chunking (CHNK)vn_CHNK_reg	3.586	+1.40	3.820	+1.59	1.847	1.239
47	Articulation clarity (CLRT)vn_CLRT_reg	3.493	+1.56	3.441	+1.51	2.018	0.945
48	Cognitive load (COGL)vn_COGL_reg	0.934	-1.09	1.025	-1.01	2.094	1.061
49	Dynamic arc (DARC)vn_DARC_reg	1.794	+0.13	1.701	+0.06	1.615	1.380
50	Disfluency (DFLU)vn_DFLU_reg	1.209	-1.08	1.043	-1.22	2.488	1.184
51	Emphasis (EMPH)vn_EMPH_reg	2.902	+0.19	2.804	+0.13	2.607	1.524
52	Esthetics (ESTH)vn_ESTH_reg	3.749	+1.72	3.499	+1.40	2.402	0.782
53	Content appropriateness (EXPL)vn_EXPL_reg	0.607	+1.62	0.554	+1.45	0.086	0.322
54	Focus (FOCS)vn_FOCS_reg	3.672	+1.21	3.741	+1.27	2.344	1.102
55	Fullness (FULL)vn_FULL_reg	3.642	+2.10	3.780	+2.25	1.778	0.889
56	Perceived gender (GEND)vn_GEND_reg	4.721	+0.42	4.883	+0.52	4.055	1.588
57	Harmonicity (HARM)vn_HARM_reg	2.407	-0.09	2.811	+0.40	2.480	0.836
58	Metallic character (METL)vn_METL_reg	1.538	-0.09	1.804	+0.19	1.621	0.958
59	Pitch range (RANG)vn_RANG_reg	3.273	+0.40	3.316	+0.45	2.914	0.897
60	Recording quality (RCQL)vn_RCQL_reg	3.961	+1.36	3.961	+1.36	2.754	0.888
61	Vocal register (REGS)vn_REGS_reg	0.785	-0.33	0.893	-0.24	1.198	1.268
62	Respiration (RESP)vn_RESP_reg	1.501	-1.12	1.384	-1.23	2.680	1.056
63	Roughness (ROUG)vn_ROUG_reg	1.454	-0.65	1.437	-0.67	2.033	0.887
64	Chest resonance (R_CHST)vn_R_CHST_reg	3.268	+1.34	3.275	+1.35	2.135	0.844
65	Head resonance (R_HEAD)vn_R_HEAD_reg	2.552	+0.49	2.684	+0.65	2.148	0.822
66	Mask resonance (R_MASK)vn_R_MASK_reg	2.770	+0.86	2.866	+0.95	1.908	1.005
67	Mixed resonance (R_MIXD)vn_R_MIXD_reg	2.985	+1.84	3.076	+1.95	1.436	0.841
68	Nasal resonance (R_NASL)vn_R_NASL_reg	3.079	+0.27	3.172	+0.36	2.791	1.047
69	Oral resonance (R_ORAL)vn_R_ORAL_reg	2.577	+0.53	2.661	+0.64	2.184	0.741
70	Throat resonance (R_THRT)vn_R_THRT_reg	2.552	+0.60	2.537	+0.58	2.070	0.803
71	Smoothness (SMTH)vn_SMTH_reg	3.791	+1.51	3.678	+1.40	2.143	1.093
72	Stance (STNC)vn_STNC_reg	2.957	+0.28	2.997	+0.32	2.633	1.137
73	Speech structure (STRU)vn_STRU_reg	3.732	+1.66	3.955	+1.90	2.137	0.958
74	ASMR style (S_ASMR)vn_S_ASMR_reg	0.898	-0.33	0.758	-0.43	1.370	1.411
75	Authoritative style (S_AUTH)vn_S_AUTH_reg	2.997	+1.83	3.232	+2.06	1.088	1.043
76	Cartoonish style (S_CART)vn_S_CART_reg	0.749	-0.58	0.578	-0.70	1.560	1.401
77	Casual style (S_CASU)vn_S_CASU_reg	3.083	-0.56	3.240	-0.43	3.793	1.278
78	Conversational style (S_CONV)vn_S_CONV_reg	3.298	+0.53	3.441	+0.64	2.594	1.318
79	Dramatic style (S_DRAM)vn_S_DRAM_reg	3.093	+0.32	3.104	+0.33	2.721	1.148
80	Formal style (S_FORM)vn_S_FORM_reg	3.199	+1.96	3.026	+1.79	1.195	1.021
81	Monologue style (S_MONO)vn_S_MONO_reg	2.938	+0.09	2.786	-0.03	2.824	1.284
82	Narrator style (S_NARR)vn_S_NARR_reg	3.729	+1.67	3.661	+1.63	1.307	1.446
83	Newsreader style (S_NEWS)vn_S_NEWS_reg	1.899	+2.63	2.166	+3.10	0.408	0.568
84	Playful style (S_PLAY)vn_S_PLAY_reg	2.547	+0.15	2.596	+0.19	2.352	1.315
85	Ranting or angry style (S_RANT)vn_S_RANT_reg	1.003	-0.16	0.978	-0.18	1.213	1.289
86	Storytelling style (S_STRY)vn_S_STRY_reg	3.643	+0.85	3.431	+0.70	2.480	1.366
87	Teacher or didactic style (S_TECH)vn_S_TECH_reg	1.135	+0.40	1.490	+0.69	0.646	1.227
88	Whispered talking style (S_WHIS)vn_S_WHIS_reg	2.710	+0.69	2.585	+0.61	1.597	1.618
89	Tempo (TEMP)vn_TEMP_reg	3.109	+0.83	3.419	+1.09	2.117	1.190
90	Tension (TENS)vn_TENS_reg	1.762	+0.24	1.802	+0.29	1.559	0.852
91	Valence (VALN)vn_VALN_reg	2.769	+0.39	2.888	+0.50	2.328	1.118
92	Valence shift (VALS)vn_VALS_reg	2.747	+0.21	2.916	+0.37	2.518	1.079
93	Velocity flux (VFLX)vn_VFLX_reg	2.876	+0.51	3.093	+0.69	2.256	1.208
94	Volatility (VOLT)vn_VOLT_reg	2.009	-0.65	2.169	-0.47	2.586	0.886
95	Vulnerability (VULN)vn_VULN_reg	2.309	-0.35	2.090	-0.57	2.648	0.984
96	Warmth (WARM)vn_WARM_reg	3.595	+1.12	3.422	+0.93	2.578	0.909
Genuineness, blend, and legacy quality Genuineness and vocal-burst blend are predicted. R_quality has Ladder training labels but no valid P3 test labels.
97	Genuineness (0–6)genuineness_0_6	0.654	-1.04	0.591	-1.07	2.332	1.621
98	Vocal-burst blend (0–10)blend_0_10	2.312	-1.59	1.930	-1.73	6.676	2.738
99	Legacy R_quality (no P3 test labels)R_quality	0.355	-2.19	0.314	-2.31	1.095	0.338
Empathic Insight Plus extra scores Nineteen additional clip-level teacher scores, including background noise and content enjoyment.
100	Ageeiv_extra:Age	3.253	+0.01	3.339	+0.30	3.250	0.293
101	Arousaleiv_extra:Arousal	1.203	-0.20	1.019	-0.62	1.289	0.435
102	Authenticityeiv_extra:Authenticity	2.807	+0.91	2.774	+0.70	2.667	0.153
103	Background Noiseeiv_extra:Background_Noise	0.301	-1.92	0.121	-2.60	0.808	0.264
104	Confident vs. Hesitanteiv_extra:Confident_vs._Hesitant	0.952	-0.29	1.059	+0.06	1.040	0.303
105	Gendereiv_extra:Gender	-0.795	-0.17	-0.853	-0.23	-0.621	0.999
106	High-Pitched vs. Low-Pitchedeiv_extra:High-Pitched_vs._Low-Pitched	1.935	+0.43	1.969	+0.56	1.827	0.250
107	Monotone vs. Expressiveeiv_extra:Monotone_vs._Expressive	1.772	-0.19	1.632	-0.48	1.859	0.470
108	Recording Qualityeiv_extra:Recording_Quality	2.707	+1.70	2.738	+1.79	2.144	0.332
109	Serious vs. Humorouseiv_extra:Serious_vs._Humorous	1.147	+0.64	1.086	+0.46	0.929	0.340
110	Soft vs. Harsheiv_extra:Soft_vs._Harsh	0.287	+0.02	0.191	-0.28	0.281	0.320
111	Submissive vs. Dominanteiv_extra:Submissive_vs._Dominant	0.325	-0.16	0.194	-0.56	0.376	0.324
112	Valenceeiv_extra:Valence	0.116	+0.29	-0.024	-0.08	0.005	0.380
113	Vulnerable vs. Emotionally Detachedeiv_extra:Vulnerable_vs._Emotionally_Detached	2.433	+1.64	2.440	+1.66	1.715	0.437
114	Warm vs. Coldeiv_extra:Warm_vs._Cold	0.206	+0.52	0.140	+0.30	0.051	0.300
115	score background qualityeiv_extra:score_background_quality	3.496	+0.28	3.524	+0.32	3.301	0.693
116	score content enjoymenteiv_extra:score_content_enjoyment	4.890	+1.26	4.888	+1.26	4.507	0.303
117	score overall qualityeiv_extra:score_overall_quality	2.923	+0.54	2.945	+0.58	2.652	0.507
118	score speech qualityeiv_extra:score_speech_quality	1.901	+0.64	1.950	+0.98	1.808	0.146
Meta AudioBox Aesthetics Four AudioBox aesthetic teacher outputs. Expansions follow the official Meta model card.
119	Content enjoyment (CE)audiobox:CE	6.372	+1.54	6.340	+1.51	4.799	1.018
120	Content usefulness (CU)audiobox:CU	7.236	+1.59	7.244	+1.59	5.649	1.001
121	Production complexity (PC)audiobox:PC	2.041	-0.18	1.820	-0.32	2.331	1.617
122	Production quality (PQ)audiobox:PQ	7.679	+0.72	7.572	+0.60	7.044	0.879
Microsoft DNSMOS Seven DNSMOS teacher outputs: raw and calibrated SIG/BAK/OVRL estimates plus P.808 MOS.
123	Speech signal quality, rawdnsmos:SIG_raw	4.238	+0.51	4.097	+0.29	3.900	0.669
124	Background quality, rawdnsmos:BAK_raw	3.907	+0.62	4.034	+0.73	3.211	1.124
125	Overall quality, rawdnsmos:OVRL_raw	3.726	+0.79	3.742	+0.81	3.085	0.812
126	Speech signal quality, calibrateddnsmos:SIG	3.675	+0.37	3.587	+0.20	3.488	0.501
127	Background quality, calibrateddnsmos:BAK	3.781	+0.42	3.865	+0.51	3.389	0.928
128	Overall quality, calibrateddnsmos:OVRL	3.243	+0.66	3.250	+0.68	2.840	0.606
129	P.808 MOS estimatednsmos:P808_MOS	4.027	+1.22	4.027	+1.22	3.421	0.496
Vocal-burst count The regression target is log(1 + count). A separate table also reports count error after inverse transformation.
130	Vocal-burst count, log(1 + count)burst_count_log1p	0.002	+0.00	-0.008	-0.01	0.000	0.647
VoiceCLAP attributes Sixty-one individual VoiceCLAP attribute teacher scores. The raw 768D VoiceCLAP embedding is stored in sidecars but is not a model output.
131	Affectionvoiceclap_attribute:Affection	0.773	-0.31	0.485	-0.83	0.947	0.554
132	Agevoiceclap_attribute:Age	3.187	-0.08	3.199	-0.05	3.229	0.547
133	Amusementvoiceclap_attribute:Amusement	0.461	+0.12	0.443	+0.09	0.392	0.572
134	Angervoiceclap_attribute:Anger	0.529	-0.92	0.702	-0.57	0.992	0.506
135	Arousalvoiceclap_attribute:Arousal	1.294	-0.20	1.452	+0.05	1.420	0.622
136	Astonishment Surprisevoiceclap_attribute:Astonishment_Surprise	0.383	-0.26	0.550	+0.09	0.509	0.479
137	Authenticityvoiceclap_attribute:Authenticity	2.820	+0.30	2.852	+0.49	2.770	0.167
138	Awevoiceclap_attribute:Awe	0.485	-0.21	0.520	-0.07	0.539	0.259
139	Background Noisevoiceclap_attribute:Background_Noise	0.210	-1.36	0.226	-1.29	0.567	0.264
140	Bitternessvoiceclap_attribute:Bitterness	0.270	-1.37	0.305	-1.22	0.592	0.236
141	Concentrationvoiceclap_attribute:Concentration	1.250	+0.07	1.230	+0.03	1.214	0.531
142	Confident vs. Hesitantvoiceclap_attribute:Confident_vs._Hesitant	0.833	-0.50	0.866	-0.43	1.069	0.468
143	Confusionvoiceclap_attribute:Confusion	0.022	-1.86	0.058	-1.75	0.643	0.334
144	Contemplationvoiceclap_attribute:Contemplation	0.392	-0.96	0.436	-0.85	0.780	0.406
145	Contemptvoiceclap_attribute:Contempt	0.490	-0.65	0.474	-0.69	0.709	0.339
146	Contentmentvoiceclap_attribute:Contentment	0.497	-0.30	0.503	-0.28	0.588	0.307
147	Disappointmentvoiceclap_attribute:Disappointment	0.370	-1.34	0.498	-0.90	0.760	0.291
148	Disgustvoiceclap_attribute:Disgust	0.412	-1.03	0.437	-0.90	0.625	0.207
149	Distressvoiceclap_attribute:Distress	0.352	-1.64	0.382	-1.56	0.927	0.350
150	Doubtvoiceclap_attribute:Doubt	0.154	-2.02	0.199	-1.79	0.535	0.188
151	Elationvoiceclap_attribute:Elation	0.626	+0.22	0.672	+0.33	0.539	0.397
152	Embarrassmentvoiceclap_attribute:Embarrassment	0.149	-0.50	0.162	-0.46	0.307	0.314
153	Emotional Numbnessvoiceclap_attribute:Emotional_Numbness	0.671	+0.03	0.704	+0.15	0.664	0.266
154	Fatigue Exhaustionvoiceclap_attribute:Fatigue_Exhaustion	-0.002	-1.78	0.081	-1.46	0.462	0.261
155	Fearvoiceclap_attribute:Fear	0.471	-0.69	0.381	-1.12	0.618	0.212
156	Gendervoiceclap_attribute:Gender	-0.532	-0.38	-0.716	-0.56	-0.151	1.005
157	Helplessnessvoiceclap_attribute:Helplessness	0.145	-1.91	0.223	-1.62	0.658	0.268
158	High-Pitched vs. Low-Pitchedvoiceclap_attribute:High-Pitched_vs._Low-Pitched	1.979	+0.37	1.938	+0.26	1.840	0.375
159	Hope Enthusiasm Optimismvoiceclap_attribute:Hope_Enthusiasm_Optimism	0.849	+0.36	1.013	+0.78	0.705	0.396
160	Impatience and Irritabilityvoiceclap_attribute:Impatience_and_Irritability	0.349	-1.30	0.618	-0.80	1.052	0.541
161	Infatuationvoiceclap_attribute:Infatuation	0.501	-0.32	0.584	-0.07	0.608	0.332
162	Interestvoiceclap_attribute:Interest	2.089	+1.12	1.983	+0.87	1.598	0.440
163	Intoxication Altered States of Consciousnessvoiceclap_attribute:Intoxication_Altered_States_of_Consciousness	0.017	-1.05	0.115	-0.84	0.502	0.463
164	Jealousy & Envyvoiceclap_attribute:Jealousy_&_Envy	0.277	-1.00	0.407	-0.47	0.523	0.245
165	Longingvoiceclap_attribute:Longing	0.252	-1.30	0.287	-1.14	0.538	0.220
166	Malevolence Malicevoiceclap_attribute:Malevolence_Malice	0.583	-0.72	0.535	-0.86	0.833	0.346
167	Monotone vs. Expressivevoiceclap_attribute:Monotone_vs._Expressive	1.659	-0.20	1.670	-0.18	1.775	0.594
168	Painvoiceclap_attribute:Pain	0.146	-1.08	0.186	-0.90	0.381	0.218
169	Pleasure Ecstasyvoiceclap_attribute:Pleasure_Ecstasy	0.376	-0.42	0.471	-0.11	0.503	0.301
170	Pridevoiceclap_attribute:Pride	0.427	-1.01	0.476	-0.87	0.780	0.349
171	Recording Qualityvoiceclap_attribute:Recording_Quality	2.912	+1.83	2.887	+1.75	2.313	0.328
172	Reliefvoiceclap_attribute:Relief	0.559	-1.12	0.691	-0.80	1.025	0.415
173	Sadnessvoiceclap_attribute:Sadness	0.420	-1.06	0.447	-0.97	0.752	0.313
174	Serious vs. Humorousvoiceclap_attribute:Serious_vs._Humorous	0.909	+0.19	0.791	-0.02	0.803	0.568
175	Sexual Lustvoiceclap_attribute:Sexual_Lust	0.474	-0.38	0.564	-0.17	0.635	0.419
176	Shamevoiceclap_attribute:Shame	0.075	-1.60	0.198	-1.16	0.526	0.283
177	Soft vs. Harshvoiceclap_attribute:Soft_vs._Harsh	0.283	+0.34	0.144	-0.04	0.160	0.360
178	Sournessvoiceclap_attribute:Sourness	0.390	-1.09	0.545	-0.55	0.706	0.291
179	Submissive vs. Dominantvoiceclap_attribute:Submissive_vs._Dominant	0.499	-0.35	0.628	+0.01	0.623	0.359
180	Teasingvoiceclap_attribute:Teasing	0.612	+0.19	0.640	+0.26	0.540	0.379
181	Thankfulness Gratitudevoiceclap_attribute:Thankfulness_Gratitude	1.096	-0.54	1.299	-0.16	1.384	0.529
182	Triumphvoiceclap_attribute:Triumph	0.356	-1.00	0.375	-0.95	0.716	0.359
183	Valencevoiceclap_attribute:Valence	0.434	+0.69	0.281	+0.45	-0.007	0.635
184	Vulnerable vs. Emotionally Detachedvoiceclap_attribute:Vulnerable_vs._Emotionally_Detached	2.430	+1.42	2.295	+1.18	1.638	0.556
185	Warm vs. Coldvoiceclap_attribute:Warm_vs._Cold	0.371	+1.09	0.241	+0.77	-0.066	0.400
186	durationvoiceclap_attribute:duration	8.271	-0.42	7.528	-0.53	10.914	6.354
187	score background qualityvoiceclap_attribute:score_background_quality	3.517	+0.55	3.599	+0.71	3.245	0.498
188	score content enjoymentvoiceclap_attribute:score_content_enjoyment	5.011	+2.42	5.048	+2.67	4.656	0.147
189	score overall qualityvoiceclap_attribute:score_overall_quality	2.884	+0.60	3.029	+0.95	2.635	0.412
190	score speech qualityvoiceclap_attribute:score_speech_quality	1.960	+0.99	1.983	+1.33	1.891	0.069
191	talking speedvoiceclap_attribute:talking_speed	17.397	+2.23	19.624	+2.82	9.028	3.756

All Orange embedding components

The cosine above is the meaningful vector-level comparison; component values have no standalone semantic label.

Timbre — all 128 vector components

Dimension	Tiny	Base	Orange teacher
0	0.1223	0.1484	0.1231
1	-0.1168	-0.0711	-0.1025
2	0.0471	0.0635	0.0450
3	-0.1168	-0.1246	-0.1046
4	0.1968	0.2015	0.1531
5	-0.0016	0.0220	-0.0231
6	0.0639	0.0540	0.0811
7	-0.0612	-0.0873	-0.0945
8	-0.0475	-0.0599	0.0787
9	0.0670	0.0800	0.0744
10	-0.0724	-0.0788	0.0042
11	-0.1339	-0.0947	-0.0468
12	0.0347	0.0449	0.0389
13	-0.0950	-0.0983	-0.1019
14	0.1599	0.2223	0.1390
15	-0.0646	-0.0635	-0.0925
16	-0.0553	-0.0721	-0.0378
17	0.0922	0.0837	0.1158
18	0.0485	0.0702	0.0536
19	-0.0594	-0.0812	-0.0687
20	-0.1360	-0.1331	-0.1033
21	0.0957	0.0522	0.1526
22	-0.0458	-0.0231	-0.0742
23	-0.1503	-0.1356	-0.0894
24	-0.0724	-0.0824	-0.0833
25	-0.0871	-0.0788	-0.0906
26	0.1004	0.0660	-0.0118
27	-0.0420	-0.0534	-0.0367
28	-0.0991	-0.1087	-0.0085
29	0.2145	0.2162	0.1782
30	0.1763	0.1942	0.0881
31	0.0854	0.0641	0.1543
32	0.1940	0.1228	0.1316
33	0.0758	0.1130	0.0623
34	-0.0401	-0.0026	0.0047
35	0.0004	-0.0278	-0.1118
36	0.1531	0.1808	0.1578
37	-0.0169	-0.0064	-0.0058
38	-0.0319	-0.0038	-0.0425
39	-0.0121	0.0257	-0.0062
40	-0.0635	-0.0653	-0.0304
41	-0.0040	0.0773	-0.0086
42	0.0337	-0.0504	0.0765
43	-0.1004	-0.0959	-0.1062
44	0.0135	0.0052	0.1060
45	-0.0214	-0.0313	-0.0399
46	0.0432	0.0295	0.0884
47	-0.0635	-0.0681	-0.0657
48	-0.0362	-0.0182	-0.0560
49	-0.0888	-0.0766	-0.0662
50	0.0591	0.0111	0.0638
51	-0.1209	-0.1093	-0.1031
52	-0.0239	0.0226	0.0865
53	-0.0902	-0.0989	-0.1052
54	0.1209	0.0934	0.0766
55	-0.0991	-0.1075	-0.0993
56	0.0540	0.0739	0.1753
57	-0.0112	-0.0051	-0.0487
58	-0.0998	-0.1124	-0.1004
59	-0.0085	-0.0650	0.0335
60	0.0381	0.0886	-0.0854
61	-0.0765	-0.0867	-0.0820
62	-0.0290	-0.0051	0.0248
63	0.0244	0.0269	-0.0351
64	-0.0153	0.0155	-0.0445
65	0.0478	0.0385	0.0259
66	0.1940	0.1600	0.1332
67	0.0977	0.0928	0.1042
68	0.0680	0.0565	0.0168
69	-0.1093	-0.0788	-0.0945
70	-0.0625	-0.0632	-0.1069
71	0.0161	0.0144	0.0029
72	-0.0224	0.0209	-0.0770
73	0.1285	0.1417	0.0031
74	-0.0697	-0.0892	-0.0426
75	0.2159	0.2296	0.1823
76	-0.0196	-0.0574	-0.1001
77	-0.0741	-0.0873	-0.0792
78	-0.0225	-0.0108	-0.0404
79	-0.1073	-0.1069	-0.0895
80	0.2637	0.2565	0.2336
81	-0.0929	-0.0934	-0.0935
82	0.0219	0.0776	-0.0148
83	0.0058	0.0034	-0.0499
84	-0.0357	0.0067	0.0299
85	-0.0004	0.0006	0.0640
86	0.0192	0.0264	0.0117
87	-0.0408	-0.0745	0.0146
88	0.0724	0.0344	0.0866
89	0.0738	0.0365	0.0427
90	0.0307	0.1160	-0.0643
91	0.0526	0.0092	0.0061
92	-0.0868	-0.0760	-0.0671
93	-0.0871	-0.0837	-0.1008
94	-0.0139	-0.0065	-0.0722
95	-0.0478	-0.0068	-0.0285
96	-0.0902	-0.1301	-0.0983
97	-0.1209	-0.0818	-0.1103
98	0.0006	-0.0776	0.0803
99	-0.0425	-0.0176	-0.0956
100	0.1414	0.0947	0.1138
101	0.0220	0.0368	0.0594
102	-0.0362	-0.0360	0.0890
103	-0.1155	-0.0782	-0.0693
104	0.0253	0.0672	0.1016
105	-0.0902	-0.1038	-0.0546
106	-0.0799	-0.0782	-0.0628
107	0.1291	0.0922	0.0708
108	0.1107	0.0739	0.1138
109	-0.0963	-0.1160	-0.1013
110	0.0016	-0.0363	0.1373
111	-0.0378	-0.0431	-0.0713
112	-0.0553	-0.0208	-0.1017
113	0.0232	0.0452	-0.0028
114	-0.0430	-0.0403	-0.0054
115	-0.1052	-0.0730	-0.0978
116	-0.0868	-0.0550	-0.0884
117	-0.0506	-0.0941	0.0470
118	0.0124	0.0168	0.0604
119	0.0331	0.0342	0.0630
120	0.1346	0.0641	0.0085
121	-0.1462	-0.1515	-0.1046
122	0.0700	0.0760	0.2295
123	-0.0758	-0.0849	-0.1050
124	0.0827	0.1008	0.0975
125	-0.0301	-0.0051	-0.0768
126	-0.0687	-0.0910	-0.0889
127	0.0237	0.0020	-0.0438

Identity — all 250 vector components

Dimension	Tiny	Base	Orange teacher
0	-0.0811	-0.0590	0.0321
1	0.0058	-0.0173	-0.0482
2	0.0177	0.1034	0.1159
3	-0.0551	-0.0290	0.0413
4	-0.0411	-0.0583	-0.0453
5	-0.0127	0.0096	0.0475
6	-0.0015	-0.0396	0.0273
7	0.1505	0.1370	0.0511
8	0.0048	-0.0143	0.0142
9	-0.0007	-0.0335	-0.0820
10	-0.0338	-0.0691	0.0292
11	-0.0326	-0.0517	-0.0674
12	0.0334	0.0193	-0.0039
13	-0.0776	-0.0175	-0.0440
14	-0.0124	-0.0182	-0.0712
15	0.0815	0.0431	0.0042
16	0.0679	0.1763	-0.0031
17	0.0299	-0.0312	0.0538
18	0.0547	0.0431	-0.0508
19	-0.0729	-0.0243	-0.0791
20	-0.0402	0.0176	0.1155
21	-0.0303	-0.0361	-0.0462
22	-0.0178	0.0047	-0.0517
23	0.1094	0.0996	0.0019
24	-0.0312	-0.0377	-0.0426
25	-0.0012	-0.0258	0.1543
26	-0.0628	0.0078	-0.0522
27	-0.0378	-0.0073	-0.0405
28	-0.0409	0.0093	0.0356
29	-0.0146	-0.0596	-0.0480
30	0.0392	0.0265	-0.0434
31	-0.0566	-0.0069	-0.0626
32	0.1032	0.1560	-0.0149
33	-0.0293	-0.0568	-0.0345
34	-0.0122	0.0230	-0.0243
35	0.0291	0.0104	-0.0642
36	-0.0838	-0.0469	-0.0527
37	-0.0462	-0.0732	-0.0345
38	-0.1117	-0.1002	0.0083
39	-0.0644	-0.0843	-0.0642
40	-0.0378	-0.0691	-0.0577
41	-0.1055	-0.1459	-0.0573
42	0.0148	-0.0403	-0.0495
43	0.0539	0.0385	0.0524
44	0.0334	0.0536	0.1417
45	-0.0308	-0.0691	-0.0572
46	-0.0158	-0.0128	-0.0631
47	0.0539	0.0102	0.0603
48	-0.0574	-0.0767	-0.0407
49	0.0636	0.0488	0.0292
50	-0.1272	-0.0726	-0.0533
51	-0.1210	-0.1560	-0.0505
52	0.0074	0.0189	0.0142
53	0.0850	0.0549	0.1116
54	0.0070	-0.0523	-0.0190
55	0.0425	0.0460	0.0020
56	0.0632	0.0631	-0.0355
57	0.1288	0.0517	-0.0056
58	-0.0857	-0.0634	-0.0193
59	-0.0134	-0.0523	-0.0694
60	0.0005	-0.0258	-0.0341
61	0.0021	0.0059	-0.0352
62	-0.1428	-0.1446	-0.0438
63	-0.0857	-0.0634	-0.0542
64	-0.0046	0.0312	0.0372
65	-0.0683	-0.0862	0.0305
66	-0.0671	-0.0520	0.0226
67	-0.0687	-0.1116	-0.0524
68	-0.0423	-0.0365	0.0970
69	0.0729	0.0320	0.0377
70	-0.0166	-0.0406	0.0304
71	-0.0072	-0.0396	-0.0254
72	-0.0032	0.0157	-0.0552
73	-0.0328	-0.0209	-0.0825
74	-0.0481	-0.0482	-0.0437
75	0.0605	0.0404	-0.0174
76	0.0297	0.0322	0.0078
77	0.0036	0.0154	-0.0800
78	0.0652	0.1478	-0.0352
79	-0.0388	0.0121	-0.0436
80	-0.0049	0.0025	-0.0529
81	-0.0555	-0.0536	-0.0597
82	-0.0815	-0.0796	-0.0479
83	-0.0380	0.0159	-0.0443
84	0.0122	0.0366	0.0151
85	-0.0497	-0.0989	-0.0533
86	0.0760	0.0767	-0.0323
87	0.1443	0.1370	0.0082
88	-0.1521	-0.1230	0.0282
89	-0.0035	-0.0344	-0.0226
90	0.0566	0.0672	-0.0368
91	0.0993	0.0812	0.0891
92	0.0056	-0.0166	-0.0460
93	-0.0089	-0.0167	0.0638
94	-0.0516	-0.0694	-0.0120
95	-0.0586	-0.0016	-0.0372
96	-0.1272	-0.0631	-0.0476
97	-0.0097	0.0125	0.0746
98	0.0811	-0.0140	0.0862
99	-0.0421	-0.0463	-0.0666
100	0.0055	0.0308	0.0396
101	0.0050	0.0279	-0.0498
102	-0.0421	-0.0415	0.0716
103	-0.0170	-0.0520	-0.0880
104	-0.0543	-0.0751	-0.0693
105	0.0330	0.0089	-0.0232
106	-0.0266	-0.0336	-0.0410
107	-0.0749	-0.0209	-0.0477
108	-0.0780	-0.0463	-0.0396
109	0.0481	0.0419	0.1777
110	-0.0687	-0.0777	-0.0634
111	0.0927	-0.0016	-0.0439
112	-0.0850	-0.0669	-0.0430
113	-0.0289	-0.0137	0.0474
114	0.0780	0.0131	0.1228
115	-0.0578	-0.0146	-0.0377
116	0.0570	0.0342	-0.0554
117	0.0086	0.0009	-0.0869
118	0.1125	0.1902	0.1954
119	-0.0520	-0.0580	0.0062
120	-0.0663	-0.0542	-0.0009
121	0.0106	0.0073	-0.0517
122	0.0378	-0.0055	-0.0503
123	-0.0452	-0.0357	-0.0550
124	-0.0574	-0.0682	-0.0531
125	0.1187	0.0713	0.0136
126	0.0656	0.0472	-0.0236
127	-0.0227	-0.0238	0.0553
128	-0.0500	-0.0472	-0.0663
129	-0.0737	-0.0596	-0.0565
130	-0.0224	0.0172	0.0143
131	-0.0760	-0.0729	-0.0466
132	-0.0252	-0.0130	0.0014
133	-0.0547	-0.0523	-0.0526
134	0.1397	0.0660	-0.0184
135	-0.0877	-0.1015	-0.0536
136	-0.0725	-0.0197	-0.0570
137	0.0129	-0.0317	0.0205
138	-0.0508	-0.0732	-0.0469
139	0.0547	0.1015	0.0947
140	-0.0663	-0.0780	0.0223
141	0.0908	0.0945	0.1207
142	0.0535	0.0751	-0.0451
143	-0.0033	0.0159	0.0624
144	-0.0756	-0.0428	0.1360
145	-0.0807	-0.0347	-0.0068
146	0.0574	0.0296	0.0061
147	0.0225	-0.0047	-0.0473
148	0.0038	0.0373	-0.0204
149	0.0378	0.1053	-0.0222
150	-0.0089	0.0296	-0.0376
151	0.0702	-0.0179	-0.0118
152	0.0068	0.0090	-0.0590
153	0.0469	0.0549	0.1440
154	-0.0756	-0.0843	-0.0519
155	0.0095	-0.0482	-0.0695
156	0.0217	0.0350	0.0384
157	0.1474	0.1617	0.1428
158	-0.0675	-0.0146	-0.0663
159	-0.0046	-0.0182	-0.0623
160	-0.0252	-0.0479	-0.0205
161	-0.0438	-0.0558	0.0078
162	0.0093	0.0174	-0.0618
163	0.0174	-0.0085	0.0690
164	0.0049	0.0669	0.1593
165	0.0497	-0.0036	-0.0762
166	0.0756	0.0476	0.0431
167	0.0433	0.0155	-0.0615
168	-0.0702	-0.0612	-0.0650
169	-0.1110	-0.1306	-0.0607
170	-0.0238	-0.0083	-0.0498
171	-0.0970	-0.0713	-0.0468
172	0.0092	-0.0203	0.0663
173	0.1179	0.1313	0.0116
174	0.0164	0.0431	-0.0547
175	-0.0328	-0.0095	-0.0167
176	0.0297	-0.0069	-0.0452
177	-0.0582	-0.0812	-0.0439
178	-0.0152	0.0026	0.0648
179	0.0209	0.0170	0.0755
180	0.0264	-0.0193	-0.0289
181	0.0574	0.0182	0.0506
182	0.0652	0.0656	0.2045
183	-0.0861	-0.0843	-0.1013
184	0.0336	0.0602	-0.0324
185	0.0247	0.0168	-0.0637
186	0.0047	-0.0202	-0.0004
187	0.0388	-0.0047	0.0836
188	-0.0053	-0.0290	-0.0500
189	-0.0448	-0.0729	-0.0153
190	0.0663	0.0634	0.0361
191	-0.0857	-0.0457	-0.0711
192	-0.0121	0.0453	-0.0087
193	0.1412	0.1357	0.1163
194	0.0268	0.0482	0.0244
195	0.1249	0.1452	-0.0220
196	-0.0336	0.0235	0.0077
197	0.0256	0.0311	-0.0020
198	-0.0900	-0.0628	-0.0514
199	0.0374	0.0173	-0.0112
200	-0.0341	-0.0555	-0.0492
201	0.0121	-0.0422	-0.0501
202	-0.0382	-0.0222	-0.0024
203	-0.0127	0.0013	0.0596
204	0.0057	-0.0441	0.0439
205	-0.1094	-0.1300	-0.0625
206	-0.0153	0.0271	-0.0068
207	0.0172	0.0214	-0.0504
208	-0.0617	0.0101	-0.0381
209	-0.0151	-0.0599	0.0418
210	0.0177	0.0173	0.0125
211	-0.0493	-0.0498	-0.0409
212	0.0846	0.1040	0.0050
213	0.1971	0.1592	0.1464
214	-0.0238	0.0076	-0.0671
215	0.1606	0.1287	0.1797
216	0.1032	0.0558	0.1343
217	0.0625	0.0488	0.1066
218	0.0326	0.0634	0.1395
219	-0.0485	-0.0514	-0.0197
220	-0.0535	-0.0498	-0.0587
221	-0.0539	-0.0238	0.0587
222	0.0555	0.0174	-0.0231
223	0.0130	0.0271	0.0140
224	-0.0016	-0.0158	0.0228
225	-0.0264	-0.0085	-0.0216
226	0.0729	0.0392	0.0808
227	0.0173	0.0387	0.0735
228	-0.0297	0.0171	0.0338
229	0.0487	0.0742	0.1575
230	0.0101	0.0748	0.0144
231	-0.0962	-0.0539	-0.0736
232	-0.0706	-0.0309	0.0033
233	-0.0314	0.0162	0.0914
234	0.0367	0.0205	0.0096
235	0.1203	0.1826	0.0513
236	-0.0520	-0.0517	-0.0457
237	-0.0419	-0.0212	0.0645
238	0.0095	0.0052	0.0873
239	0.0822	0.1027	-0.0073
240	-0.0950	-0.0510	-0.0500
241	-0.0691	-0.1002	-0.0718
242	-0.0159	0.0262	0.0206
243	-0.0460	0.0049	0.0626
244	0.0811	0.1008	0.1230
245	0.0904	0.1059	-0.0506
246	-0.1474	-0.1459	-0.0431
247	-0.0559	0.0055	0.0228
248	0.0388	0.0379	0.0276
249	0.0411	0.0243	-0.0277

Source: Emolia / Emilia source archive · SHA-256 506ea3896dd448ab…

e05FrenchEmolia / Emilia

Emolia FR · FR_B00000_S00110_W000008

Natural speech · Original speech · 7.3 s

J'en déduis que son auteur est sans doute assez fortuné car le papier est d'une rare qualité. Oui.

Tiny Base · values are model estimates, not ground truth

Strongest emotions relative to training

Contemplation

z +0.97 / +1.29raw 0.66 / 0.85

Doubt

z +1.21 / +0.83raw 0.57 / 0.39

Concentration

z +1.18 / +0.89raw 1.51 / 1.30

Contempt

z +0.31 / +1.05raw 0.14 / 0.49

Sourness

z +0.14 / +0.66raw 0.06 / 0.28

Teasing

z +0.27 / +0.60raw 0.15 / 0.33

Emotional Numbness

z +0.60 / +0.36raw 0.55 / 0.34

The center of each bar is the S9 teacher median. Positive z is to the right; negative z is to the left. Ranking uses z, not raw teacher units.

Strongest VoiceNet dimensions relative to training

Metallic character (METL)

z +1.39 / +1.39raw 2.96 / 2.96

Throat resonance (R_THRT)

z +1.21 / +1.24raw 3.04 / 3.07

Teacher or didactic style (S_TECH)

z +1.16 / +1.01raw 2.07 / 1.88

Chest resonance (R_CHST)

z +1.04 / +1.08raw 3.01 / 3.05

Conversational style (S_CONV)

z +0.98 / +1.02raw 3.88 / 3.94

Mixed resonance (R_MIXD)

z +0.93 / +1.01raw 2.21 / 2.29

Narrator style (S_NARR)

z +1.00 / +0.69raw 2.75 / 2.30

All 57 VoiceNet predictions, including raw units, are in the full table below. These seven are ranked by z; the top values may differ from the strongest raw dimensions.

Voice, speed and quality scores in context

Genuineness (0–6)z +0.05 / +0.14raw 2.41 / 2.56

Vocal-burst blend (0–10)z -1.60 / -1.75raw 2.29 / 1.89

Content enjoyment (CE)z +0.29 / +0.68raw 5.10 / 5.49

Production quality (PQ)z +0.19 / +0.12raw 7.21 / 7.15

Speech signal quality, calibratedz +0.26 / +0.28raw 3.62 / 3.63

Background quality, calibratedz +0.37 / +0.55raw 3.73 / 3.90

Overall quality, calibratedz +0.53 / +0.70raw 3.16 / 3.26

P.808 MOS estimatez +1.34 / +1.28raw 4.09 / 4.05

score content enjoymentz +0.45 / +0.57raw 4.64 / 4.68

score overall qualityz +0.73 / +0.79raw 3.02 / 3.05

Background Noisez -1.04 / -1.59raw 0.53 / 0.39

Tempo (TEMP)z -0.44 / -0.57raw 1.60 / 1.44

Arousal (AROU)z -0.47 / -0.61raw 1.82 / 1.66

Valence (VALN)z +0.47 / +0.60raw 2.85 / 3.00

Recording quality (RCQL)z -0.48 / -0.50raw 2.33 / 2.31

Background noise (BKGN)z +0.23 / +0.23raw 2.88 / 2.88

talking speedz +0.61 / +0.57raw 11.34 / 11.16

Characters per second (CPS): 13.42 raw · z +1.17

Orange speaker embedding reconstruction

Cosine against Orange on this same clip (higher means closer to that teacher vector):

Embedding	Tiny	Base
Timbre · 128D	0.802	0.834
Identity · 250D	0.723	0.739

Vocal-burst regions

Tiny

Base

0 s7.3 s

Verified burst intervals are unavailable for this clip.

Tiny: 0 regions, count-head estimate 0.69; Base: 1 regions, count-head estimate 0.46.

Exact predicted start and end times

Model	Region	Start (s)	End (s)	Duration (s)
Base	1	1.10	1.50	0.40

All 192 score slots · raw and z values

#	Target	Tiny raw	Tiny z	Base raw	Base z	Train median	Train SD
Emotion scores Forty clip-level Empathic Insight emotion teacher outputs. Each row evaluates one named emotion score.
0	Affectionemo_Affection	0.011	+0.01	0.009	+0.00	0.007	0.570
1	Amusementemo_Amusement	-0.203	-0.23	-0.092	-0.10	-0.001	0.885
2	Angeremo_Anger	0.190	+0.30	0.234	+0.37	0.004	0.613
3	Astonishment Surpriseemo_Astonishment_Surprise	0.006	+0.00	0.019	+0.02	0.005	0.572
4	Aweemo_Awe	0.014	+0.03	0.027	+0.06	0.000	0.427
5	Bitternessemo_Bitterness	-0.005	-0.04	0.049	+0.09	0.013	0.415
6	Concentrationemo_Concentration	1.510	+1.18	1.296	+0.89	0.634	0.741
7	Confusionemo_Confusion	0.244	+0.45	0.039	+0.07	0.001	0.540
8	Contemplationemo_Contemplation	0.664	+0.97	0.851	+1.29	0.082	0.598
9	Contemptemo_Contempt	0.144	+0.31	0.485	+1.05	-0.000	0.464
10	Contentmentemo_Contentment	0.059	+0.11	0.176	+0.34	0.000	0.514
11	Disappointmentemo_Disappointment	-0.017	-0.02	-0.003	-0.00	0.000	0.700
12	Disgustemo_Disgust	-0.001	-0.02	0.111	+0.21	0.007	0.489
13	Distressemo_Distress	0.002	+0.00	-0.007	-0.01	0.000	0.821
14	Doubtemo_Doubt	0.569	+1.21	0.390	+0.83	0.006	0.466
15	Elationemo_Elation	0.017	+0.01	0.000	-0.02	0.012	0.728
16	Embarrassmentemo_Embarrassment	-0.070	-0.26	0.000	-0.10	0.043	0.430
17	Emotional Numbnessemo_Emotional_Numbness	0.551	+0.60	0.336	+0.36	0.004	0.917
18	Fatigue Exhaustionemo_Fatigue_Exhaustion	0.004	-0.05	0.004	-0.05	0.028	0.539
19	Fearemo_Fear	-0.030	-0.07	0.043	+0.05	0.015	0.610
20	Helplessnessemo_Helplessness	0.041	+0.06	0.027	+0.04	-0.004	0.696
21	Hope Enthusiasm Optimismemo_Hope_Enthusiasm_Optimism	0.012	-0.14	-0.006	-0.16	0.117	0.760
22	Impatience and Irritabilityemo_Impatience_and_Irritability	0.172	+0.03	0.092	-0.08	0.149	0.705
23	Infatuationemo_Infatuation	-0.018	-0.01	0.010	+0.05	-0.015	0.533
24	Interestemo_Interest	1.495	-0.10	1.581	-0.01	1.589	0.907
25	Intoxication Altered States of Consciousnessemo_Intoxication_Altered_States_of_Consciousness	-0.035	-0.02	-0.048	-0.04	-0.025	0.559
26	Jealousy and Envyemo_Jealousy_and_Envy	0.039	-0.05	0.074	+0.03	0.059	0.442
27	Longingemo_Longing	0.030	-0.09	0.072	-0.02	0.087	0.632
28	Malevolence Maliceemo_Malevolence_Malice	0.121	+0.12	0.274	+0.41	0.055	0.534
29	Painemo_Pain	0.021	+0.04	0.028	+0.05	-0.002	0.579
30	Pleasure Ecstasyemo_Pleasure_Ecstasy	-0.015	-0.05	0.028	+0.02	0.017	0.614
31	Prideemo_Pride	0.019	+0.03	0.036	+0.07	0.002	0.509
32	Reliefemo_Relief	0.013	-0.03	0.026	-0.01	0.033	0.681
33	Sadnessemo_Sadness	0.011	+0.01	-0.019	-0.02	0.000	0.759
34	Sexual Lustemo_Sexual_Lust	-0.054	-0.17	0.002	-0.06	0.030	0.494
35	Shameemo_Shame	0.001	-0.02	-0.006	-0.04	0.013	0.510
36	Sournessemo_Sourness	0.057	+0.14	0.284	+0.66	-0.005	0.439
37	Teasingemo_Teasing	0.149	+0.27	0.326	+0.60	0.000	0.545
38	Thankfulness Gratitudeemo_Thankfulness_Gratitude	0.081	+0.06	0.042	+0.00	0.041	0.697
39	Triumphemo_Triumph	0.003	+0.02	0.023	+0.06	-0.007	0.521
VoiceNet dimensions Fifty-seven VoiceNet voice, delivery, style, and recording dimensions. Codes are expanded in the target column.
40	Perceived voice age (AGEV)vn_AGEV_reg	3.351	+0.30	3.577	+0.48	2.984	1.238
41	Arousal (AROU)vn_AROU_reg	1.825	-0.47	1.662	-0.61	2.359	1.147
42	Arousal shift (ARSH)vn_ARSH_reg	2.355	-0.26	2.476	-0.12	2.580	0.867
43	Vocal attack (ATCK)vn_ATCK_reg	1.685	-0.37	1.612	-0.42	2.162	1.295
44	Background noise (BKGN)vn_BKGN_reg	2.878	+0.23	2.876	+0.23	2.703	0.761
45	Brightness (BRGT)vn_BRGT_reg	1.150	-1.04	1.026	-1.19	1.991	0.813
46	Speech chunking (CHNK)vn_CHNK_reg	2.213	+0.30	2.060	+0.17	1.847	1.239
47	Articulation clarity (CLRT)vn_CLRT_reg	1.388	-0.67	1.555	-0.49	2.018	0.945
48	Cognitive load (COGL)vn_COGL_reg	2.738	+0.61	2.474	+0.36	2.094	1.061
49	Dynamic arc (DARC)vn_DARC_reg	1.155	-0.33	1.104	-0.37	1.615	1.380
50	Disfluency (DFLU)vn_DFLU_reg	2.940	+0.38	3.027	+0.46	2.488	1.184
51	Emphasis (EMPH)vn_EMPH_reg	2.326	-0.18	2.112	-0.33	2.607	1.524
52	Esthetics (ESTH)vn_ESTH_reg	2.144	-0.33	2.174	-0.29	2.402	0.782
53	Content appropriateness (EXPL)vn_EXPL_reg	0.226	+0.43	0.299	+0.66	0.086	0.322
54	Focus (FOCS)vn_FOCS_reg	2.042	-0.27	2.174	-0.15	2.344	1.102
55	Fullness (FULL)vn_FULL_reg	1.710	-0.08	1.727	-0.06	1.778	0.889
56	Perceived gender (GEND)vn_GEND_reg	4.615	+0.35	4.951	+0.56	4.055	1.588
57	Harmonicity (HARM)vn_HARM_reg	1.860	-0.74	1.741	-0.88	2.480	0.836
58	Metallic character (METL)vn_METL_reg	2.956	+1.39	2.956	+1.39	1.621	0.958
59	Pitch range (RANG)vn_RANG_reg	2.602	-0.35	2.611	-0.34	2.914	0.897
60	Recording quality (RCQL)vn_RCQL_reg	2.330	-0.48	2.307	-0.50	2.754	0.888
61	Vocal register (REGS)vn_REGS_reg	0.245	-0.75	0.225	-0.77	1.198	1.268
62	Respiration (RESP)vn_RESP_reg	2.278	-0.38	2.086	-0.56	2.680	1.056
63	Roughness (ROUG)vn_ROUG_reg	2.341	+0.35	2.142	+0.12	2.033	0.887
64	Chest resonance (R_CHST)vn_R_CHST_reg	3.010	+1.04	3.049	+1.08	2.135	0.844
65	Head resonance (R_HEAD)vn_R_HEAD_reg	1.888	-0.32	1.801	-0.42	2.148	0.822
66	Mask resonance (R_MASK)vn_R_MASK_reg	1.846	-0.06	1.598	-0.31	1.908	1.005
67	Mixed resonance (R_MIXD)vn_R_MIXD_reg	2.213	+0.93	2.285	+1.01	1.436	0.841
68	Nasal resonance (R_NASL)vn_R_NASL_reg	3.209	+0.40	3.196	+0.39	2.791	1.047
69	Oral resonance (R_ORAL)vn_R_ORAL_reg	2.693	+0.69	2.597	+0.56	2.184	0.741
70	Throat resonance (R_THRT)vn_R_THRT_reg	3.043	+1.21	3.068	+1.24	2.070	0.803
71	Smoothness (SMTH)vn_SMTH_reg	2.134	-0.01	2.017	-0.11	2.143	1.093
72	Stance (STNC)vn_STNC_reg	2.364	-0.24	2.428	-0.18	2.633	1.137
73	Speech structure (STRU)vn_STRU_reg	2.746	+0.64	2.564	+0.45	2.137	0.958
74	ASMR style (S_ASMR)vn_S_ASMR_reg	2.163	+0.56	2.236	+0.61	1.370	1.411
75	Authoritative style (S_AUTH)vn_S_AUTH_reg	2.112	+0.98	2.019	+0.89	1.088	1.043
76	Cartoonish style (S_CART)vn_S_CART_reg	2.423	+0.62	2.519	+0.68	1.560	1.401
77	Casual style (S_CASU)vn_S_CASU_reg	3.384	-0.32	3.299	-0.39	3.793	1.278
78	Conversational style (S_CONV)vn_S_CONV_reg	3.880	+0.98	3.941	+1.02	2.594	1.318
79	Dramatic style (S_DRAM)vn_S_DRAM_reg	1.756	-0.84	1.658	-0.93	2.721	1.148
80	Formal style (S_FORM)vn_S_FORM_reg	1.742	+0.54	1.663	+0.46	1.195	1.021
81	Monologue style (S_MONO)vn_S_MONO_reg	3.051	+0.18	2.768	-0.04	2.824	1.284
82	Narrator style (S_NARR)vn_S_NARR_reg	2.748	+1.00	2.299	+0.69	1.307	1.446
83	Newsreader style (S_NEWS)vn_S_NEWS_reg	0.553	+0.26	0.450	+0.07	0.408	0.568
84	Playful style (S_PLAY)vn_S_PLAY_reg	2.969	+0.47	2.944	+0.45	2.352	1.315
85	Ranting or angry style (S_RANT)vn_S_RANT_reg	0.906	-0.24	1.006	-0.16	1.213	1.289
86	Storytelling style (S_STRY)vn_S_STRY_reg	3.207	+0.53	3.169	+0.50	2.480	1.366
87	Teacher or didactic style (S_TECH)vn_S_TECH_reg	2.070	+1.16	1.880	+1.01	0.646	1.227
88	Whispered talking style (S_WHIS)vn_S_WHIS_reg	2.997	+0.87	3.203	+0.99	1.597	1.618
89	Tempo (TEMP)vn_TEMP_reg	1.599	-0.44	1.444	-0.57	2.117	1.190
90	Tension (TENS)vn_TENS_reg	2.137	+0.68	1.846	+0.34	1.559	0.852
91	Valence (VALN)vn_VALN_reg	2.848	+0.47	3.003	+0.60	2.328	1.118
92	Valence shift (VALS)vn_VALS_reg	3.077	+0.52	3.163	+0.60	2.518	1.079
93	Velocity flux (VFLX)vn_VFLX_reg	1.908	-0.29	1.896	-0.30	2.256	1.208
94	Volatility (VOLT)vn_VOLT_reg	2.128	-0.52	2.098	-0.55	2.586	0.886
95	Vulnerability (VULN)vn_VULN_reg	1.753	-0.91	1.695	-0.97	2.648	0.984
96	Warmth (WARM)vn_WARM_reg	2.876	+0.33	2.948	+0.41	2.578	0.909
Genuineness, blend, and legacy quality Genuineness and vocal-burst blend are predicted. R_quality has Ladder training labels but no valid P3 test labels.
97	Genuineness (0–6)genuineness_0_6	2.414	+0.05	2.557	+0.14	2.332	1.621
98	Vocal-burst blend (0–10)blend_0_10	2.291	-1.60	1.888	-1.75	6.676	2.738
99	Legacy R_quality (no P3 test labels)R_quality	0.663	-1.28	0.632	-1.37	1.095	0.338
Empathic Insight Plus extra scores Nineteen additional clip-level teacher scores, including background noise and content enjoyment.
100	Ageeiv_extra:Age	3.354	+0.35	3.365	+0.39	3.250	0.293
101	Arousaleiv_extra:Arousal	0.988	-0.69	0.999	-0.67	1.289	0.435
102	Authenticityeiv_extra:Authenticity	2.609	-0.38	2.614	-0.34	2.667	0.153
103	Background Noiseeiv_extra:Background_Noise	0.532	-1.04	0.387	-1.59	0.808	0.264
104	Confident vs. Hesitanteiv_extra:Confident_vs._Hesitant	1.227	+0.62	1.198	+0.52	1.040	0.303
105	Gendereiv_extra:Gender	-0.783	-0.16	-0.798	-0.18	-0.621	0.999
106	High-Pitched vs. Low-Pitchedeiv_extra:High-Pitched_vs._Low-Pitched	1.871	+0.17	1.895	+0.27	1.827	0.250
107	Monotone vs. Expressiveeiv_extra:Monotone_vs._Expressive	1.481	-0.81	1.739	-0.26	1.859	0.470
108	Recording Qualityeiv_extra:Recording_Quality	2.213	+0.21	2.263	+0.36	2.144	0.332
109	Serious vs. Humorouseiv_extra:Serious_vs._Humorous	1.155	+0.66	1.258	+0.96	0.929	0.340
110	Soft vs. Harsheiv_extra:Soft_vs._Harsh	0.261	-0.06	0.355	+0.23	0.281	0.320
111	Submissive vs. Dominanteiv_extra:Submissive_vs._Dominant	0.317	-0.18	0.401	+0.08	0.376	0.324
112	Valenceeiv_extra:Valence	-0.014	-0.05	-0.005	-0.03	0.005	0.380
113	Vulnerable vs. Emotionally Detachedeiv_extra:Vulnerable_vs._Emotionally_Detached	2.108	+0.90	1.975	+0.60	1.715	0.437
114	Warm vs. Coldeiv_extra:Warm_vs._Cold	0.112	+0.20	0.180	+0.43	0.051	0.300
115	score background qualityeiv_extra:score_background_quality	3.599	+0.43	3.694	+0.57	3.301	0.693
116	score content enjoymenteiv_extra:score_content_enjoyment	4.644	+0.45	4.680	+0.57	4.507	0.303
117	score overall qualityeiv_extra:score_overall_quality	3.020	+0.73	3.052	+0.79	2.652	0.507
118	score speech qualityeiv_extra:score_speech_quality	1.921	+0.78	1.945	+0.94	1.808	0.146
Meta AudioBox Aesthetics Four AudioBox aesthetic teacher outputs. Expansions follow the official Meta model card.
119	Content enjoyment (CE)audiobox:CE	5.097	+0.29	5.490	+0.68	4.799	1.018
120	Content usefulness (CU)audiobox:CU	5.666	+0.02	5.541	-0.11	5.649	1.001
121	Production complexity (PC)audiobox:PC	1.669	-0.41	1.694	-0.39	2.331	1.617
122	Production quality (PQ)audiobox:PQ	7.213	+0.19	7.151	+0.12	7.044	0.879
Microsoft DNSMOS Seven DNSMOS teacher outputs: raw and calibrated SIG/BAK/OVRL estimates plus P.808 MOS.
123	Speech signal quality, rawdnsmos:SIG_raw	4.134	+0.35	4.155	+0.38	3.900	0.669
124	Background quality, rawdnsmos:BAK_raw	3.806	+0.53	3.999	+0.70	3.211	1.124
125	Overall quality, rawdnsmos:OVRL_raw	3.599	+0.63	3.723	+0.79	3.085	0.812
126	Speech signal quality, calibrateddnsmos:SIG	3.616	+0.26	3.628	+0.28	3.488	0.501
127	Background quality, calibrateddnsmos:BAK	3.731	+0.37	3.898	+0.55	3.389	0.928
128	Overall quality, calibrateddnsmos:OVRL	3.162	+0.53	3.262	+0.70	2.840	0.606
129	P.808 MOS estimatednsmos:P808_MOS	4.086	+1.34	4.055	+1.28	3.421	0.496
Vocal-burst count The regression target is log(1 + count). A separate table also reports count error after inverse transformation.
130	Vocal-burst count, log(1 + count)burst_count_log1p	0.527	+0.81	0.377	+0.58	0.000	0.647
VoiceCLAP attributes Sixty-one individual VoiceCLAP attribute teacher scores. The raw 768D VoiceCLAP embedding is stored in sidecars but is not a model output.
131	Affectionvoiceclap_attribute:Affection	0.665	-0.51	0.721	-0.41	0.947	0.554
132	Agevoiceclap_attribute:Age	3.306	+0.14	3.093	-0.25	3.229	0.547
133	Amusementvoiceclap_attribute:Amusement	0.530	+0.24	0.361	-0.05	0.392	0.572
134	Angervoiceclap_attribute:Anger	0.686	-0.61	0.688	-0.60	0.992	0.506
135	Arousalvoiceclap_attribute:Arousal	1.324	-0.15	1.305	-0.18	1.420	0.622
136	Astonishment Surprisevoiceclap_attribute:Astonishment_Surprise	0.593	+0.18	0.596	+0.18	0.509	0.479
137	Authenticityvoiceclap_attribute:Authenticity	2.654	-0.70	2.655	-0.69	2.770	0.167
138	Awevoiceclap_attribute:Awe	0.382	-0.60	0.457	-0.32	0.539	0.259
139	Background Noisevoiceclap_attribute:Background_Noise	0.462	-0.40	0.510	-0.22	0.567	0.264
140	Bitternessvoiceclap_attribute:Bitterness	0.313	-1.19	0.327	-1.13	0.592	0.236
141	Concentrationvoiceclap_attribute:Concentration	1.192	-0.04	1.080	-0.25	1.214	0.531
142	Confident vs. Hesitantvoiceclap_attribute:Confident_vs._Hesitant	1.505	+0.93	1.478	+0.87	1.069	0.468
143	Confusionvoiceclap_attribute:Confusion	0.934	+0.87	0.979	+1.00	0.643	0.334
144	Contemplationvoiceclap_attribute:Contemplation	0.836	+0.14	0.895	+0.28	0.780	0.406
145	Contemptvoiceclap_attribute:Contempt	0.582	-0.37	0.600	-0.32	0.709	0.339
146	Contentmentvoiceclap_attribute:Contentment	0.394	-0.63	0.407	-0.59	0.588	0.307
147	Disappointmentvoiceclap_attribute:Disappointment	0.570	-0.65	0.470	-1.00	0.760	0.291
148	Disgustvoiceclap_attribute:Disgust	0.514	-0.53	0.486	-0.67	0.625	0.207
149	Distressvoiceclap_attribute:Distress	0.563	-1.04	0.524	-1.15	0.927	0.350
150	Doubtvoiceclap_attribute:Doubt	0.658	+0.66	0.653	+0.63	0.535	0.188
151	Elationvoiceclap_attribute:Elation	0.471	-0.17	0.465	-0.19	0.539	0.397
152	Embarrassmentvoiceclap_attribute:Embarrassment	0.329	+0.07	0.314	+0.02	0.307	0.314
153	Emotional Numbnessvoiceclap_attribute:Emotional_Numbness	0.711	+0.18	0.697	+0.13	0.664	0.266
154	Fatigue Exhaustionvoiceclap_attribute:Fatigue_Exhaustion	0.471	+0.04	0.429	-0.13	0.462	0.261
155	Fearvoiceclap_attribute:Fear	0.333	-1.34	0.364	-1.20	0.618	0.212
156	Gendervoiceclap_attribute:Gender	-0.637	-0.48	-0.783	-0.63	-0.151	1.005
157	Helplessnessvoiceclap_attribute:Helplessness	0.446	-0.79	0.413	-0.91	0.658	0.268
158	High-Pitched vs. Low-Pitchedvoiceclap_attribute:High-Pitched_vs._Low-Pitched	1.960	+0.32	2.009	+0.45	1.840	0.375
159	Hope Enthusiasm Optimismvoiceclap_attribute:Hope_Enthusiasm_Optimism	0.626	-0.20	0.596	-0.27	0.705	0.396
160	Impatience and Irritabilityvoiceclap_attribute:Impatience_and_Irritability	0.869	-0.34	0.902	-0.28	1.052	0.541
161	Infatuationvoiceclap_attribute:Infatuation	0.430	-0.54	0.556	-0.16	0.608	0.332
162	Interestvoiceclap_attribute:Interest	1.452	-0.33	1.450	-0.34	1.598	0.440
163	Intoxication Altered States of Consciousnessvoiceclap_attribute:Intoxication_Altered_States_of_Consciousness	0.583	+0.17	0.684	+0.39	0.502	0.463
164	Jealousy & Envyvoiceclap_attribute:Jealousy_&_Envy	0.372	-0.61	0.441	-0.33	0.523	0.245
165	Longingvoiceclap_attribute:Longing	0.510	-0.13	0.510	-0.13	0.538	0.220
166	Malevolence Malicevoiceclap_attribute:Malevolence_Malice	0.521	-0.90	0.644	-0.55	0.833	0.346
167	Monotone vs. Expressivevoiceclap_attribute:Monotone_vs._Expressive	1.521	-0.43	1.622	-0.26	1.775	0.594
168	Painvoiceclap_attribute:Pain	0.227	-0.71	0.228	-0.70	0.381	0.218
169	Pleasure Ecstasyvoiceclap_attribute:Pleasure_Ecstasy	0.367	-0.45	0.393	-0.37	0.503	0.301
170	Pridevoiceclap_attribute:Pride	0.399	-1.09	0.459	-0.92	0.780	0.349
171	Recording Qualityvoiceclap_attribute:Recording_Quality	2.232	-0.25	2.201	-0.34	2.313	0.328
172	Reliefvoiceclap_attribute:Relief	0.736	-0.70	0.658	-0.88	1.025	0.415
173	Sadnessvoiceclap_attribute:Sadness	0.578	-0.56	0.514	-0.76	0.752	0.313
174	Serious vs. Humorousvoiceclap_attribute:Serious_vs._Humorous	1.159	+0.63	1.131	+0.58	0.803	0.568
175	Sexual Lustvoiceclap_attribute:Sexual_Lust	0.530	-0.25	0.629	-0.02	0.635	0.419
176	Shamevoiceclap_attribute:Shame	0.425	-0.36	0.440	-0.31	0.526	0.283
177	Soft vs. Harshvoiceclap_attribute:Soft_vs._Harsh	0.085	-0.21	0.078	-0.23	0.160	0.360
178	Sournessvoiceclap_attribute:Sourness	0.504	-0.69	0.528	-0.61	0.706	0.291
179	Submissive vs. Dominantvoiceclap_attribute:Submissive_vs._Dominant	0.438	-0.52	0.469	-0.43	0.623	0.359
180	Teasingvoiceclap_attribute:Teasing	0.687	+0.39	0.630	+0.24	0.540	0.379
181	Thankfulness Gratitudevoiceclap_attribute:Thankfulness_Gratitude	1.269	-0.22	1.143	-0.45	1.384	0.529
182	Triumphvoiceclap_attribute:Triumph	0.367	-0.97	0.422	-0.82	0.716	0.359
183	Valencevoiceclap_attribute:Valence	-0.095	-0.14	-0.324	-0.50	-0.007	0.635
184	Vulnerable vs. Emotionally Detachedvoiceclap_attribute:Vulnerable_vs._Emotionally_Detached	2.041	+0.72	1.914	+0.50	1.638	0.556
185	Warm vs. Coldvoiceclap_attribute:Warm_vs._Cold	-0.004	+0.16	-0.006	+0.15	-0.066	0.400
186	durationvoiceclap_attribute:duration	6.761	-0.65	7.454	-0.54	10.914	6.354
187	score background qualityvoiceclap_attribute:score_background_quality	3.427	+0.37	3.430	+0.37	3.245	0.498
188	score content enjoymentvoiceclap_attribute:score_content_enjoyment	4.710	+0.37	4.700	+0.30	4.656	0.147
189	score overall qualityvoiceclap_attribute:score_overall_quality	2.808	+0.42	2.799	+0.40	2.635	0.412
190	score speech qualityvoiceclap_attribute:score_speech_quality	1.975	+1.21	1.952	+0.88	1.891	0.069
191	talking speedvoiceclap_attribute:talking_speed	11.336	+0.61	11.160	+0.57	9.028	3.756

All Orange embedding components

The cosine above is the meaningful vector-level comparison; component values have no standalone semantic label.

Timbre — all 128 vector components

Dimension	Tiny	Base	Orange teacher
0	-0.1098	-0.1160	-0.0745
1	0.0544	0.0848	0.1359
2	0.1295	0.0982	0.1670
3	0.0798	0.0279	0.1675
4	-0.1098	-0.0333	-0.0669
5	-0.1227	-0.0848	-0.0948
6	0.0189	0.0753	-0.0062
7	-0.0663	-0.0688	-0.0685
8	0.0407	0.0835	0.0167
9	-0.0469	0.0144	0.1032
10	0.0735	0.0740	0.1071
11	-0.0047	-0.0389	0.0715
12	-0.0276	0.0593	0.0307
13	-0.0321	0.0041	-0.0598
14	0.1647	0.1679	0.1343
15	-0.1155	-0.1052	-0.0671
16	-0.1227	-0.0827	-0.0927
17	-0.1129	-0.1333	-0.0779
18	-0.0570	-0.1103	-0.0569
19	-0.0875	-0.0710	-0.0708
20	-0.1025	-0.0883	-0.0750
21	-0.0678	-0.0844	-0.0688
22	0.0813	0.1238	0.0551
23	-0.0089	-0.0366	-0.0876
24	-0.0466	-0.0632	-0.0605
25	-0.0399	-0.0110	-0.0490
26	-0.0766	-0.0381	0.0064
27	-0.0813	-0.0701	-0.0698
28	0.0637	0.0255	-0.0223
29	-0.0510	-0.0413	-0.0802
30	-0.1036	-0.1108	-0.0806
31	0.0399	0.0744	0.0331
32	-0.0694	-0.0744	-0.0721
33	-0.0155	-0.0387	-0.0818
34	-0.0533	-0.0917	-0.0671
35	-0.0953	-0.1060	-0.0865
36	0.0072	0.0032	-0.0318
37	-0.1088	-0.1480	-0.0887
38	0.0886	0.0138	0.0617
39	-0.0787	-0.0891	-0.0756
40	-0.0741	-0.0602	-0.0722
41	0.0183	-0.0376	0.1426
42	-0.1155	-0.0844	-0.0756
43	-0.0202	-0.0359	-0.0053
44	-0.0787	-0.0610	-0.0719
45	0.1051	0.0865	0.0811
46	0.0030	0.0167	-0.0706
47	-0.0249	-0.0580	0.0559
48	0.0225	0.0671	0.0462
49	0.2942	0.2735	0.2230
50	-0.0730	-0.0714	-0.0766
51	0.2092	0.1809	0.1884
52	0.0216	-0.0718	-0.0806
53	-0.0311	-0.0684	-0.0146
54	0.0518	-0.0082	0.0018
55	0.0596	0.0439	0.0963
56	0.0355	0.1341	0.1826
57	-0.0102	0.0394	0.0892
58	0.0787	0.1497	0.1351
59	0.0246	0.1073	-0.0277
60	-0.0963	-0.0740	-0.0222
61	0.0792	0.0541	0.0217
62	0.0093	-0.0083	0.0019
63	-0.0378	-0.0422	0.0028
64	0.0471	-0.0036	0.0291
65	0.1802	0.1887	0.2296
66	0.0456	0.1142	0.0563
67	-0.0337	-0.0179	-0.0215
68	0.0603	0.1134	0.1180
69	0.2755	0.2389	0.2249
70	-0.0891	-0.1177	-0.0776
71	0.0378	0.0513	-0.0020
72	0.1300	0.1264	0.1641
73	-0.0355	0.0156	0.0642
74	0.0417	0.0351	0.0648
75	-0.0153	-0.0675	-0.0909
76	0.0968	0.1073	0.1110
77	-0.0870	-0.0645	-0.0684
78	-0.1098	-0.0788	-0.0667
79	0.1103	0.0320	-0.0112
80	0.0989	0.0861	-0.0185
81	0.1947	0.0909	0.0983
82	-0.0299	-0.0457	-0.0030
83	0.0435	0.1367	0.1636
84	-0.0417	-0.0476	-0.0502
85	0.0264	-0.0011	-0.0445
86	0.0135	0.0913	0.0422
87	-0.0860	-0.0457	-0.0199
88	0.0829	0.1134	0.0771
89	0.0046	0.0567	-0.0018
90	0.0886	0.0433	0.1223
91	-0.0440	0.0061	-0.0688
92	0.2341	0.2925	0.2214
93	-0.0673	-0.0662	-0.0536
94	-0.0300	-0.0762	-0.0451
95	0.1196	0.0900	0.1032
96	-0.0001	-0.0301	0.0073
97	0.1574	0.1026	0.1226
98	-0.0777	-0.0576	-0.0757
99	-0.0289	0.0104	0.0060
100	0.1771	0.1783	0.1633
101	0.0653	0.0376	-0.0724
102	-0.0500	-0.0357	-0.0381
103	0.0399	0.0296	0.0377
104	-0.0629	-0.1125	-0.0732
105	0.0124	0.0387	-0.0677
106	0.0984	0.0543	0.1074
107	0.0132	0.0461	0.0709
108	-0.1005	-0.1047	-0.0812
109	-0.0246	0.0270	0.1039
110	-0.0073	-0.0309	-0.0693
111	0.0492	0.0563	0.0266
112	-0.0461	-0.1073	-0.0154
113	-0.0603	-0.0602	-0.0568
114	-0.0179	-0.0491	-0.0806
115	0.0337	-0.0163	-0.0388
116	0.2103	0.1541	0.1216
117	-0.1150	-0.1095	-0.0872
118	-0.0232	0.0623	0.1112
119	-0.0432	-0.0666	-0.0724
120	-0.1155	-0.0448	-0.0770
121	0.0281	0.0134	0.0099
122	0.0137	0.0164	0.0241
123	-0.0256	-0.0344	0.0280
124	-0.0077	-0.0122	0.0978
125	-0.1051	-0.0961	-0.0746
126	0.0347	0.0065	0.0852
127	0.0262	0.0104	0.0323

Identity — all 250 vector components

Dimension	Tiny	Base	Orange teacher
0	-0.0203	0.0190	-0.0201
1	-0.0599	-0.0611	-0.0442
2	-0.0388	-0.0233	-0.0561
3	-0.0081	-0.0402	-0.0865
4	-0.0228	-0.0543	-0.0415
5	0.0254	0.0822	0.0511
6	-0.1080	-0.1282	-0.0669
7	-0.0382	-0.0490	-0.0462
8	-0.0130	-0.0056	0.0691
9	0.0262	0.0381	0.0200
10	-0.0312	-0.0317	-0.0399
11	-0.0373	-0.0539	-0.0617
12	0.0259	0.0432	0.0807
13	0.0265	0.0358	0.0608
14	-0.0852	-0.0890	-0.0651
15	0.1050	0.1109	0.1246
16	0.0350	-0.0322	0.0815
17	-0.0295	0.0040	-0.0548
18	0.1468	0.1728	0.2107
19	-0.0405	-0.0728	-0.0724
20	-0.0348	-0.0551	-0.0457
21	0.0126	-0.0090	-0.0192
22	-0.0133	-0.0127	-0.0324
23	-0.0407	-0.0330	-0.0441
24	-0.0517	-0.0709	-0.0389
25	0.0114	0.0077	0.0533
26	-0.0696	-0.0668	-0.0503
27	-0.0536	-0.0528	-0.0371
28	-0.0256	-0.0245	-0.0494
29	-0.0667	-0.0585	-0.0439
30	-0.0399	-0.0272	-0.0397
31	0.1173	0.1388	0.0958
32	-0.0603	-0.0163	-0.0469
33	-0.0418	-0.0255	-0.0410
34	-0.0721	-0.0943	-0.0545
35	0.0776	0.0494	0.0078
36	0.0411	0.0012	0.0365
37	0.0662	0.0272	0.0255
38	0.0420	0.0875	0.0844
39	0.0248	0.0379	-0.0499
40	-0.0312	-0.0207	-0.0213
41	-0.0416	-0.0255	-0.0524
42	-0.0688	-0.0487	-0.0453
43	0.0637	0.0128	0.0480
44	-0.0700	-0.0102	-0.0549
45	0.0304	-0.0290	-0.0139
46	-0.0557	-0.0185	-0.0660
47	-0.1050	-0.0732	-0.0597
48	0.0620	0.0543	0.1153
49	-0.0250	-0.0025	-0.0057
50	0.0835	0.0769	0.0590
51	-0.0574	-0.0709	-0.0462
52	-0.0062	-0.0377	-0.0408
53	-0.0437	-0.0279	-0.0441
54	-0.0462	-0.0192	-0.0771
55	0.0225	0.0195	-0.0142
56	0.0172	0.0218	0.0155
57	-0.1198	-0.1215	-0.0533
58	0.1308	0.1471	0.1318
59	0.0157	-0.0330	0.0039
60	-0.0243	-0.0082	-0.0478
61	0.0392	0.0886	0.0643
62	-0.0390	-0.0268	-0.0401
63	-0.0540	-0.0532	-0.0496
64	-0.0373	-0.0468	-0.0508
65	0.0189	-0.0174	-0.0557
66	-0.0233	-0.0253	-0.0575
67	0.0991	0.0313	0.0163
68	-0.0131	0.0426	0.0500
69	0.0384	0.0058	0.0481
70	-0.0141	-0.0099	-0.0662
71	-0.0751	-0.0407	-0.0478
72	-0.0962	-0.0924	-0.0505
73	-0.0439	-0.0634	-0.0814
74	-0.0742	-0.0747	-0.0492
75	0.0856	0.0901	0.0890
76	-0.0239	-0.0581	-0.0434
77	0.0679	0.0260	0.0274
78	0.0056	0.0807	0.0158
79	-0.0502	-0.0521	-0.0488
80	0.0717	0.0558	0.1559
81	0.0227	0.0028	-0.0546
82	0.2025	0.1411	0.1150
83	-0.0553	-0.0490	-0.0364
84	-0.0137	-0.0509	-0.0577
85	-0.0641	-0.0785	-0.0487
86	-0.0755	-0.0849	-0.0435
87	0.0085	-0.0573	-0.0389
88	0.0810	0.0671	0.0095
89	-0.0772	-0.0447	-0.0440
90	-0.0527	-0.0438	-0.0483
91	0.0002	0.0558	-0.0573
92	-0.0540	-0.0660	-0.0421
93	-0.1198	-0.0494	-0.0553
94	-0.0612	-0.0375	0.0043
95	0.1358	0.1494	0.1874
96	0.0683	0.0875	0.2048
97	0.0306	0.0709	0.1140
98	-0.1105	-0.0890	-0.0515
99	0.0894	0.0273	0.0907
100	-0.0721	-0.0498	-0.0549
101	-0.0738	-0.0656	-0.0460
102	-0.0007	0.0034	-0.0063
103	-0.0789	-0.0751	-0.0805
104	-0.0130	-0.0229	0.0163
105	-0.0348	0.0426	-0.0021
106	-0.0553	-0.0656	-0.0375
107	-0.0667	-0.0875	-0.0436
108	-0.0662	-0.0600	-0.0362
109	-0.0759	-0.0679	-0.0468
110	-0.0137	-0.0165	0.0224
111	-0.0529	-0.0524	-0.0401
112	-0.0230	-0.0311	-0.0105
113	-0.0924	-0.0788	-0.0830
114	0.0003	0.0200	-0.0036
115	0.1350	0.1033	0.0958
116	-0.1055	-0.1071	-0.0875
117	0.0443	0.0075	0.0273
118	-0.0018	-0.0054	-0.0558
119	0.0163	-0.0268	0.0023
120	-0.0316	-0.0372	-0.0621
121	-0.0081	-0.0083	-0.0524
122	0.0091	-0.0043	0.0005
123	0.0810	0.0409	0.0206
124	-0.0772	-0.0913	-0.0486
125	-0.0586	-0.0713	-0.0473
126	-0.0124	-0.0604	-0.0942
127	-0.1080	-0.0758	-0.0501
128	-0.0470	-0.0351	-0.0257
129	0.0548	0.0247	0.0339
130	0.0696	0.0532	0.0690
131	-0.0248	-0.0421	-0.0426
132	-0.1029	-0.0815	-0.0516
133	-0.0675	-0.0943	-0.0482
134	-0.0367	-0.0468	-0.0233
135	0.0713	0.0717	0.0198
136	-0.0534	-0.0562	0.0322
137	-0.0561	-0.0273	-0.0452
138	-0.0574	-0.0686	-0.0429
139	-0.0071	-0.0004	-0.0498
140	0.0616	0.0713	0.0743
141	-0.0941	-0.0837	-0.0482
142	-0.0194	0.0187	-0.0421
143	-0.0352	-0.0058	0.1223
144	0.0544	0.0803	0.0639
145	0.0095	0.0383	-0.0316
146	-0.0281	-0.0262	-0.0584
147	-0.0201	-0.0157	-0.0433
148	-0.0688	-0.0698	-0.0537
149	0.1139	0.1629	0.0546
150	0.0688	-0.0164	-0.0479
151	-0.0002	0.0137	-0.0555
152	-0.0210	-0.0324	-0.0540
153	0.0607	0.0702	-0.0351
154	-0.0206	-0.0322	-0.0475
155	-0.0228	-0.0513	-0.0635
156	-0.0772	-0.0822	-0.0488
157	0.0460	0.0849	0.0517
158	0.0231	-0.0141	-0.0606
159	0.0502	0.0055	-0.0570
160	-0.0188	-0.0273	-0.0463
161	-0.1434	-0.0924	-0.0496
162	0.0319	0.0190	0.0702
163	-0.0030	0.0209	-0.0287
164	-0.0831	-0.0637	-0.0428
165	-0.0369	0.0383	-0.0101
166	0.0705	0.0981	0.0915
167	-0.0409	-0.0604	0.0146
168	0.0953	0.0481	-0.0250
169	0.0616	0.0543	0.0201
170	-0.0768	-0.0585	-0.0456
171	0.0120	0.0237	-0.0428
172	-0.0094	-0.0675	-0.0564
173	-0.0388	-0.1056	-0.0571
174	0.0213	-0.0124	0.1625
175	-0.0840	-0.1139	-0.0807
176	-0.1000	-0.0777	-0.0414
177	0.0150	0.0604	0.0142
178	-0.0016	0.0251	-0.0432
179	0.0163	0.0686	-0.0012
180	-0.0227	-0.0270	-0.0557
181	0.1223	0.1192	0.0441
182	0.0103	0.0377	-0.0421
183	-0.0696	-0.0935	-0.0982
184	-0.0254	-0.0126	-0.0252
185	0.0146	0.0019	0.0846
186	-0.0915	-0.0453	-0.0587
187	-0.0093	0.0104	0.0270
188	-0.0523	-0.0736	-0.0457
189	0.0506	0.0332	0.0210
190	0.0529	0.0321	-0.0578
191	0.0445	0.0458	-0.0651
192	0.0751	0.0471	0.1243
193	0.1232	0.1758	0.1449
194	-0.0498	-0.0207	0.0564
195	0.1299	0.1735	-0.0463
196	-0.0373	-0.0626	-0.0473
197	-0.0219	-0.0218	-0.0681
198	-0.0595	-0.0702	-0.0471
199	0.0540	0.0198	0.0751
200	0.0840	0.1011	0.1353
201	-0.0734	-0.0637	-0.0459
202	-0.0738	-0.1003	-0.0095
203	-0.0152	0.0147	0.0453
204	0.0226	0.0324	0.0241
205	0.0508	0.0240	0.0229
206	0.0139	0.0040	-0.0502
207	0.0090	-0.0322	-0.0658
208	-0.0118	-0.0129	-0.0505
209	-0.0468	-0.0762	-0.0712
210	-0.0176	-0.0178	-0.0634
211	0.0014	-0.0041	0.0071
212	-0.0772	-0.0328	-0.0712
213	0.0534	0.0081	-0.0638
214	0.0026	0.0536	-0.0614
215	-0.0705	-0.0966	-0.0409
216	-0.0198	0.0061	-0.0433
217	0.0123	-0.0116	0.0178
218	0.1384	0.1690	0.1740
219	-0.0570	-0.0332	-0.0457
220	0.0071	-0.0521	-0.0537
221	-0.0451	-0.0077	-0.0029
222	-0.1358	-0.0466	-0.0571
223	0.0087	-0.0481	-0.0391
224	0.1721	0.1403	0.1780
225	-0.0536	-0.0736	-0.0405
226	0.0780	0.0954	0.0946
227	-0.0012	0.0205	-0.0626
228	-0.0295	-0.0304	0.0216
229	0.1384	0.0739	0.1037
230	-0.0953	-0.0818	-0.0496
231	-0.1072	-0.1026	-0.0674
232	-0.0416	-0.0539	-0.0668
233	0.0460	0.0341	0.0133
234	-0.0456	-0.0417	-0.0413
235	0.0570	0.0702	0.0278
236	-0.0018	-0.0302	-0.0249
237	-0.0180	-0.0021	-0.0497
238	-0.0620	-0.0404	-0.0271
239	-0.0831	-0.0762	-0.0503
240	-0.0399	-0.0041	-0.0497
241	0.0278	0.0762	0.0786
242	0.0092	0.0443	0.0429
243	0.0193	-0.0243	-0.0450
244	-0.0464	-0.0349	-0.0518
245	0.1190	0.1147	0.0270
246	-0.0310	-0.0532	-0.0394
247	0.1059	0.0792	0.1048
248	-0.0449	-0.0551	-0.0534
249	0.0806	0.0871	0.0812

Source: Emolia / Emilia source archive · SHA-256 d7247351f449dd22…

e06FrenchEmolia / Emilia

Emolia FR · FR_B00000_S00010_W000021

Natural speech · Original speech · 9.0 s

Alors telles que nous avons mentionnées au début de cette session d'étude, avant que ce gouvernement ne soit en place.

Tiny Base · values are model estimates, not ground truth

Strongest emotions relative to training

Concentration

z +1.67 / +1.43raw 1.87 / 1.70

Contemplation

z +0.83 / +1.04raw 0.58 / 0.71

Interest

z +0.61 / +0.43raw 2.14 / 1.98

Pride

z +0.58 / +0.47raw 0.30 / 0.24

Contentment

z +0.54 / +0.25raw 0.28 / 0.13

Anger

z +0.27 / +0.26raw 0.17 / 0.16

Emotional Numbness

z +0.15 / +0.14raw 0.14 / 0.14

The center of each bar is the S9 teacher median. Positive z is to the right; negative z is to the left. Ranking uses z, not raw teacher units.

Strongest VoiceNet dimensions relative to training

Teacher or didactic style (S_TECH)

z +2.01 / +2.36raw 3.12 / 3.54

Authoritative style (S_AUTH)

z +1.65 / +1.78raw 2.81 / 2.95

Mixed resonance (R_MIXD)

z +1.29 / +1.70raw 2.52 / 2.87

Throat resonance (R_THRT)

z +1.62 / +1.64raw 3.37 / 3.39

Chest resonance (R_CHST)

z +1.28 / +1.57raw 3.22 / 3.46

Perceived voice age (AGEV)

z +1.24 / +1.50raw 4.52 / 4.84

Formal style (S_FORM)

z +1.31 / +1.49raw 2.54 / 2.72

All 57 VoiceNet predictions, including raw units, are in the full table below. These seven are ranked by z; the top values may differ from the strongest raw dimensions.

Voice, speed and quality scores in context

Genuineness (0–6)z +0.92 / +0.70raw 3.82 / 3.46

Vocal-burst blend (0–10)z -1.51 / -1.83raw 2.55 / 1.65

Content enjoyment (CE)z +0.53 / +0.66raw 5.34 / 5.47

Production quality (PQ)z -0.22 / -0.06raw 6.85 / 6.99

Speech signal quality, calibratedz +0.18 / +0.22raw 3.58 / 3.60

Background quality, calibratedz +0.66 / +0.39raw 4.00 / 3.75

Overall quality, calibratedz +0.70 / +0.54raw 3.26 / 3.17

P.808 MOS estimatez +0.89 / +0.96raw 3.86 / 3.90

score content enjoymentz +0.17 / +0.42raw 4.56 / 4.63

score overall qualityz +0.86 / +0.63raw 3.09 / 2.97

Background Noisez -0.33 / -1.08raw 0.72 / 0.52

Tempo (TEMP)z +0.01 / -0.25raw 2.13 / 1.82

Arousal (AROU)z -0.24 / -0.32raw 2.08 / 1.99

Valence (VALN)z +0.64 / +0.71raw 3.04 / 3.12

Recording quality (RCQL)z -0.24 / -0.14raw 2.54 / 2.63

Background noise (BKGN)z -0.53 / -0.37raw 2.30 / 2.42

talking speedz +1.09 / +1.26raw 13.13 / 13.76

Characters per second (CPS): 13.16 raw · z +1.10

Orange speaker embedding reconstruction

Cosine against Orange on this same clip (higher means closer to that teacher vector):

Embedding	Tiny	Base
Timbre · 128D	0.798	0.867
Identity · 250D	0.671	0.762

Vocal-burst regions

Tiny

Base

0 s9.0 s

Verified burst intervals are unavailable for this clip.

Tiny: 0 regions, count-head estimate 0.10; Base: 0 regions, count-head estimate 0.00.

Exact predicted start and end times

Model	Region	Start (s)	End (s)	Duration (s)

All 192 score slots · raw and z values

#	Target	Tiny raw	Tiny z	Base raw	Base z	Train median	Train SD
Emotion scores Forty clip-level Empathic Insight emotion teacher outputs. Each row evaluates one named emotion score.
0	Affectionemo_Affection	-0.013	-0.04	-0.022	-0.05	0.007	0.570
1	Amusementemo_Amusement	-0.020	-0.02	0.024	+0.03	-0.001	0.885
2	Angeremo_Anger	0.170	+0.27	0.165	+0.26	0.004	0.613
3	Astonishment Surpriseemo_Astonishment_Surprise	0.030	+0.04	0.012	+0.01	0.005	0.572
4	Aweemo_Awe	0.008	+0.02	0.027	+0.06	0.000	0.427
5	Bitternessemo_Bitterness	0.023	+0.02	-0.001	-0.04	0.013	0.415
6	Concentrationemo_Concentration	1.869	+1.67	1.698	+1.43	0.634	0.741
7	Confusionemo_Confusion	-0.043	-0.08	0.005	+0.01	0.001	0.540
8	Contemplationemo_Contemplation	0.577	+0.83	0.706	+1.04	0.082	0.598
9	Contemptemo_Contempt	0.020	+0.04	0.016	+0.03	-0.000	0.464
10	Contentmentemo_Contentment	0.275	+0.54	0.128	+0.25	0.000	0.514
11	Disappointmentemo_Disappointment	-0.077	-0.11	-0.061	-0.09	0.000	0.700
12	Disgustemo_Disgust	0.057	+0.10	-0.004	-0.02	0.007	0.489
13	Distressemo_Distress	0.006	+0.01	-0.030	-0.04	0.000	0.821
14	Doubtemo_Doubt	-0.034	-0.08	0.008	+0.00	0.006	0.466
15	Elationemo_Elation	0.000	-0.02	0.006	-0.01	0.012	0.728
16	Embarrassmentemo_Embarrassment	-0.056	-0.23	-0.001	-0.10	0.043	0.430
17	Emotional Numbnessemo_Emotional_Numbness	0.141	+0.15	0.137	+0.14	0.004	0.917
18	Fatigue Exhaustionemo_Fatigue_Exhaustion	0.008	-0.04	0.051	+0.04	0.028	0.539
19	Fearemo_Fear	0.004	-0.02	-0.013	-0.04	0.015	0.610
20	Helplessnessemo_Helplessness	-0.053	-0.07	-0.064	-0.09	-0.004	0.696
21	Hope Enthusiasm Optimismemo_Hope_Enthusiasm_Optimism	0.185	+0.09	-0.044	-0.21	0.117	0.760
22	Impatience and Irritabilityemo_Impatience_and_Irritability	-0.082	-0.33	-0.012	-0.23	0.149	0.705
23	Infatuationemo_Infatuation	-0.046	-0.06	-0.021	-0.01	-0.015	0.533
24	Interestemo_Interest	2.138	+0.61	1.978	+0.43	1.589	0.907
25	Intoxication Altered States of Consciousnessemo_Intoxication_Altered_States_of_Consciousness	-0.025	-0.00	-0.021	+0.01	-0.025	0.559
26	Jealousy and Envyemo_Jealousy_and_Envy	0.027	-0.07	0.041	-0.04	0.059	0.442
27	Longingemo_Longing	-0.009	-0.15	0.000	-0.14	0.087	0.632
28	Malevolence Maliceemo_Malevolence_Malice	0.085	+0.06	0.029	-0.05	0.055	0.534
29	Painemo_Pain	0.013	+0.03	0.039	+0.07	-0.002	0.579
30	Pleasure Ecstasyemo_Pleasure_Ecstasy	-0.073	-0.15	0.006	-0.02	0.017	0.614
31	Prideemo_Pride	0.297	+0.58	0.241	+0.47	0.002	0.509
32	Reliefemo_Relief	0.024	-0.01	0.054	+0.03	0.033	0.681
33	Sadnessemo_Sadness	-0.046	-0.06	-0.037	-0.05	0.000	0.759
34	Sexual Lustemo_Sexual_Lust	-0.025	-0.11	-0.025	-0.11	0.030	0.494
35	Shameemo_Shame	0.010	-0.01	0.015	+0.00	0.013	0.510
36	Sournessemo_Sourness	-0.042	-0.08	-0.003	+0.01	-0.005	0.439
37	Teasingemo_Teasing	0.003	+0.01	0.028	+0.05	0.000	0.545
38	Thankfulness Gratitudeemo_Thankfulness_Gratitude	0.038	-0.00	0.083	+0.06	0.041	0.697
39	Triumphemo_Triumph	0.054	+0.12	0.010	+0.03	-0.007	0.521
VoiceNet dimensions Fifty-seven VoiceNet voice, delivery, style, and recording dimensions. Codes are expanded in the target column.
40	Perceived voice age (AGEV)vn_AGEV_reg	4.522	+1.24	4.837	+1.50	2.984	1.238
41	Arousal (AROU)vn_AROU_reg	2.080	-0.24	1.988	-0.32	2.359	1.147
42	Arousal shift (ARSH)vn_ARSH_reg	2.614	+0.04	2.591	+0.01	2.580	0.867
43	Vocal attack (ATCK)vn_ATCK_reg	2.535	+0.29	2.345	+0.14	2.162	1.295
44	Background noise (BKGN)vn_BKGN_reg	2.303	-0.53	2.420	-0.37	2.703	0.761
45	Brightness (BRGT)vn_BRGT_reg	2.432	+0.54	2.606	+0.76	1.991	0.813
46	Speech chunking (CHNK)vn_CHNK_reg	2.176	+0.27	2.096	+0.20	1.847	1.239
47	Articulation clarity (CLRT)vn_CLRT_reg	2.208	+0.20	2.273	+0.27	2.018	0.945
48	Cognitive load (COGL)vn_COGL_reg	3.113	+0.96	3.158	+1.00	2.094	1.061
49	Dynamic arc (DARC)vn_DARC_reg	1.802	+0.14	1.831	+0.16	1.615	1.380
50	Disfluency (DFLU)vn_DFLU_reg	3.618	+0.95	3.419	+0.79	2.488	1.184
51	Emphasis (EMPH)vn_EMPH_reg	3.368	+0.50	3.356	+0.49	2.607	1.524
52	Esthetics (ESTH)vn_ESTH_reg	2.541	+0.18	2.580	+0.23	2.402	0.782
53	Content appropriateness (EXPL)vn_EXPL_reg	-0.030	-0.36	0.002	-0.26	0.086	0.322
54	Focus (FOCS)vn_FOCS_reg	2.983	+0.58	2.742	+0.36	2.344	1.102
55	Fullness (FULL)vn_FULL_reg	2.386	+0.68	2.648	+0.98	1.778	0.889
56	Perceived gender (GEND)vn_GEND_reg	4.696	+0.40	4.939	+0.56	4.055	1.588
57	Harmonicity (HARM)vn_HARM_reg	2.145	-0.40	2.174	-0.37	2.480	0.836
58	Metallic character (METL)vn_METL_reg	2.963	+1.40	3.023	+1.46	1.621	0.958
59	Pitch range (RANG)vn_RANG_reg	2.407	-0.56	2.484	-0.48	2.914	0.897
60	Recording quality (RCQL)vn_RCQL_reg	2.544	-0.24	2.629	-0.14	2.754	0.888
61	Vocal register (REGS)vn_REGS_reg	0.564	-0.50	0.412	-0.62	1.198	1.268
62	Respiration (RESP)vn_RESP_reg	2.439	-0.23	2.690	+0.01	2.680	1.056
63	Roughness (ROUG)vn_ROUG_reg	2.636	+0.68	2.564	+0.60	2.033	0.887
64	Chest resonance (R_CHST)vn_R_CHST_reg	3.215	+1.28	3.461	+1.57	2.135	0.844
65	Head resonance (R_HEAD)vn_R_HEAD_reg	2.248	+0.12	2.182	+0.04	2.148	0.822
66	Mask resonance (R_MASK)vn_R_MASK_reg	2.510	+0.60	2.387	+0.48	1.908	1.005
67	Mixed resonance (R_MIXD)vn_R_MIXD_reg	2.521	+1.29	2.867	+1.70	1.436	0.841
68	Nasal resonance (R_NASL)vn_R_NASL_reg	4.302	+1.44	4.285	+1.43	2.791	1.047
69	Oral resonance (R_ORAL)vn_R_ORAL_reg	3.236	+1.42	3.172	+1.34	2.184	0.741
70	Throat resonance (R_THRT)vn_R_THRT_reg	3.370	+1.62	3.389	+1.64	2.070	0.803
71	Smoothness (SMTH)vn_SMTH_reg	2.046	-0.09	2.128	-0.01	2.143	1.093
72	Stance (STNC)vn_STNC_reg	3.237	+0.53	3.059	+0.37	2.633	1.137
73	Speech structure (STRU)vn_STRU_reg	2.434	+0.31	2.356	+0.23	2.137	0.958
74	ASMR style (S_ASMR)vn_S_ASMR_reg	0.564	-0.57	0.758	-0.43	1.370	1.411
75	Authoritative style (S_AUTH)vn_S_AUTH_reg	2.810	+1.65	2.948	+1.78	1.088	1.043
76	Cartoonish style (S_CART)vn_S_CART_reg	1.857	+0.21	2.099	+0.39	1.560	1.401
77	Casual style (S_CASU)vn_S_CASU_reg	3.364	-0.34	3.132	-0.52	3.793	1.278
78	Conversational style (S_CONV)vn_S_CONV_reg	3.025	+0.33	2.852	+0.20	2.594	1.318
79	Dramatic style (S_DRAM)vn_S_DRAM_reg	1.974	-0.65	2.134	-0.51	2.721	1.148
80	Formal style (S_FORM)vn_S_FORM_reg	2.537	+1.31	2.719	+1.49	1.195	1.021
81	Monologue style (S_MONO)vn_S_MONO_reg	3.456	+0.49	3.625	+0.62	2.824	1.284
82	Narrator style (S_NARR)vn_S_NARR_reg	1.752	+0.31	1.755	+0.31	1.307	1.446
83	Newsreader style (S_NEWS)vn_S_NEWS_reg	0.691	+0.50	0.763	+0.62	0.408	0.568
84	Playful style (S_PLAY)vn_S_PLAY_reg	2.842	+0.37	2.903	+0.42	2.352	1.315
85	Ranting or angry style (S_RANT)vn_S_RANT_reg	0.562	-0.50	0.432	-0.61	1.213	1.289
86	Storytelling style (S_STRY)vn_S_STRY_reg	2.528	+0.03	2.569	+0.06	2.480	1.366
87	Teacher or didactic style (S_TECH)vn_S_TECH_reg	3.117	+2.01	3.535	+2.36	0.646	1.227
88	Whispered talking style (S_WHIS)vn_S_WHIS_reg	1.790	+0.12	1.924	+0.20	1.597	1.618
89	Tempo (TEMP)vn_TEMP_reg	2.130	+0.01	1.821	-0.25	2.117	1.190
90	Tension (TENS)vn_TENS_reg	1.994	+0.51	2.092	+0.63	1.559	0.852
91	Valence (VALN)vn_VALN_reg	3.042	+0.64	3.122	+0.71	2.328	1.118
92	Valence shift (VALS)vn_VALS_reg	3.759	+1.15	3.862	+1.25	2.518	1.079
93	Velocity flux (VFLX)vn_VFLX_reg	2.256	-0.00	2.489	+0.19	2.256	1.208
94	Volatility (VOLT)vn_VOLT_reg	2.301	-0.32	2.186	-0.45	2.586	0.886
95	Vulnerability (VULN)vn_VULN_reg	1.978	-0.68	1.819	-0.84	2.648	0.984
96	Warmth (WARM)vn_WARM_reg	2.740	+0.18	2.783	+0.23	2.578	0.909
Genuineness, blend, and legacy quality Genuineness and vocal-burst blend are predicted. R_quality has Ladder training labels but no valid P3 test labels.
97	Genuineness (0–6)genuineness_0_6	3.823	+0.92	3.459	+0.70	2.332	1.621
98	Vocal-burst blend (0–10)blend_0_10	2.546	-1.51	1.654	-1.83	6.676	2.738
99	Legacy R_quality (no P3 test labels)R_quality	0.910	-0.55	0.756	-1.00	1.095	0.338
Empathic Insight Plus extra scores Nineteen additional clip-level teacher scores, including background noise and content enjoyment.
100	Ageeiv_extra:Age	3.426	+0.60	3.424	+0.59	3.250	0.293
101	Arousaleiv_extra:Arousal	1.125	-0.38	1.022	-0.61	1.289	0.435
102	Authenticityeiv_extra:Authenticity	2.660	-0.05	2.665	-0.02	2.667	0.153
103	Background Noiseeiv_extra:Background_Noise	0.721	-0.33	0.521	-1.08	0.808	0.264
104	Confident vs. Hesitanteiv_extra:Confident_vs._Hesitant	0.909	-0.43	0.898	-0.47	1.040	0.303
105	Gendereiv_extra:Gender	-1.137	-0.52	-1.106	-0.49	-0.621	0.999
106	High-Pitched vs. Low-Pitchedeiv_extra:High-Pitched_vs._Low-Pitched	2.192	+1.46	2.138	+1.24	1.827	0.250
107	Monotone vs. Expressiveeiv_extra:Monotone_vs._Expressive	1.637	-0.47	1.571	-0.61	1.859	0.470
108	Recording Qualityeiv_extra:Recording_Quality	2.288	+0.43	2.359	+0.65	2.144	0.332
109	Serious vs. Humorouseiv_extra:Serious_vs._Humorous	0.860	-0.20	0.820	-0.32	0.929	0.340
110	Soft vs. Harsheiv_extra:Soft_vs._Harsh	0.103	-0.56	0.065	-0.67	0.281	0.320
111	Submissive vs. Dominanteiv_extra:Submissive_vs._Dominant	0.456	+0.25	0.429	+0.17	0.376	0.324
112	Valenceeiv_extra:Valence	0.063	+0.15	0.047	+0.11	0.005	0.380
113	Vulnerable vs. Emotionally Detachedeiv_extra:Vulnerable_vs._Emotionally_Detached	2.375	+1.51	2.375	+1.51	1.715	0.437
114	Warm vs. Coldeiv_extra:Warm_vs._Cold	0.126	+0.25	0.027	-0.08	0.051	0.300
115	score background qualityeiv_extra:score_background_quality	3.738	+0.63	3.654	+0.51	3.301	0.693
116	score content enjoymenteiv_extra:score_content_enjoyment	4.559	+0.17	4.634	+0.42	4.507	0.303
117	score overall qualityeiv_extra:score_overall_quality	3.088	+0.86	2.971	+0.63	2.652	0.507
118	score speech qualityeiv_extra:score_speech_quality	1.937	+0.89	1.946	+0.95	1.808	0.146
Meta AudioBox Aesthetics Four AudioBox aesthetic teacher outputs. Expansions follow the official Meta model card.
119	Content enjoyment (CE)audiobox:CE	5.336	+0.53	5.475	+0.66	4.799	1.018
120	Content usefulness (CU)audiobox:CU	5.484	-0.16	5.573	-0.08	5.649	1.001
121	Production complexity (PC)audiobox:PC	1.890	-0.27	1.738	-0.37	2.331	1.617
122	Production quality (PQ)audiobox:PQ	6.854	-0.22	6.988	-0.06	7.044	0.879
Microsoft DNSMOS Seven DNSMOS teacher outputs: raw and calibrated SIG/BAK/OVRL estimates plus P.808 MOS.
123	Speech signal quality, rawdnsmos:SIG_raw	4.066	+0.25	4.105	+0.31	3.900	0.669
124	Background quality, rawdnsmos:BAK_raw	4.100	+0.79	3.837	+0.56	3.211	1.124
125	Overall quality, rawdnsmos:OVRL_raw	3.719	+0.78	3.599	+0.63	3.085	0.812
126	Speech signal quality, calibrateddnsmos:SIG	3.578	+0.18	3.597	+0.22	3.488	0.501
127	Background quality, calibrateddnsmos:BAK	4.003	+0.66	3.749	+0.39	3.389	0.928
128	Overall quality, calibrateddnsmos:OVRL	3.264	+0.70	3.169	+0.54	2.840	0.606
129	P.808 MOS estimatednsmos:P808_MOS	3.861	+0.89	3.899	+0.96	3.421	0.496
Vocal-burst count The regression target is log(1 + count). A separate table also reports count error after inverse transformation.
130	Vocal-burst count, log(1 + count)burst_count_log1p	0.091	+0.14	0.002	+0.00	0.000	0.647
VoiceCLAP attributes Sixty-one individual VoiceCLAP attribute teacher scores. The raw 768D VoiceCLAP embedding is stored in sidecars but is not a model output.
131	Affectionvoiceclap_attribute:Affection	0.877	-0.13	0.652	-0.53	0.947	0.554
132	Agevoiceclap_attribute:Age	3.532	+0.55	3.398	+0.31	3.229	0.547
133	Amusementvoiceclap_attribute:Amusement	0.303	-0.16	0.182	-0.37	0.392	0.572
134	Angervoiceclap_attribute:Anger	0.888	-0.21	0.801	-0.38	0.992	0.506
135	Arousalvoiceclap_attribute:Arousal	1.556	+0.22	1.415	-0.01	1.420	0.622
136	Astonishment Surprisevoiceclap_attribute:Astonishment_Surprise	0.577	+0.14	0.303	-0.43	0.509	0.479
137	Authenticityvoiceclap_attribute:Authenticity	2.829	+0.35	2.824	+0.32	2.770	0.167
138	Awevoiceclap_attribute:Awe	0.743	+0.79	0.438	-0.39	0.539	0.259
139	Background Noisevoiceclap_attribute:Background_Noise	0.466	-0.38	0.383	-0.70	0.567	0.264
140	Bitternessvoiceclap_attribute:Bitterness	0.539	-0.23	0.526	-0.28	0.592	0.236
141	Concentrationvoiceclap_attribute:Concentration	1.639	+0.80	1.716	+0.94	1.214	0.531
142	Confident vs. Hesitantvoiceclap_attribute:Confident_vs._Hesitant	1.362	+0.62	1.287	+0.47	1.069	0.468
143	Confusionvoiceclap_attribute:Confusion	0.606	-0.11	0.425	-0.65	0.643	0.334
144	Contemplationvoiceclap_attribute:Contemplation	1.111	+0.82	1.122	+0.84	0.780	0.406
145	Contemptvoiceclap_attribute:Contempt	0.635	-0.22	0.564	-0.43	0.709	0.339
146	Contentmentvoiceclap_attribute:Contentment	0.483	-0.34	0.462	-0.41	0.588	0.307
147	Disappointmentvoiceclap_attribute:Disappointment	0.766	+0.02	0.624	-0.47	0.760	0.291
148	Disgustvoiceclap_attribute:Disgust	0.604	-0.10	0.498	-0.61	0.625	0.207
149	Distressvoiceclap_attribute:Distress	0.909	-0.05	0.620	-0.88	0.927	0.350
150	Doubtvoiceclap_attribute:Doubt	0.412	-0.65	0.325	-1.12	0.535	0.188
151	Elationvoiceclap_attribute:Elation	0.585	+0.12	0.489	-0.13	0.539	0.397
152	Embarrassmentvoiceclap_attribute:Embarrassment	0.273	-0.11	0.150	-0.50	0.307	0.314
153	Emotional Numbnessvoiceclap_attribute:Emotional_Numbness	0.584	-0.30	0.694	+0.11	0.664	0.266
154	Fatigue Exhaustionvoiceclap_attribute:Fatigue_Exhaustion	0.308	-0.59	0.274	-0.72	0.462	0.261
155	Fearvoiceclap_attribute:Fear	0.335	-1.33	0.239	-1.79	0.618	0.212
156	Gendervoiceclap_attribute:Gender	-1.077	-0.92	-1.281	-1.12	-0.151	1.005
157	Helplessnessvoiceclap_attribute:Helplessness	0.559	-0.37	0.384	-1.02	0.658	0.268
158	High-Pitched vs. Low-Pitchedvoiceclap_attribute:High-Pitched_vs._Low-Pitched	2.292	+1.21	2.275	+1.16	1.840	0.375
159	Hope Enthusiasm Optimismvoiceclap_attribute:Hope_Enthusiasm_Optimism	0.840	+0.34	0.818	+0.28	0.705	0.396
160	Impatience and Irritabilityvoiceclap_attribute:Impatience_and_Irritability	0.996	-0.10	0.817	-0.43	1.052	0.541
161	Infatuationvoiceclap_attribute:Infatuation	0.269	-1.02	0.149	-1.38	0.608	0.332
162	Interestvoiceclap_attribute:Interest	1.899	+0.68	1.911	+0.71	1.598	0.440
163	Intoxication Altered States of Consciousnessvoiceclap_attribute:Intoxication_Altered_States_of_Consciousness	0.204	-0.64	0.202	-0.65	0.502	0.463
164	Jealousy & Envyvoiceclap_attribute:Jealousy_&_Envy	0.321	-0.82	0.305	-0.89	0.523	0.245
165	Longingvoiceclap_attribute:Longing	0.460	-0.36	0.329	-0.95	0.538	0.220
166	Malevolence Malicevoiceclap_attribute:Malevolence_Malice	0.599	-0.68	0.604	-0.66	0.833	0.346
167	Monotone vs. Expressivevoiceclap_attribute:Monotone_vs._Expressive	1.938	+0.27	1.758	-0.03	1.775	0.594
168	Painvoiceclap_attribute:Pain	0.200	-0.83	0.082	-1.37	0.381	0.218
169	Pleasure Ecstasyvoiceclap_attribute:Pleasure_Ecstasy	0.250	-0.84	0.196	-1.02	0.503	0.301
170	Pridevoiceclap_attribute:Pride	0.907	+0.36	0.818	+0.11	0.780	0.349
171	Recording Qualityvoiceclap_attribute:Recording_Quality	2.332	+0.06	2.400	+0.26	2.313	0.328
172	Reliefvoiceclap_attribute:Relief	0.641	-0.93	0.442	-1.40	1.025	0.415
173	Sadnessvoiceclap_attribute:Sadness	0.716	-0.11	0.498	-0.81	0.752	0.313
174	Serious vs. Humorousvoiceclap_attribute:Serious_vs._Humorous	0.802	-0.00	0.787	-0.03	0.803	0.568
175	Sexual Lustvoiceclap_attribute:Sexual_Lust	0.154	-1.15	0.082	-1.32	0.635	0.419
176	Shamevoiceclap_attribute:Shame	0.644	+0.42	0.480	-0.17	0.526	0.283
177	Soft vs. Harshvoiceclap_attribute:Soft_vs._Harsh	0.080	-0.22	0.024	-0.38	0.160	0.360
178	Sournessvoiceclap_attribute:Sourness	0.561	-0.50	0.419	-0.99	0.706	0.291
179	Submissive vs. Dominantvoiceclap_attribute:Submissive_vs._Dominant	0.685	+0.17	0.666	+0.12	0.623	0.359
180	Teasingvoiceclap_attribute:Teasing	0.184	-0.94	0.134	-1.07	0.540	0.379
181	Thankfulness Gratitudevoiceclap_attribute:Thankfulness_Gratitude	1.376	-0.01	1.052	-0.63	1.384	0.529
182	Triumphvoiceclap_attribute:Triumph	0.665	-0.14	0.546	-0.47	0.716	0.359
183	Valencevoiceclap_attribute:Valence	-0.408	-0.63	-0.352	-0.54	-0.007	0.635
184	Vulnerable vs. Emotionally Detachedvoiceclap_attribute:Vulnerable_vs._Emotionally_Detached	2.230	+1.06	2.356	+1.29	1.638	0.556
185	Warm vs. Coldvoiceclap_attribute:Warm_vs._Cold	0.103	+0.42	0.101	+0.42	-0.066	0.400
186	durationvoiceclap_attribute:duration	9.161	-0.28	8.840	-0.33	10.914	6.354
187	score background qualityvoiceclap_attribute:score_background_quality	3.579	+0.67	3.585	+0.68	3.245	0.498
188	score content enjoymentvoiceclap_attribute:score_content_enjoyment	4.641	-0.10	4.679	+0.16	4.656	0.147
189	score overall qualityvoiceclap_attribute:score_overall_quality	2.852	+0.52	2.845	+0.51	2.635	0.412
190	score speech qualityvoiceclap_attribute:score_speech_quality	1.962	+1.02	1.975	+1.21	1.891	0.069
191	talking speedvoiceclap_attribute:talking_speed	13.131	+1.09	13.762	+1.26	9.028	3.756

All Orange embedding components

The cosine above is the meaningful vector-level comparison; component values have no standalone semantic label.

Timbre — all 128 vector components

Dimension	Tiny	Base	Orange teacher
0	-0.0984	-0.1097	-0.1041
1	0.3476	0.2140	0.0931
2	-0.0451	-0.0472	-0.0577
3	-0.0773	-0.0594	-0.0694
4	0.0654	0.0392	-0.0316
5	-0.1375	-0.1433	-0.1324
6	-0.0692	-0.0635	-0.0948
7	-0.0554	-0.0440	-0.0608
8	-0.1432	-0.1061	-0.0940
9	-0.0802	-0.0757	-0.0365
10	-0.0702	-0.0825	-0.0562
11	-0.0898	-0.1233	-0.0979
12	-0.0004	-0.0635	-0.0539
13	-0.0874	-0.0943	-0.0985
14	-0.0101	-0.0063	0.0070
15	0.0368	0.0131	-0.0224
16	0.0259	0.0621	0.1078
17	-0.0735	-0.0469	-0.0507
18	0.0802	0.0546	0.1425
19	-0.0449	-0.0278	-0.0075
20	-0.0516	-0.0825	-0.1048
21	-0.0754	-0.0925	-0.0963
22	-0.1022	-0.1011	-0.0984
23	-0.1490	-0.1487	-0.1238
24	-0.0275	-0.0206	0.0004
25	0.1270	0.1351	0.0563
26	0.0902	0.1206	0.1494
27	-0.0793	-0.0703	-0.0545
28	-0.0812	-0.0698	-0.0699
29	0.0375	0.0537	0.0126
30	0.0220	0.0558	0.0207
31	0.0106	0.0501	0.1107
32	-0.0879	-0.1007	-0.1008
33	-0.0461	-0.0255	-0.0070
34	-0.0310	-0.0789	-0.0798
35	-0.0344	-0.0406	-0.1020
36	0.0640	0.0515	0.0582
37	-0.0580	-0.0676	-0.1043
38	-0.0103	-0.0286	-0.0017
39	-0.0855	-0.0948	-0.1056
40	-0.1046	-0.0934	-0.1010
41	-0.0344	-0.0424	-0.0224
42	0.0375	0.0952	0.1188
43	0.0759	0.0413	0.0654
44	0.0602	0.0329	0.0725
45	-0.0520	-0.0113	0.0308
46	0.1738	0.2430	0.1063
47	-0.0998	-0.0839	-0.1058
48	0.1251	0.1020	0.0571
49	0.0310	0.0114	-0.0171
50	-0.1337	-0.1061	-0.1071
51	0.0750	0.0438	-0.0242
52	-0.0668	-0.0875	-0.0658
53	0.0149	-0.0229	-0.0406
54	0.0229	0.0598	0.1622
55	0.0277	-0.0238	0.0768
56	0.0133	-0.0447	-0.0179
57	-0.0139	-0.0458	-0.0740
58	-0.0118	-0.0125	-0.0438
59	-0.0542	-0.0320	-0.0123
60	-0.1151	-0.1161	-0.1010
61	-0.0224	-0.0193	-0.0964
62	-0.1027	-0.1034	-0.0979
63	0.0044	0.0249	0.1060
64	-0.1155	-0.1025	-0.1062
65	0.0573	0.0780	0.0953
66	0.1881	0.2122	0.2052
67	-0.0797	-0.0617	-0.0972
68	-0.0068	0.0390	0.0152
69	-0.0523	-0.0753	-0.0959
70	-0.0246	-0.0639	-0.0922
71	-0.0439	-0.0703	-0.1132
72	-0.1289	-0.1206	-0.1013
73	-0.1003	-0.1056	-0.0780
74	0.1232	0.1270	0.1049
75	-0.0473	-0.0048	0.0393
76	0.1967	0.1868	0.1857
77	-0.0084	-0.0017	0.0528
78	0.0025	0.0278	-0.0321
79	-0.0399	-0.0562	-0.0908
80	-0.0167	0.0333	0.0723
81	-0.0006	-0.0349	-0.0219
82	-0.0950	-0.1120	-0.1002
83	0.1093	0.0789	0.0259
84	-0.0437	-0.0444	-0.0138
85	-0.0640	-0.0929	-0.0538
86	-0.0286	-0.0916	-0.0673
87	0.0917	0.1306	0.2100
88	0.1671	0.1913	0.1740
89	0.0069	0.0499	-0.0193
90	-0.0463	-0.0553	-0.1135
91	0.0921	0.1297	0.0790
92	0.0773	0.0408	-0.0177
93	-0.0134	-0.0313	0.0464
94	-0.1065	-0.0934	-0.1066
95	0.1308	0.0528	0.0629
96	-0.0423	-0.0285	0.0395
97	0.0142	0.0113	0.0128
98	0.0113	0.0315	0.1442
99	-0.0167	-0.0347	-0.1003
100	0.1900	0.2466	0.2001
101	0.0389	0.0270	0.0112
102	-0.0955	-0.0744	-0.1120
103	-0.0195	-0.0311	-0.0804
104	-0.0726	-0.0807	-0.1024
105	0.0212	-0.0247	-0.0300
106	0.0282	-0.0167	0.1048
107	0.1451	0.1623	0.1656
108	-0.0387	-0.0528	0.0266
109	-0.0042	-0.0212	-0.0459
110	-0.0011	0.0062	0.0144
111	-0.0220	-0.0162	0.0168
112	0.0602	0.0374	0.0089
113	0.0874	0.0449	0.1199
114	-0.0807	-0.0866	-0.1127
115	0.0377	-0.0126	-0.0039
116	0.2521	0.2358	0.1210
117	-0.1356	-0.1029	-0.0733
118	0.1241	0.0871	0.0472
119	0.1189	0.1029	0.0800
120	-0.0592	-0.0338	-0.1077
121	0.0826	0.0255	0.0493
122	-0.0280	-0.0263	0.0345
123	0.1528	0.1941	0.1426
124	-0.0060	-0.0576	-0.0468
125	0.0499	0.0639	0.0453
126	-0.0759	-0.0852	-0.0902
127	0.0960	0.0721	0.0673

Identity — all 250 vector components

Dimension	Tiny	Base	Orange teacher
0	-0.0028	0.0341	-0.0459
1	0.0114	0.0715	0.1121
2	0.0431	-0.0197	-0.0560
3	-0.0262	-0.0332	-0.0920
4	0.0493	0.0748	0.0782
5	0.0581	0.0327	0.0475
6	0.0035	-0.0120	0.0559
7	0.0150	-0.0154	0.0031
8	-0.0968	-0.0454	-0.0540
9	-0.0293	-0.0767	-0.0517
10	-0.0306	-0.0880	-0.0508
11	-0.0845	-0.0457	-0.0656
12	-0.0019	0.0419	0.1200
13	0.0444	0.0308	0.0313
14	0.0559	0.0572	0.0180
15	0.0405	0.0904	0.0447
16	-0.0607	-0.0913	-0.0700
17	0.0056	0.0224	0.0535
18	-0.0086	-0.0298	0.0204
19	0.0332	-0.0003	-0.0435
20	-0.0253	-0.0814	-0.0485
21	0.0282	0.0235	-0.0238
22	-0.0045	0.0026	-0.0503
23	-0.0963	-0.0791	-0.0469
24	-0.0147	0.0299	0.0624
25	-0.0042	-0.0197	0.0214
26	0.0126	-0.0379	-0.0534
27	-0.0020	0.0192	0.0645
28	-0.0019	-0.0175	-0.0051
29	0.0963	0.1233	0.0289
30	0.2762	0.2325	0.1484
31	0.1575	0.1252	0.2035
32	0.0451	0.0602	0.1194
33	-0.0457	-0.0147	-0.0020
34	-0.0400	-0.0464	0.0148
35	0.0673	0.0715	0.0460
36	0.0197	0.0304	-0.0423
37	0.1786	0.1902	0.1743
38	0.1117	0.0899	0.1122
39	-0.0195	-0.0377	0.0185
40	-0.0131	-0.0294	0.0444
41	0.0691	0.0374	0.0235
42	-0.0545	-0.0819	-0.0482
43	0.1698	0.1026	0.1307
44	0.0442	0.0244	0.0412
45	-0.0133	-0.0374	-0.0288
46	-0.0068	0.0417	-0.0164
47	-0.1122	-0.1214	-0.0635
48	0.0365	-0.0103	0.0356
49	-0.0166	0.0511	0.0511
50	-0.0267	-0.0189	-0.0074
51	-0.0232	0.0225	0.0667
52	-0.0321	0.0212	0.0687
53	0.0274	0.0412	0.0470
54	0.1196	0.1497	0.1288
55	-0.0374	-0.0791	-0.0536
56	-0.0479	-0.0148	-0.0569
57	0.0235	0.0932	0.0354
58	0.0836	0.0346	-0.0071
59	0.0517	0.0781	0.1157
60	-0.0321	-0.0522	-0.0271
61	-0.0012	-0.0617	-0.0450
62	0.0216	0.0265	-0.0067
63	-0.0664	-0.0993	-0.0526
64	-0.0011	-0.0195	-0.0540
65	-0.1496	-0.1261	-0.0591
66	-0.0682	-0.0506	-0.0610
67	0.0787	0.0175	0.0200
68	-0.0119	-0.0101	-0.0446
69	0.0274	0.0464	0.0128
70	-0.0288	-0.0289	0.0030
71	0.0356	0.0182	-0.0508
72	-0.0013	0.0098	0.0482
73	0.0241	-0.0228	-0.0039
74	0.0046	-0.0269	0.0267
75	-0.0477	-0.0023	0.0793
76	0.0845	0.0073	0.0345
77	0.0020	0.0289	0.0524
78	0.0365	0.0617	-0.0172
79	-0.0189	-0.0221	-0.0518
80	-0.0402	0.0570	0.0439
81	-0.0471	-0.0426	-0.0580
82	-0.0139	-0.0421	-0.0465
83	0.0220	0.0405	0.0513
84	-0.0853	-0.0974	-0.0729
85	-0.0955	-0.0626	-0.0518
86	0.0112	-0.0234	0.0548
87	0.0523	0.0110	0.1209
88	0.0096	-0.0106	-0.0038
89	0.0228	0.0286	-0.0390
90	-0.0968	-0.0555	-0.0513
91	-0.0552	-0.0433	0.0041
92	0.0020	-0.0532	-0.0447
93	0.1540	0.1459	0.1815
94	-0.0293	0.0147	-0.0171
95	-0.0686	-0.0081	-0.0540
96	-0.0352	-0.0197	0.0033
97	-0.0264	0.0235	0.0097
98	0.0198	0.0332	0.0345
99	-0.0225	0.0285	0.0511
100	-0.0796	-0.1487	-0.0584
101	-0.0078	-0.0245	0.0281
102	-0.0501	-0.0466	-0.0578
103	-0.0326	0.0244	0.0590
104	-0.0490	-0.0520	-0.0567
105	0.0139	0.0687	-0.0155
106	0.1196	0.0325	0.0184
107	-0.0862	-0.0490	-0.0464
108	0.0161	-0.0207	-0.0059
109	-0.0054	0.0148	-0.0411
110	0.0055	0.0019	-0.0207
111	0.0105	0.0419	-0.0136
112	0.0378	-0.0212	-0.0418
113	-0.0444	-0.0384	-0.0882
114	-0.0809	-0.0513	-0.0576
115	0.1452	0.1619	0.1388
116	-0.0787	-0.0701	-0.0929
117	0.0933	0.0522	0.0403
118	-0.0493	-0.0227	0.0060
119	-0.1416	-0.1097	-0.0532
120	-0.0241	-0.0051	-0.0498
121	-0.0831	-0.0880	-0.0556
122	-0.0651	-0.0208	-0.0130
123	-0.0633	-0.0329	-0.0072
124	-0.0730	-0.0833	-0.0516
125	0.0288	0.0112	0.0811
126	-0.0131	-0.0251	-0.0046
127	-0.0625	-0.0501	-0.0532
128	-0.0387	-0.0438	-0.0634
129	-0.0840	-0.0518	-0.0549
130	0.0280	0.0007	0.0203
131	-0.0787	-0.0577	-0.0453
132	-0.0495	-0.0913	-0.0548
133	-0.0278	-0.0301	0.0151
134	-0.0170	0.0120	0.0318
135	-0.0244	-0.0025	-0.0521
136	-0.0183	-0.0281	-0.0126
137	-0.0066	0.0088	-0.0210
138	-0.0708	-0.0445	-0.0456
139	0.0094	0.0139	0.0108
140	0.0262	0.0322	0.0028
141	0.0488	0.0287	0.0203
142	-0.0140	0.0546	0.0564
143	-0.0510	0.0003	0.0397
144	0.0161	-0.0029	-0.0450
145	-0.0462	-0.0499	-0.0170
146	0.0647	0.0621	0.0970
147	-0.1056	-0.1021	-0.0460
148	0.0060	0.0051	-0.0217
149	-0.0249	0.0299	0.1266
150	0.0007	0.0419	0.0437
151	0.0422	0.0927	0.0613
152	0.0006	-0.0294	-0.0574
153	-0.0691	-0.0320	-0.0815
154	-0.0607	-0.0706	-0.0504
155	-0.0218	0.0341	-0.0520
156	-0.0717	-0.0454	-0.0518
157	0.1443	0.0847	0.1117
158	-0.0501	-0.0654	-0.0644
159	0.1214	0.0908	0.0734
160	-0.0673	-0.0146	-0.0107
161	-0.0336	0.0187	-0.0216
162	-0.0814	-0.0315	0.0289
163	0.0315	0.0527	0.0605
164	-0.0515	-0.0377	-0.0454
165	0.0407	0.0692	0.0574
166	0.1302	0.1732	0.1837
167	-0.1135	-0.0777	-0.0656
168	0.0117	0.0355	0.0314
169	0.0827	0.1214	0.0893
170	0.0306	0.0518	-0.0129
171	0.0499	0.0438	0.0157
172	-0.0374	-0.0539	0.0714
173	-0.0567	-0.0687	-0.0177
174	0.0981	0.0965	0.1499
175	-0.0189	-0.0167	-0.0742
176	-0.0611	-0.0238	-0.0440
177	-0.0308	-0.0214	-0.0426
178	-0.0200	0.0205	0.0808
179	0.0691	0.0260	-0.0457
180	0.0308	0.0098	0.0873
181	0.0501	0.1153	0.1267
182	-0.0464	-0.0229	-0.0447
183	0.0002	0.0334	0.0367
184	-0.0572	-0.0258	-0.0526
185	0.0347	0.0494	0.0640
186	-0.0146	-0.0325	-0.0606
187	0.0429	0.1770	0.0856
188	0.0207	0.0149	-0.0486
189	0.0831	0.1003	0.1165
190	0.0367	-0.0095	0.0675
191	-0.0629	-0.0607	-0.0691
192	0.1302	0.0683	0.1121
193	0.0704	0.0602	0.0611
194	0.0352	-0.0129	0.0385
195	0.1425	0.2109	0.1202
196	-0.0211	-0.0697	-0.0502
197	0.0999	0.1144	0.1029
198	-0.0572	-0.0711	-0.0500
199	0.0330	0.0748	0.0801
200	0.1104	0.1732	0.1582
201	-0.0347	-0.0098	-0.0158
202	-0.0673	-0.0315	-0.0116
203	-0.0809	-0.0520	-0.0414
204	-0.0449	-0.0485	0.0356
205	-0.0361	0.0168	0.0370
206	-0.0343	-0.0313	0.0271
207	0.0391	0.0459	0.0769
208	-0.0889	-0.0932	-0.0536
209	-0.0633	-0.0857	-0.0435
210	-0.0018	-0.0337	-0.0673
211	-0.0051	-0.0327	0.0368
212	0.0085	0.0650	0.0462
213	0.0252	0.0377	0.0099
214	0.1240	0.1299	0.0880
215	-0.0550	-0.0923	-0.0435
216	0.0223	0.0360	-0.0435
217	0.0040	0.0020	0.0347
218	0.0959	0.0412	0.0662
219	0.0047	0.0271	0.0033
220	-0.0915	-0.0941	-0.0571
221	0.0142	0.0124	0.0876
222	-0.0787	-0.0414	-0.0606
223	0.0000	0.0318	0.1058
224	0.1434	0.0786	0.0389
225	-0.0420	-0.0581	-0.0430
226	-0.0585	-0.0294	0.0670
227	-0.0268	0.0025	-0.0283
228	-0.0611	-0.0339	0.0488
229	-0.0383	-0.0315	-0.0094
230	0.0195	0.0577	0.0276
231	0.1034	0.0513	-0.0339
232	-0.0135	0.0358	0.0444
233	-0.0400	-0.0214	0.0086
234	-0.0020	-0.0763	-0.0439
235	0.1012	0.0890	0.1328
236	-0.0041	-0.0289	-0.0444
237	0.1082	0.0824	0.0416
238	0.0073	-0.0038	-0.0567
239	-0.0032	-0.0082	-0.0535
240	-0.0059	0.0339	0.0415
241	-0.0893	-0.0379	0.0195
242	-0.0295	-0.0128	-0.0762
243	0.0552	0.0631	0.1143
244	-0.0413	-0.0555	-0.0550
245	0.0567	0.0795	-0.0128
246	0.0078	0.0123	0.0089
247	0.0664	0.0562	0.0576
248	-0.0739	-0.0562	0.0373
249	0.0152	-0.0101	0.0085

Source: Emolia / Emilia source archive · SHA-256 04491c3d8aff8226…

e07JapaneseEmolia / Emilia

Emolia JA · JA_B00000_S00310_W000001

Natural speech · Original speech · 13.2 s

だからそういう意味での資格のことを話したんだけど、まぁ、えっと、そう、今日資格なんだけど、私はね、こないだ、こないだ聴覚の話してた時に、女の人は聴覚がすごく、

Tiny Base · values are model estimates, not ground truth

Strongest emotions relative to training

Contemplation

z +1.42 / +2.20raw 0.93 / 1.40

Contentment

z +1.79 / +1.53raw 0.92 / 0.79

Doubt

z +0.85 / +1.48raw 0.40 / 0.70

Concentration

z +1.16 / +1.28raw 1.49 / 1.58

Astonishment Surprise

z +0.57 / +0.94raw 0.33 / 0.54

Sourness

z +0.94 / +0.47raw 0.41 / 0.20

Interest

z +0.80 / +0.92raw 2.31 / 2.42

The center of each bar is the S9 teacher median. Positive z is to the right; negative z is to the left. Ranking uses z, not raw teacher units.

Strongest VoiceNet dimensions relative to training

Teacher or didactic style (S_TECH)

z +2.36 / +2.36raw 3.54 / 3.54

Vocal register (REGS)

z +1.88 / +2.08raw 3.58 / 3.84

Cartoonish style (S_CART)

z +1.96 / +1.31raw 4.30 / 3.39

Pitch range (RANG)

z +1.40 / +1.32raw 4.17 / 4.10

Playful style (S_PLAY)

z +1.36 / +1.32raw 4.14 / 4.09

Conversational style (S_CONV)

z +1.19 / +1.33raw 4.17 / 4.35

Tempo (TEMP)

z +0.97 / +1.16raw 3.27 / 3.49

All 57 VoiceNet predictions, including raw units, are in the full table below. These seven are ranked by z; the top values may differ from the strongest raw dimensions.

Voice, speed and quality scores in context

Genuineness (0–6)z +1.06 / +1.15raw 4.04 / 4.19

Vocal-burst blend (0–10)z +0.24 / +0.28raw 7.34 / 7.44

Content enjoyment (CE)z +0.03 / +0.36raw 4.83 / 5.17

Production quality (PQ)z -0.65 / -0.02raw 6.47 / 7.02

Speech signal quality, calibratedz +0.08 / +0.10raw 3.53 / 3.54

Background quality, calibratedz -0.05 / +0.24raw 3.34 / 3.61

Overall quality, calibratedz +0.09 / +0.24raw 2.89 / 2.99

P.808 MOS estimatez +0.11 / +0.28raw 3.47 / 3.56

score content enjoymentz +0.15 / -0.11raw 4.55 / 4.47

score overall qualityz +0.41 / +0.27raw 2.86 / 2.79

Background Noisez -0.23 / -0.15raw 0.75 / 0.77

Tempo (TEMP)z +0.97 / +1.16raw 3.27 / 3.49

Arousal (AROU)z -0.16 / -0.45raw 2.18 / 1.84

Valence (VALN)z +0.94 / +0.92raw 3.38 / 3.36

Recording quality (RCQL)z -0.04 / +0.10raw 2.72 / 2.85

Background noise (BKGN)z +0.42 / +0.42raw 3.02 / 3.02

talking speedz -1.35 / +0.10raw 3.94 / 9.42

Characters per second (CPS): 5.96 raw · z -0.82

Orange speaker embedding reconstruction

Cosine against Orange on this same clip (higher means closer to that teacher vector):

Embedding	Tiny	Base
Timbre · 128D	0.829	0.850
Identity · 250D	0.620	0.605

Vocal-burst regions

Tiny

Base

0 s13.2 s

Verified burst intervals are unavailable for this clip.

Tiny: 2 regions, count-head estimate 1.23; Base: 1 regions, count-head estimate 1.11.

Exact predicted start and end times

Model	Region	Start (s)	End (s)	Duration (s)
Tiny	1	0.02	0.36	0.34
Tiny	2	4.00	4.20	0.20
Base	1	4.00	4.22	0.22

All 192 score slots · raw and z values

#	Target	Tiny raw	Tiny z	Base raw	Base z	Train median	Train SD
Emotion scores Forty clip-level Empathic Insight emotion teacher outputs. Each row evaluates one named emotion score.
0	Affectionemo_Affection	0.368	+0.63	0.226	+0.38	0.007	0.570
1	Amusementemo_Amusement	0.338	+0.38	0.178	+0.20	-0.001	0.885
2	Angeremo_Anger	0.196	+0.31	-0.084	-0.14	0.004	0.613
3	Astonishment Surpriseemo_Astonishment_Surprise	0.333	+0.57	0.544	+0.94	0.005	0.572
4	Aweemo_Awe	0.044	+0.10	0.014	+0.03	0.000	0.427
5	Bitternessemo_Bitterness	0.052	+0.09	0.010	-0.01	0.013	0.415
6	Concentrationemo_Concentration	1.492	+1.16	1.584	+1.28	0.634	0.741
7	Confusionemo_Confusion	0.322	+0.59	0.350	+0.65	0.001	0.540
8	Contemplationemo_Contemplation	0.929	+1.42	1.398	+2.20	0.082	0.598
9	Contemptemo_Contempt	0.324	+0.70	0.108	+0.23	-0.000	0.464
10	Contentmentemo_Contentment	0.921	+1.79	0.787	+1.53	0.000	0.514
11	Disappointmentemo_Disappointment	0.358	+0.51	0.151	+0.22	0.000	0.700
12	Disgustemo_Disgust	0.176	+0.34	0.019	+0.02	0.007	0.489
13	Distressemo_Distress	0.052	+0.06	0.009	+0.01	0.000	0.821
14	Doubtemo_Doubt	0.402	+0.85	0.697	+1.48	0.006	0.466
15	Elationemo_Elation	0.332	+0.44	0.140	+0.18	0.012	0.728
16	Embarrassmentemo_Embarrassment	0.416	+0.87	0.304	+0.61	0.043	0.430
17	Emotional Numbnessemo_Emotional_Numbness	-0.023	-0.03	-0.010	-0.02	0.004	0.917
18	Fatigue Exhaustionemo_Fatigue_Exhaustion	0.022	-0.01	0.037	+0.02	0.028	0.539
19	Fearemo_Fear	-0.034	-0.08	-0.034	-0.08	0.015	0.610
20	Helplessnessemo_Helplessness	-0.014	-0.02	-0.042	-0.05	-0.004	0.696
21	Hope Enthusiasm Optimismemo_Hope_Enthusiasm_Optimism	0.474	+0.47	0.687	+0.75	0.117	0.760
22	Impatience and Irritabilityemo_Impatience_and_Irritability	0.677	+0.75	0.151	+0.00	0.149	0.705
23	Infatuationemo_Infatuation	-0.009	+0.01	-0.042	-0.05	-0.015	0.533
24	Interestemo_Interest	2.313	+0.80	2.420	+0.92	1.589	0.907
25	Intoxication Altered States of Consciousnessemo_Intoxication_Altered_States_of_Consciousness	0.007	+0.06	0.021	+0.08	-0.025	0.559
26	Jealousy and Envyemo_Jealousy_and_Envy	0.170	+0.25	0.077	+0.04	0.059	0.442
27	Longingemo_Longing	0.229	+0.23	0.323	+0.37	0.087	0.632
28	Malevolence Maliceemo_Malevolence_Malice	0.071	+0.03	0.078	+0.04	0.055	0.534
29	Painemo_Pain	-0.033	-0.05	0.040	+0.07	-0.002	0.579
30	Pleasure Ecstasyemo_Pleasure_Ecstasy	0.240	+0.36	0.070	+0.09	0.017	0.614
31	Prideemo_Pride	0.127	+0.25	0.097	+0.19	0.002	0.509
32	Reliefemo_Relief	0.088	+0.08	0.007	-0.04	0.033	0.681
33	Sadnessemo_Sadness	0.032	+0.04	-0.001	-0.00	0.000	0.759
34	Sexual Lustemo_Sexual_Lust	0.139	+0.22	0.025	-0.01	0.030	0.494
35	Shameemo_Shame	0.039	+0.05	0.014	+0.00	0.013	0.510
36	Sournessemo_Sourness	0.407	+0.94	0.201	+0.47	-0.005	0.439
37	Teasingemo_Teasing	0.212	+0.39	0.028	+0.05	0.000	0.545
38	Thankfulness Gratitudeemo_Thankfulness_Gratitude	0.137	+0.14	0.049	+0.01	0.041	0.697
39	Triumphemo_Triumph	-0.003	+0.01	-0.010	-0.01	-0.007	0.521
VoiceNet dimensions Fifty-seven VoiceNet voice, delivery, style, and recording dimensions. Codes are expanded in the target column.
40	Perceived voice age (AGEV)vn_AGEV_reg	3.420	+0.35	3.326	+0.28	2.984	1.238
41	Arousal (AROU)vn_AROU_reg	2.181	-0.16	1.843	-0.45	2.359	1.147
42	Arousal shift (ARSH)vn_ARSH_reg	2.522	-0.07	2.551	-0.03	2.580	0.867
43	Vocal attack (ATCK)vn_ATCK_reg	2.216	+0.04	2.202	+0.03	2.162	1.295
44	Background noise (BKGN)vn_BKGN_reg	3.024	+0.42	3.021	+0.42	2.703	0.761
45	Brightness (BRGT)vn_BRGT_reg	2.451	+0.57	2.483	+0.61	1.991	0.813
46	Speech chunking (CHNK)vn_CHNK_reg	2.530	+0.55	2.895	+0.85	1.847	1.239
47	Articulation clarity (CLRT)vn_CLRT_reg	2.365	+0.37	2.607	+0.62	2.018	0.945
48	Cognitive load (COGL)vn_COGL_reg	2.423	+0.31	2.309	+0.20	2.094	1.061
49	Dynamic arc (DARC)vn_DARC_reg	1.646	+0.02	1.317	-0.22	1.615	1.380
50	Disfluency (DFLU)vn_DFLU_reg	3.078	+0.50	3.023	+0.45	2.488	1.184
51	Emphasis (EMPH)vn_EMPH_reg	3.362	+0.50	3.313	+0.46	2.607	1.524
52	Esthetics (ESTH)vn_ESTH_reg	2.524	+0.16	2.784	+0.49	2.402	0.782
53	Content appropriateness (EXPL)vn_EXPL_reg	0.274	+0.58	0.169	+0.26	0.086	0.322
54	Focus (FOCS)vn_FOCS_reg	2.317	-0.02	2.314	-0.03	2.344	1.102
55	Fullness (FULL)vn_FULL_reg	1.609	-0.19	1.831	+0.06	1.778	0.889
56	Perceived gender (GEND)vn_GEND_reg	1.605	-1.54	1.629	-1.53	4.055	1.588
57	Harmonicity (HARM)vn_HARM_reg	1.721	-0.91	1.873	-0.73	2.480	0.836
58	Metallic character (METL)vn_METL_reg	1.826	+0.21	1.856	+0.25	1.621	0.958
59	Pitch range (RANG)vn_RANG_reg	4.173	+1.40	4.096	+1.32	2.914	0.897
60	Recording quality (RCQL)vn_RCQL_reg	2.716	-0.04	2.846	+0.10	2.754	0.888
61	Vocal register (REGS)vn_REGS_reg	3.582	+1.88	3.837	+2.08	1.198	1.268
62	Respiration (RESP)vn_RESP_reg	3.820	+1.08	3.386	+0.67	2.680	1.056
63	Roughness (ROUG)vn_ROUG_reg	2.777	+0.84	2.829	+0.90	2.033	0.887
64	Chest resonance (R_CHST)vn_R_CHST_reg	2.222	+0.10	2.348	+0.25	2.135	0.844
65	Head resonance (R_HEAD)vn_R_HEAD_reg	2.896	+0.91	2.890	+0.90	2.148	0.822
66	Mask resonance (R_MASK)vn_R_MASK_reg	2.502	+0.59	2.674	+0.76	1.908	1.005
67	Mixed resonance (R_MIXD)vn_R_MIXD_reg	1.591	+0.18	2.037	+0.72	1.436	0.841
68	Nasal resonance (R_NASL)vn_R_NASL_reg	3.807	+0.97	3.345	+0.53	2.791	1.047
69	Oral resonance (R_ORAL)vn_R_ORAL_reg	2.301	+0.16	2.550	+0.50	2.184	0.741
70	Throat resonance (R_THRT)vn_R_THRT_reg	2.044	-0.03	2.238	+0.21	2.070	0.803
71	Smoothness (SMTH)vn_SMTH_reg	3.070	+0.85	3.105	+0.88	2.143	1.093
72	Stance (STNC)vn_STNC_reg	2.948	+0.28	2.870	+0.21	2.633	1.137
73	Speech structure (STRU)vn_STRU_reg	2.445	+0.32	2.653	+0.54	2.137	0.958
74	ASMR style (S_ASMR)vn_S_ASMR_reg	1.250	-0.08	1.567	+0.14	1.370	1.411
75	Authoritative style (S_AUTH)vn_S_AUTH_reg	1.812	+0.69	1.950	+0.83	1.088	1.043
76	Cartoonish style (S_CART)vn_S_CART_reg	4.300	+1.96	3.391	+1.31	1.560	1.401
77	Casual style (S_CASU)vn_S_CASU_reg	4.658	+0.68	4.598	+0.63	3.793	1.278
78	Conversational style (S_CONV)vn_S_CONV_reg	4.165	+1.19	4.349	+1.33	2.594	1.318
79	Dramatic style (S_DRAM)vn_S_DRAM_reg	3.816	+0.95	3.585	+0.75	2.721	1.148
80	Formal style (S_FORM)vn_S_FORM_reg	1.383	+0.18	1.574	+0.37	1.195	1.021
81	Monologue style (S_MONO)vn_S_MONO_reg	3.372	+0.43	3.431	+0.47	2.824	1.284
82	Narrator style (S_NARR)vn_S_NARR_reg	1.698	+0.27	1.918	+0.42	1.307	1.446
83	Newsreader style (S_NEWS)vn_S_NEWS_reg	0.460	+0.09	0.521	+0.20	0.408	0.568
84	Playful style (S_PLAY)vn_S_PLAY_reg	4.137	+1.36	4.087	+1.32	2.352	1.315
85	Ranting or angry style (S_RANT)vn_S_RANT_reg	2.077	+0.67	1.307	+0.07	1.213	1.289
86	Storytelling style (S_STRY)vn_S_STRY_reg	4.040	+1.14	3.529	+0.77	2.480	1.366
87	Teacher or didactic style (S_TECH)vn_S_TECH_reg	3.535	+2.36	3.535	+2.36	0.646	1.227
88	Whispered talking style (S_WHIS)vn_S_WHIS_reg	2.242	+0.40	2.210	+0.38	1.597	1.618
89	Tempo (TEMP)vn_TEMP_reg	3.273	+0.97	3.494	+1.16	2.117	1.190
90	Tension (TENS)vn_TENS_reg	1.590	+0.04	1.250	-0.36	1.559	0.852
91	Valence (VALN)vn_VALN_reg	3.378	+0.94	3.360	+0.92	2.328	1.118
92	Valence shift (VALS)vn_VALS_reg	3.064	+0.51	3.347	+0.77	2.518	1.079
93	Velocity flux (VFLX)vn_VFLX_reg	2.500	+0.20	2.596	+0.28	2.256	1.208
94	Volatility (VOLT)vn_VOLT_reg	3.115	+0.60	3.046	+0.52	2.586	0.886
95	Vulnerability (VULN)vn_VULN_reg	2.434	-0.22	2.330	-0.32	2.648	0.984
96	Warmth (WARM)vn_WARM_reg	3.160	+0.64	3.210	+0.69	2.578	0.909
Genuineness, blend, and legacy quality Genuineness and vocal-burst blend are predicted. R_quality has Ladder training labels but no valid P3 test labels.
97	Genuineness (0–6)genuineness_0_6	4.043	+1.06	4.194	+1.15	2.332	1.621
98	Vocal-burst blend (0–10)blend_0_10	7.337	+0.24	7.440	+0.28	6.676	2.738
99	Legacy R_quality (no P3 test labels)R_quality	1.408	+0.93	1.442	+1.03	1.095	0.338
Empathic Insight Plus extra scores Nineteen additional clip-level teacher scores, including background noise and content enjoyment.
100	Ageeiv_extra:Age	3.245	-0.02	3.256	+0.02	3.250	0.293
101	Arousaleiv_extra:Arousal	1.550	+0.60	1.282	-0.02	1.289	0.435
102	Authenticityeiv_extra:Authenticity	2.884	+1.42	2.856	+1.23	2.667	0.153
103	Background Noiseeiv_extra:Background_Noise	0.747	-0.23	0.768	-0.15	0.808	0.264
104	Confident vs. Hesitanteiv_extra:Confident_vs._Hesitant	1.363	+1.07	1.568	+1.74	1.040	0.303
105	Gendereiv_extra:Gender	1.527	+2.15	1.356	+1.98	-0.621	0.999
106	High-Pitched vs. Low-Pitchedeiv_extra:High-Pitched_vs._Low-Pitched	1.694	-0.53	1.666	-0.65	1.827	0.250
107	Monotone vs. Expressiveeiv_extra:Monotone_vs._Expressive	2.660	+1.71	2.635	+1.65	1.859	0.470
108	Recording Qualityeiv_extra:Recording_Quality	2.362	+0.66	2.288	+0.43	2.144	0.332
109	Serious vs. Humorouseiv_extra:Serious_vs._Humorous	1.260	+0.97	1.304	+1.10	0.929	0.340
110	Soft vs. Harsheiv_extra:Soft_vs._Harsh	0.753	+1.48	0.807	+1.65	0.281	0.320
111	Submissive vs. Dominanteiv_extra:Submissive_vs._Dominant	0.521	+0.45	0.244	-0.41	0.376	0.324
112	Valenceeiv_extra:Valence	0.307	+0.79	0.120	+0.30	0.005	0.380
113	Vulnerable vs. Emotionally Detachedeiv_extra:Vulnerable_vs._Emotionally_Detached	1.306	-0.93	1.323	-0.90	1.715	0.437
114	Warm vs. Coldeiv_extra:Warm_vs._Cold	0.283	+0.77	0.344	+0.97	0.051	0.300
115	score background qualityeiv_extra:score_background_quality	3.440	+0.20	3.362	+0.09	3.301	0.693
116	score content enjoymenteiv_extra:score_content_enjoyment	4.553	+0.15	4.474	-0.11	4.507	0.303
117	score overall qualityeiv_extra:score_overall_quality	2.858	+0.41	2.787	+0.27	2.652	0.507
118	score speech qualityeiv_extra:score_speech_quality	1.765	-0.29	1.760	-0.32	1.808	0.146
Meta AudioBox Aesthetics Four AudioBox aesthetic teacher outputs. Expansions follow the official Meta model card.
119	Content enjoyment (CE)audiobox:CE	4.829	+0.03	5.167	+0.36	4.799	1.018
120	Content usefulness (CU)audiobox:CU	5.270	-0.38	5.656	+0.01	5.649	1.001
121	Production complexity (PC)audiobox:PC	2.256	-0.05	2.281	-0.03	2.331	1.617
122	Production quality (PQ)audiobox:PQ	6.473	-0.65	7.024	-0.02	7.044	0.879
Microsoft DNSMOS Seven DNSMOS teacher outputs: raw and calibrated SIG/BAK/OVRL estimates plus P.808 MOS.
123	Speech signal quality, rawdnsmos:SIG_raw	3.973	+0.11	3.977	+0.12	3.900	0.669
124	Background quality, rawdnsmos:BAK_raw	3.326	+0.10	3.544	+0.30	3.211	1.124
125	Overall quality, rawdnsmos:OVRL_raw	3.224	+0.17	3.313	+0.28	3.085	0.812
126	Speech signal quality, calibrateddnsmos:SIG	3.529	+0.08	3.536	+0.10	3.488	0.501
127	Background quality, calibrateddnsmos:BAK	3.340	-0.05	3.609	+0.24	3.389	0.928
128	Overall quality, calibrateddnsmos:OVRL	2.892	+0.09	2.987	+0.24	2.840	0.606
129	P.808 MOS estimatednsmos:P808_MOS	3.475	+0.11	3.561	+0.28	3.421	0.496
Vocal-burst count The regression target is log(1 + count). A separate table also reports count error after inverse transformation.
130	Vocal-burst count, log(1 + count)burst_count_log1p	0.802	+1.24	0.746	+1.15	0.000	0.647
VoiceCLAP attributes Sixty-one individual VoiceCLAP attribute teacher scores. The raw 768D VoiceCLAP embedding is stored in sidecars but is not a model output.
131	Affectionvoiceclap_attribute:Affection	1.264	+0.57	1.369	+0.76	0.947	0.554
132	Agevoiceclap_attribute:Age	3.104	-0.23	3.051	-0.32	3.229	0.547
133	Amusementvoiceclap_attribute:Amusement	0.969	+1.01	0.860	+0.82	0.392	0.572
134	Angervoiceclap_attribute:Anger	0.579	-0.82	0.777	-0.43	0.992	0.506
135	Arousalvoiceclap_attribute:Arousal	1.748	+0.53	1.773	+0.57	1.420	0.622
136	Astonishment Surprisevoiceclap_attribute:Astonishment_Surprise	1.077	+1.19	0.958	+0.94	0.509	0.479
137	Authenticityvoiceclap_attribute:Authenticity	3.083	+1.87	3.046	+1.65	2.770	0.167
138	Awevoiceclap_attribute:Awe	0.647	+0.41	0.652	+0.43	0.539	0.259
139	Background Noisevoiceclap_attribute:Background_Noise	0.617	+0.19	0.521	-0.18	0.567	0.264
140	Bitternessvoiceclap_attribute:Bitterness	0.290	-1.28	0.370	-0.94	0.592	0.236
141	Concentrationvoiceclap_attribute:Concentration	1.151	-0.12	1.251	+0.07	1.214	0.531
142	Confident vs. Hesitantvoiceclap_attribute:Confident_vs._Hesitant	1.606	+1.15	1.928	+1.84	1.069	0.468
143	Confusionvoiceclap_attribute:Confusion	1.187	+1.63	1.321	+2.03	0.643	0.334
144	Contemplationvoiceclap_attribute:Contemplation	0.896	+0.29	1.065	+0.70	0.780	0.406
145	Contemptvoiceclap_attribute:Contempt	0.762	+0.16	0.675	-0.10	0.709	0.339
146	Contentmentvoiceclap_attribute:Contentment	0.997	+1.33	0.804	+0.70	0.588	0.307
147	Disappointmentvoiceclap_attribute:Disappointment	0.808	+0.17	0.816	+0.19	0.760	0.291
148	Disgustvoiceclap_attribute:Disgust	0.544	-0.39	0.595	-0.14	0.625	0.207
149	Distressvoiceclap_attribute:Distress	0.701	-0.65	0.727	-0.57	0.927	0.350
150	Doubtvoiceclap_attribute:Doubt	0.651	+0.62	0.805	+1.43	0.535	0.188
151	Elationvoiceclap_attribute:Elation	1.040	+1.26	0.790	+0.63	0.539	0.397
152	Embarrassmentvoiceclap_attribute:Embarrassment	0.714	+1.30	0.746	+1.40	0.307	0.314
153	Emotional Numbnessvoiceclap_attribute:Emotional_Numbness	0.117	-2.06	0.215	-1.69	0.664	0.266
154	Fatigue Exhaustionvoiceclap_attribute:Fatigue_Exhaustion	0.228	-0.89	0.215	-0.94	0.462	0.261
155	Fearvoiceclap_attribute:Fear	0.437	-0.85	0.467	-0.71	0.618	0.212
156	Gendervoiceclap_attribute:Gender	1.230	+1.37	1.293	+1.44	-0.151	1.005
157	Helplessnessvoiceclap_attribute:Helplessness	0.558	-0.37	0.550	-0.40	0.658	0.268
158	High-Pitched vs. Low-Pitchedvoiceclap_attribute:High-Pitched_vs._Low-Pitched	1.759	-0.22	1.678	-0.43	1.840	0.375
159	Hope Enthusiasm Optimismvoiceclap_attribute:Hope_Enthusiasm_Optimism	1.154	+1.13	1.018	+0.79	0.705	0.396
160	Impatience and Irritabilityvoiceclap_attribute:Impatience_and_Irritability	0.954	-0.18	1.069	+0.03	1.052	0.541
161	Infatuationvoiceclap_attribute:Infatuation	0.386	-0.67	0.610	+0.01	0.608	0.332
162	Interestvoiceclap_attribute:Interest	2.148	+1.25	2.120	+1.19	1.598	0.440
163	Intoxication Altered States of Consciousnessvoiceclap_attribute:Intoxication_Altered_States_of_Consciousness	0.156	-0.75	0.281	-0.48	0.502	0.463
164	Jealousy & Envyvoiceclap_attribute:Jealousy_&_Envy	0.783	+1.06	0.873	+1.43	0.523	0.245
165	Longingvoiceclap_attribute:Longing	0.609	+0.32	0.659	+0.55	0.538	0.220
166	Malevolence Malicevoiceclap_attribute:Malevolence_Malice	0.411	-1.22	0.492	-0.99	0.833	0.346
167	Monotone vs. Expressivevoiceclap_attribute:Monotone_vs._Expressive	2.716	+1.58	2.809	+1.74	1.775	0.594
168	Painvoiceclap_attribute:Pain	0.054	-1.50	0.111	-1.24	0.381	0.218
169	Pleasure Ecstasyvoiceclap_attribute:Pleasure_Ecstasy	0.846	+1.14	0.637	+0.45	0.503	0.301
170	Pridevoiceclap_attribute:Pride	1.213	+1.24	0.913	+0.38	0.780	0.349
171	Recording Qualityvoiceclap_attribute:Recording_Quality	2.459	+0.44	2.462	+0.45	2.313	0.328
172	Reliefvoiceclap_attribute:Relief	1.476	+1.09	1.224	+0.48	1.025	0.415
173	Sadnessvoiceclap_attribute:Sadness	0.660	-0.29	0.621	-0.42	0.752	0.313
174	Serious vs. Humorousvoiceclap_attribute:Serious_vs._Humorous	1.271	+0.82	1.372	+1.00	0.803	0.568
175	Sexual Lustvoiceclap_attribute:Sexual_Lust	0.297	-0.81	0.346	-0.69	0.635	0.419
176	Shamevoiceclap_attribute:Shame	0.484	-0.15	0.674	+0.52	0.526	0.283
177	Soft vs. Harshvoiceclap_attribute:Soft_vs._Harsh	0.560	+1.11	0.540	+1.06	0.160	0.360
178	Sournessvoiceclap_attribute:Sourness	0.742	+0.12	0.712	+0.02	0.706	0.291
179	Submissive vs. Dominantvoiceclap_attribute:Submissive_vs._Dominant	0.584	-0.11	0.481	-0.40	0.623	0.359
180	Teasingvoiceclap_attribute:Teasing	0.893	+0.93	0.752	+0.56	0.540	0.379
181	Thankfulness Gratitudevoiceclap_attribute:Thankfulness_Gratitude	1.517	+0.25	1.598	+0.41	1.384	0.529
182	Triumphvoiceclap_attribute:Triumph	0.883	+0.46	0.704	-0.03	0.716	0.359
183	Valencevoiceclap_attribute:Valence	0.598	+0.95	0.139	+0.23	-0.007	0.635
184	Vulnerable vs. Emotionally Detachedvoiceclap_attribute:Vulnerable_vs._Emotionally_Detached	1.105	-0.96	1.053	-1.05	1.638	0.556
185	Warm vs. Coldvoiceclap_attribute:Warm_vs._Cold	0.230	+0.74	0.094	+0.40	-0.066	0.400
186	durationvoiceclap_attribute:duration	14.171	+0.51	13.429	+0.40	10.914	6.354
187	score background qualityvoiceclap_attribute:score_background_quality	3.347	+0.20	3.378	+0.27	3.245	0.498
188	score content enjoymentvoiceclap_attribute:score_content_enjoyment	4.827	+1.17	4.802	+0.99	4.656	0.147
189	score overall qualityvoiceclap_attribute:score_overall_quality	2.772	+0.33	2.746	+0.27	2.635	0.412
190	score speech qualityvoiceclap_attribute:score_speech_quality	1.853	-0.54	1.889	-0.02	1.891	0.069
191	talking speedvoiceclap_attribute:talking_speed	3.941	-1.35	9.418	+0.10	9.028	3.756

All Orange embedding components

The cosine above is the meaningful vector-level comparison; component values have no standalone semantic label.

Timbre — all 128 vector components

Dimension	Tiny	Base	Orange teacher
0	-0.0955	-0.0788	-0.0802
1	0.1464	0.1388	0.0945
2	0.1230	0.0901	0.1439
3	-0.0806	-0.0965	-0.0817
4	-0.0919	-0.0577	-0.0757
5	-0.0336	-0.0139	-0.1020
6	0.0633	0.0641	0.1082
7	0.1181	0.0747	0.0903
8	0.0442	0.0383	0.0124
9	-0.1082	-0.0637	-0.0693
10	-0.0997	-0.1041	-0.0749
11	-0.0905	-0.1199	-0.0942
12	-0.0753	-0.0486	-0.0811
13	-0.0675	-0.0509	0.0071
14	0.0431	0.0554	0.0230
15	0.0208	0.0292	-0.0166
16	-0.1068	-0.1003	-0.0975
17	-0.0905	-0.0543	-0.0539
18	-0.0887	-0.1154	-0.0743
19	-0.0474	-0.0428	-0.0757
20	0.1414	0.0633	0.1367
21	0.0415	0.0163	-0.0741
22	0.0460	0.0027	-0.0744
23	0.0082	-0.0238	-0.0562
24	0.1895	0.1229	0.1677
25	0.0232	0.0762	0.1375
26	-0.0926	-0.0875	-0.0756
27	0.0544	0.0652	0.0030
28	-0.0976	-0.0622	-0.0829
29	0.1740	0.1689	0.1281
30	0.0530	0.0633	0.0587
31	-0.0962	-0.0788	-0.0744
32	0.1018	0.1523	0.0862
33	-0.0757	-0.1086	-0.0888
34	-0.0781	-0.0690	-0.0723
35	0.0969	0.1312	0.1117
36	-0.0718	-0.0383	-0.0574
37	0.0048	-0.0600	0.0090
38	-0.0163	-0.0292	-0.0271
39	-0.0100	-0.0159	-0.0388
40	-0.0884	-0.1161	-0.0777
41	-0.0605	-0.0965	-0.1011
42	-0.1245	-0.1063	-0.0322
43	0.0559	0.0394	-0.0017
44	-0.1004	-0.0890	-0.0774
45	-0.0292	-0.0097	-0.0659
46	0.0933	0.1591	0.1283
47	0.0018	0.0143	-0.0392
48	-0.1160	-0.1071	-0.0787
49	-0.0806	-0.0479	-0.0814
50	-0.0764	-0.0897	-0.0824
51	0.1138	0.0747	0.0416
52	0.0155	-0.0375	-0.0897
53	0.0509	0.0224	0.1393
54	-0.0301	-0.0194	-0.0346
55	0.0133	-0.0236	-0.0350
56	-0.0997	-0.1033	-0.0764
57	0.0348	-0.0126	-0.0514
58	-0.0366	0.0161	0.0119
59	0.0757	0.1350	0.0615
60	-0.0084	-0.1003	-0.0777
61	0.2588	0.2805	0.2373
62	0.0027	0.0087	-0.0555
63	-0.0849	-0.1139	-0.0765
64	0.0375	0.0349	-0.0717
65	0.0112	0.0403	0.1062
66	0.0852	0.1365	0.1858
67	-0.0817	-0.0600	-0.0777
68	0.1641	0.1335	0.1449
69	0.1612	0.1742	0.2391
70	0.0276	-0.0202	-0.0358
71	0.0316	-0.0464	-0.0557
72	0.0919	0.1410	0.0941
73	0.0407	0.0358	0.0295
74	-0.1450	-0.1124	-0.0880
75	0.1011	0.0950	0.1926
76	0.1895	0.2112	0.1498
77	-0.0919	-0.0852	-0.0736
78	-0.1047	-0.0988	-0.0717
79	0.1280	0.0584	0.1215
80	-0.0799	-0.0833	-0.0729
81	0.0527	-0.0000	0.0427
82	-0.0697	-0.0660	-0.0771
83	-0.0548	-0.0788	-0.0374
84	-0.0050	-0.0358	-0.0321
85	-0.0887	-0.0762	-0.0856
86	0.1018	0.0615	0.0402
87	-0.0247	-0.0558	-0.0575
88	-0.0948	-0.0879	-0.0748
89	-0.0615	-0.0114	0.0029
90	0.0499	0.0226	-0.0220
91	-0.0142	-0.0091	0.1083
92	-0.0598	0.0287	0.0290
93	-0.0249	-0.0479	-0.0655
94	0.0484	-0.0201	-0.0043
95	-0.0053	0.0458	-0.0644
96	0.0269	-0.0056	0.0652
97	0.0274	0.0191	0.1445
98	-0.0327	-0.0102	-0.0078
99	0.0530	0.0958	0.0371
100	0.1909	0.2036	0.1652
101	-0.0725	-0.0253	-0.0779
102	-0.0771	-0.0894	-0.0862
103	-0.1025	-0.0867	-0.0851
104	-0.0170	-0.0095	0.0208
105	0.0182	0.0694	0.1146
106	0.0079	-0.0462	-0.0077
107	-0.0891	-0.0769	-0.0751
108	-0.0940	-0.0807	-0.0425
109	0.0414	0.0452	0.1183
110	-0.0912	-0.0867	-0.0620
111	0.0990	0.0140	0.1344
112	-0.0725	-0.0818	-0.0207
113	-0.1131	-0.0618	-0.1134
114	0.0463	0.0633	0.0867
115	0.0076	-0.0206	-0.0195
116	0.2051	0.2760	0.1967
117	-0.1011	-0.1033	-0.0938
118	-0.0983	-0.0826	-0.0784
119	0.0884	0.0603	-0.0025
120	0.0456	0.1274	0.0572
121	-0.0679	-0.0554	-0.0042
122	-0.1329	-0.1274	-0.0828
123	0.0410	0.0447	-0.0701
124	-0.0672	-0.0724	-0.0052
125	-0.0721	-0.0995	-0.0803
126	-0.0460	-0.0588	-0.0695
127	0.1754	0.0894	0.0649

Identity — all 250 vector components

Dimension	Tiny	Base	Orange teacher
0	-0.0654	-0.0413	-0.0122
1	0.0125	0.0236	-0.0368
2	-0.1320	-0.0896	-0.0625
3	0.0491	-0.0048	0.0326
4	-0.0103	-0.0362	-0.0462
5	-0.0098	-0.0538	-0.0531
6	-0.0324	-0.0431	-0.0745
7	-0.1215	-0.0605	-0.0515
8	0.1192	0.1112	0.0987
9	0.0142	0.0623	0.0000
10	-0.0372	-0.0527	-0.0533
11	-0.0257	-0.0666	-0.0019
12	0.1381	0.0355	0.0812
13	-0.0788	-0.0704	-0.0448
14	-0.0189	-0.0079	0.0279
15	0.1464	0.1286	0.0799
16	-0.0269	-0.0425	0.0611
17	0.0904	0.0291	0.0677
18	0.0871	0.1583	0.0207
19	-0.0399	-0.0156	-0.0132
20	-0.0555	-0.1053	-0.0508
21	0.0691	0.0346	0.2435
22	0.0826	0.0605	0.0149
23	-0.0577	-0.0457	-0.0491
24	0.0838	0.0160	-0.0434
25	-0.0283	0.0292	-0.0010
26	-0.0743	-0.0191	-0.0560
27	-0.0638	-0.0599	-0.0413
28	0.0793	0.0495	-0.0132
29	-0.0144	0.0365	-0.0086
30	0.1032	0.0559	0.1396
31	0.0679	0.0124	0.0327
32	0.0257	-0.0319	-0.0522
33	-0.0033	0.0047	-0.0106
34	0.0721	0.0016	-0.0607
35	-0.0243	-0.0013	-0.0199
36	0.0932	-0.0050	-0.0287
37	-0.0290	-0.0108	-0.0351
38	-0.0605	-0.0681	-0.0704
39	0.0926	0.0457	0.1366
40	0.0030	-0.0237	0.0435
41	-0.0342	-0.0442	-0.0465
42	0.0782	0.0071	0.0379
43	0.1608	0.1467	0.1741
44	0.0057	-0.0402	-0.0609
45	0.0760	0.0844	0.1195
46	-0.0323	0.0056	-0.0746
47	0.0507	-0.0480	0.0334
48	0.0118	-0.0045	0.0022
49	-0.0649	-0.1088	-0.0540
50	-0.0693	-0.0422	-0.0226
51	-0.0663	-0.1502	-0.0515
52	0.0284	-0.0202	-0.0501
53	0.0156	-0.0626	-0.0491
54	0.0682	0.1839	0.0586
55	0.0943	0.0733	0.0455
56	0.0383	0.0378	-0.0477
57	-0.0148	0.0469	0.0081
58	-0.0304	0.0075	0.0569
59	0.0270	0.0515	-0.0143
60	-0.0288	0.0345	-0.0532
61	-0.0079	0.0149	-0.0017
62	-0.0145	-0.0074	-0.0068
63	-0.0538	-0.0489	-0.0552
64	0.0943	0.0439	0.0054
65	-0.0291	-0.0175	0.0019
66	0.0354	-0.0550	0.0765
67	0.1963	0.1019	0.1194
68	0.0416	-0.0221	0.0048
69	-0.0577	-0.0477	-0.0651
70	-0.0527	-0.0684	-0.0736
71	-0.0530	-0.0567	-0.0532
72	0.0435	0.0167	0.0097
73	-0.0173	0.0201	0.0233
74	-0.0854	-0.0937	-0.0548
75	0.0641	0.0370	-0.0620
76	0.0022	0.0186	0.0400
77	0.0000	0.0489	-0.0046
78	0.0229	0.0515	0.0482
79	-0.0013	-0.0004	-0.0543
80	-0.0295	-0.0908	-0.0009
81	0.0519	0.0410	0.0356
82	0.0298	-0.0710	-0.0104
83	-0.0449	-0.1030	-0.0451
84	0.1120	0.0407	0.0276
85	0.0281	0.0501	0.0342
86	-0.0257	-0.0223	-0.0484
87	-0.0183	-0.0774	-0.0433
88	-0.0316	0.0164	0.0317
89	-0.0059	0.0803	-0.0490
90	-0.0191	0.0005	-0.0169
91	-0.0006	0.0890	0.0191
92	-0.0394	-0.0375	0.0303
93	0.0494	0.0489	-0.0391
94	-0.0679	-0.0439	-0.0878
95	0.0037	-0.0565	-0.0263
96	-0.0218	-0.0579	-0.0485
97	0.0363	0.0208	-0.0530
98	-0.0107	0.0495	-0.0304
99	-0.0876	-0.0861	-0.0679
100	0.1453	0.1438	0.1656
101	-0.0171	-0.0949	-0.0512
102	0.0474	0.0109	0.0474
103	0.1631	0.1117	0.1355
104	-0.0679	-0.0707	-0.0275
105	-0.0441	-0.0681	0.0430
106	-0.1159	-0.0995	-0.0418
107	-0.0544	-0.1019	-0.0486
108	0.0276	0.0365	-0.0403
109	-0.0538	0.0287	-0.0521
110	0.0059	0.0236	0.0789
111	0.0198	0.0165	-0.0447
112	0.0422	0.0492	0.0635
113	0.0165	-0.0276	0.0205
114	0.0854	0.0797	0.0294
115	0.0329	0.1298	0.2183
116	-0.0058	0.0124	0.0558
117	0.1009	0.0291	0.1075
118	-0.0632	-0.0713	-0.0707
119	0.0372	0.0356	0.0068
120	-0.0860	-0.0178	-0.0392
121	0.1664	0.0803	0.1718
122	-0.0599	-0.0425	-0.0512
123	-0.0580	-0.0614	-0.0560
124	-0.0052	-0.0614	0.1215
125	-0.0272	-0.0434	-0.0527
126	0.0480	0.0004	-0.0057
127	-0.0191	-0.0908	-0.0558
128	-0.0202	-0.0064	0.0364
129	0.0060	-0.0362	0.0565
130	-0.0298	-0.0454	-0.0545
131	-0.0474	-0.0176	-0.0475
132	0.0865	0.0035	0.0217
133	-0.0030	-0.0077	-0.0536
134	-0.0458	-0.0704	-0.0754
135	0.1043	0.0174	-0.0329
136	-0.0092	-0.0815	-0.0581
137	-0.0788	-0.0815	-0.0504
138	-0.0438	-0.0304	-0.0478
139	0.0037	0.1275	0.0539
140	-0.0079	-0.0215	-0.0639
141	-0.0009	0.0492	-0.0536
142	-0.0532	-0.0591	-0.0468
143	-0.0452	-0.0643	0.0406
144	-0.0588	-0.0119	0.0887
145	0.0463	0.0066	0.0010
146	0.1115	0.0053	0.0717
147	-0.0721	-0.0931	-0.0482
148	-0.0117	-0.0051	-0.0598
149	-0.0394	0.0002	-0.0698
150	-0.0849	-0.0599	-0.0534
151	0.0165	0.0541	0.0942
152	-0.0030	-0.0259	-0.0345
153	0.0233	0.0387	-0.0692
154	-0.0156	-0.0573	-0.0529
155	0.0033	0.0062	0.0388
156	-0.0483	-0.0559	-0.0543
157	0.1082	0.0949	0.0460
158	0.0904	0.0655	0.0622
159	-0.0257	-0.0503	0.0523
160	0.0258	-0.0608	-0.0515
161	0.0607	0.1024	0.1003
162	-0.0177	-0.0978	-0.0629
163	-0.0385	-0.0303	-0.0281
164	-0.0288	-0.0608	-0.0476
165	0.0799	0.1699	0.0855
166	-0.0455	-0.0856	-0.0630
167	-0.0507	-0.0483	-0.0687
168	0.0177	0.0266	0.0332
169	-0.0616	-0.0762	-0.0619
170	0.0455	0.0133	0.0614
171	0.0510	0.0048	0.0602
172	-0.0915	-0.1455	-0.0628
173	-0.0164	-0.0365	-0.0635
174	0.0505	-0.0086	0.0070
175	-0.1137	-0.0937	-0.0660
176	-0.0505	-0.0535	-0.0461
177	0.0252	0.0210	0.1116
178	0.0329	0.0068	-0.0055
179	0.0281	0.0266	-0.0256
180	0.0546	-0.0011	0.0445
181	-0.0349	-0.0345	-0.0773
182	-0.0326	-0.0052	-0.0285
183	-0.0079	-0.0390	0.0270
184	0.1021	0.0133	-0.0551
185	0.0782	0.0550	0.0044
186	0.0366	0.0463	0.0562
187	-0.0483	0.0378	-0.0313
188	0.0460	0.0174	0.0188
189	0.0971	0.0713	0.1033
190	0.0474	-0.0112	-0.0654
191	0.0496	0.0471	0.0227
192	-0.0316	-0.1013	-0.0656
193	-0.1270	-0.0925	-0.0571
194	0.0351	0.0227	-0.0703
195	-0.0715	-0.0214	-0.0515
196	-0.0252	0.0064	-0.0526
197	-0.0657	-0.0821	-0.0758
198	-0.0638	-0.0687	-0.0524
199	0.0358	-0.0559	0.0242
200	0.0123	-0.0256	0.0448
201	0.0186	0.0428	-0.0474
202	-0.1093	-0.0585	-0.0685
203	-0.0483	-0.0180	0.0116
204	-0.0402	0.0375	-0.0381
205	0.0063	-0.0483	-0.0472
206	0.1819	0.0757	0.0410
207	-0.0117	-0.0195	-0.0446
208	-0.0749	-0.0498	-0.0562
209	0.0308	0.0230	-0.0873
210	-0.0113	-0.0275	0.0194
211	-0.0771	-0.0856	-0.0417
212	0.0164	-0.0457	-0.0509
213	-0.0008	-0.0185	0.0301
214	0.0326	0.1065	-0.0432
215	-0.0139	-0.0160	-0.0456
216	-0.0127	0.0151	0.0113
217	0.0287	0.0244	0.1086
218	0.0298	0.0165	-0.0629
219	0.0388	-0.0175	0.0323
220	-0.0860	-0.1234	-0.0598
221	-0.0943	-0.0075	-0.0470
222	-0.0363	-0.0212	0.0004
223	-0.0202	-0.0579	-0.0435
224	0.0541	0.0368	-0.0009
225	-0.0632	-0.0180	-0.0451
226	0.0092	0.0448	-0.0403
227	0.0826	0.1053	0.2041
228	-0.0262	-0.0704	-0.0877
229	-0.0776	-0.0873	-0.0594
230	-0.0496	-0.0661	-0.0552
231	0.1176	0.0605	0.0351
232	0.0560	0.0562	0.0312
233	-0.0596	-0.0803	-0.0067
234	0.1143	0.0115	0.0224
235	0.0602	0.1176	-0.0445
236	-0.0460	-0.0451	-0.0197
237	-0.0120	0.0463	0.0793
238	-0.0904	-0.0434	-0.0594
239	0.0079	-0.0434	-0.0247
240	-0.0921	-0.1158	-0.0553
241	0.0849	-0.0071	-0.0322
242	-0.0361	-0.0098	-0.0723
243	-0.0113	-0.0704	-0.0696
244	0.0068	-0.0165	0.0372
245	0.1919	0.2829	0.1749
246	-0.0574	-0.0960	-0.0439
247	0.0244	0.0179	0.0804
248	-0.0444	-0.0570	-0.0620
249	0.1032	0.0260	0.1345

Source: Emolia / Emilia source archive · SHA-256 028dbeae0f1af297…

e08JapaneseEmolia / Emilia

Emolia JA · JA_B00000_S00080_W000086

Natural speech · Original speech · 3.2 s

午後になったらうなぎを取りに行ってぇ。

Tiny Base · values are model estimates, not ground truth

Strongest emotions relative to training

Impatience and Irritability

z +1.59 / +0.67raw 1.27 / 0.62

Confusion

z +1.15 / +0.79raw 0.62 / 0.43

Doubt

z +0.86 / +0.51raw 0.41 / 0.24

Anger

z +0.79 / +0.29raw 0.49 / 0.18

Longing

z +0.73 / +0.57raw 0.55 / 0.45

Disappointment

z +0.27 / +0.48raw 0.19 / 0.33

Teasing

z +0.45 / +0.03raw 0.25 / 0.02

The center of each bar is the S9 teacher median. Positive z is to the right; negative z is to the left. Ranking uses z, not raw teacher units.

Strongest VoiceNet dimensions relative to training

Vocal register (REGS)

z +2.33 / +2.42raw 4.15 / 4.27

Pitch range (RANG)

z +1.57 / +1.68raw 4.33 / 4.42

Brightness (BRGT)

z +1.63 / +1.42raw 3.32 / 3.15

Storytelling style (S_STRY)

z +1.57 / +1.32raw 4.63 / 4.29

Conversational style (S_CONV)

z +1.52 / +1.37raw 4.60 / 4.40

Nasal resonance (R_NASL)

z +1.51 / +1.33raw 4.37 / 4.19

Head resonance (R_HEAD)

z +1.32 / +1.39raw 3.24 / 3.29

All 57 VoiceNet predictions, including raw units, are in the full table below. These seven are ranked by z; the top values may differ from the strongest raw dimensions.

Voice, speed and quality scores in context

Genuineness (0–6)z +1.16 / +1.21raw 4.21 / 4.29

Vocal-burst blend (0–10)z -0.70 / -0.48raw 4.76 / 5.36

Content enjoyment (CE)z -0.04 / +0.04raw 4.76 / 4.84

Production quality (PQ)z -0.43 / -0.30raw 6.67 / 6.78

Speech signal quality, calibratedz -0.51 / -0.32raw 3.24 / 3.33

Background quality, calibratedz +0.28 / +0.26raw 3.65 / 3.63

Overall quality, calibratedz -0.02 / -0.05raw 2.83 / 2.81

P.808 MOS estimatez -0.26 / -0.44raw 3.29 / 3.20

score content enjoymentz -0.98 / -1.09raw 4.21 / 4.18

score overall qualityz -0.17 / -0.29raw 2.56 / 2.50

Background Noisez +0.12 / +0.04raw 0.84 / 0.82

Tempo (TEMP)z +0.11 / +0.09raw 2.24 / 2.23

Arousal (AROU)z -0.05 / -0.07raw 2.31 / 2.28

Valence (VALN)z +0.51 / +0.31raw 2.90 / 2.67

Recording quality (RCQL)z -0.46 / -0.83raw 2.35 / 2.01

Background noise (BKGN)z -0.32 / -0.41raw 2.46 / 2.39

talking speedz +0.40 / +0.64raw 10.51 / 11.45

Characters per second (CPS): 5.86 raw · z -0.84

Orange speaker embedding reconstruction

Cosine against Orange on this same clip (higher means closer to that teacher vector):

Embedding	Tiny	Base
Timbre · 128D	0.731	0.754
Identity · 250D	0.717	0.757

Vocal-burst regions

Tiny

Base

0 s3.2 s

Verified burst intervals are unavailable for this clip.

Tiny: 0 regions, count-head estimate 0.06; Base: 0 regions, count-head estimate 0.00.

Exact predicted start and end times

Model	Region	Start (s)	End (s)	Duration (s)

All 192 score slots · raw and z values

#	Target	Tiny raw	Tiny z	Base raw	Base z	Train median	Train SD
Emotion scores Forty clip-level Empathic Insight emotion teacher outputs. Each row evaluates one named emotion score.
0	Affectionemo_Affection	0.131	+0.22	0.122	+0.20	0.007	0.570
1	Amusementemo_Amusement	0.244	+0.28	0.312	+0.35	-0.001	0.885
2	Angeremo_Anger	0.487	+0.79	0.182	+0.29	0.004	0.613
3	Astonishment Surpriseemo_Astonishment_Surprise	0.066	+0.11	0.043	+0.07	0.005	0.572
4	Aweemo_Awe	0.007	+0.02	-0.011	-0.02	0.000	0.427
5	Bitternessemo_Bitterness	0.025	+0.03	0.037	+0.06	0.013	0.415
6	Concentrationemo_Concentration	0.664	+0.04	0.766	+0.18	0.634	0.741
7	Confusionemo_Confusion	0.622	+1.15	0.426	+0.79	0.001	0.540
8	Contemplationemo_Contemplation	0.064	-0.03	0.103	+0.03	0.082	0.598
9	Contemptemo_Contempt	0.111	+0.24	0.018	+0.04	-0.000	0.464
10	Contentmentemo_Contentment	0.012	+0.02	0.085	+0.16	0.000	0.514
11	Disappointmentemo_Disappointment	0.191	+0.27	0.333	+0.48	0.000	0.700
12	Disgustemo_Disgust	-0.016	-0.05	-0.005	-0.03	0.007	0.489
13	Distressemo_Distress	0.168	+0.20	0.219	+0.27	0.000	0.821
14	Doubtemo_Doubt	0.409	+0.86	0.242	+0.51	0.006	0.466
15	Elationemo_Elation	0.031	+0.03	0.073	+0.08	0.012	0.728
16	Embarrassmentemo_Embarrassment	0.062	+0.04	0.060	+0.04	0.043	0.430
17	Emotional Numbnessemo_Emotional_Numbness	0.054	+0.05	0.182	+0.19	0.004	0.917
18	Fatigue Exhaustionemo_Fatigue_Exhaustion	0.069	+0.08	0.051	+0.04	0.028	0.539
19	Fearemo_Fear	0.066	+0.08	0.029	+0.02	0.015	0.610
20	Helplessnessemo_Helplessness	0.224	+0.33	0.265	+0.39	-0.004	0.696
21	Hope Enthusiasm Optimismemo_Hope_Enthusiasm_Optimism	0.095	-0.03	0.077	-0.05	0.117	0.760
22	Impatience and Irritabilityemo_Impatience_and_Irritability	1.273	+1.59	0.624	+0.67	0.149	0.705
23	Infatuationemo_Infatuation	-0.032	-0.03	-0.047	-0.06	-0.015	0.533
24	Interestemo_Interest	1.028	-0.62	0.985	-0.67	1.589	0.907
25	Intoxication Altered States of Consciousnessemo_Intoxication_Altered_States_of_Consciousness	0.049	+0.13	-0.009	+0.03	-0.025	0.559
26	Jealousy and Envyemo_Jealousy_and_Envy	0.027	-0.07	0.019	-0.09	0.059	0.442
27	Longingemo_Longing	0.546	+0.73	0.445	+0.57	0.087	0.632
28	Malevolence Maliceemo_Malevolence_Malice	0.054	-0.00	0.050	-0.01	0.055	0.534
29	Painemo_Pain	-0.021	-0.03	0.031	+0.06	-0.002	0.579
30	Pleasure Ecstasyemo_Pleasure_Ecstasy	0.032	+0.02	0.073	+0.09	0.017	0.614
31	Prideemo_Pride	-0.011	-0.03	0.053	+0.10	0.002	0.509
32	Reliefemo_Relief	0.051	+0.03	0.062	+0.04	0.033	0.681
33	Sadnessemo_Sadness	0.204	+0.27	0.317	+0.42	0.000	0.759
34	Sexual Lustemo_Sexual_Lust	0.018	-0.02	-0.006	-0.07	0.030	0.494
35	Shameemo_Shame	-0.042	-0.11	-0.007	-0.04	0.013	0.510
36	Sournessemo_Sourness	0.007	+0.03	-0.016	-0.02	-0.005	0.439
37	Teasingemo_Teasing	0.248	+0.45	0.018	+0.03	0.000	0.545
38	Thankfulness Gratitudeemo_Thankfulness_Gratitude	-0.013	-0.08	0.008	-0.05	0.041	0.697
39	Triumphemo_Triumph	-0.016	-0.02	0.024	+0.06	-0.007	0.521
VoiceNet dimensions Fifty-seven VoiceNet voice, delivery, style, and recording dimensions. Codes are expanded in the target column.
40	Perceived voice age (AGEV)vn_AGEV_reg	0.358	-2.12	0.191	-2.26	2.984	1.238
41	Arousal (AROU)vn_AROU_reg	2.306	-0.05	2.279	-0.07	2.359	1.147
42	Arousal shift (ARSH)vn_ARSH_reg	3.300	+0.83	3.187	+0.70	2.580	0.867
43	Vocal attack (ATCK)vn_ATCK_reg	2.337	+0.14	2.093	-0.05	2.162	1.295
44	Background noise (BKGN)vn_BKGN_reg	2.460	-0.32	2.392	-0.41	2.703	0.761
45	Brightness (BRGT)vn_BRGT_reg	3.319	+1.63	3.148	+1.42	1.991	0.813
46	Speech chunking (CHNK)vn_CHNK_reg	1.432	-0.34	1.505	-0.28	1.847	1.239
47	Articulation clarity (CLRT)vn_CLRT_reg	1.170	-0.90	1.050	-1.02	2.018	0.945
48	Cognitive load (COGL)vn_COGL_reg	1.965	-0.12	1.694	-0.38	2.094	1.061
49	Dynamic arc (DARC)vn_DARC_reg	2.592	+0.71	2.339	+0.52	1.615	1.380
50	Disfluency (DFLU)vn_DFLU_reg	2.917	+0.36	3.184	+0.59	2.488	1.184
51	Emphasis (EMPH)vn_EMPH_reg	2.356	-0.16	1.938	-0.44	2.607	1.524
52	Esthetics (ESTH)vn_ESTH_reg	2.915	+0.66	2.885	+0.62	2.402	0.782
53	Content appropriateness (EXPL)vn_EXPL_reg	0.024	-0.19	0.009	-0.24	0.086	0.322
54	Focus (FOCS)vn_FOCS_reg	1.923	-0.38	1.970	-0.34	2.344	1.102
55	Fullness (FULL)vn_FULL_reg	0.757	-1.15	0.826	-1.07	1.778	0.889
56	Perceived gender (GEND)vn_GEND_reg	-0.100	-2.62	-0.199	-2.68	4.055	1.588
57	Harmonicity (HARM)vn_HARM_reg	2.973	+0.59	3.041	+0.67	2.480	0.836
58	Metallic character (METL)vn_METL_reg	2.122	+0.52	1.996	+0.39	1.621	0.958
59	Pitch range (RANG)vn_RANG_reg	4.326	+1.57	4.424	+1.68	2.914	0.897
60	Recording quality (RCQL)vn_RCQL_reg	2.345	-0.46	2.013	-0.83	2.754	0.888
61	Vocal register (REGS)vn_REGS_reg	4.151	+2.33	4.269	+2.42	1.198	1.268
62	Respiration (RESP)vn_RESP_reg	2.925	+0.23	3.285	+0.57	2.680	1.056
63	Roughness (ROUG)vn_ROUG_reg	1.773	-0.29	1.873	-0.18	2.033	0.887
64	Chest resonance (R_CHST)vn_R_CHST_reg	1.341	-0.94	1.172	-1.14	2.135	0.844
65	Head resonance (R_HEAD)vn_R_HEAD_reg	3.237	+1.32	3.289	+1.39	2.148	0.822
66	Mask resonance (R_MASK)vn_R_MASK_reg	3.218	+1.30	3.026	+1.11	1.908	1.005
67	Mixed resonance (R_MIXD)vn_R_MIXD_reg	0.657	-0.93	0.696	-0.88	1.436	0.841
68	Nasal resonance (R_NASL)vn_R_NASL_reg	4.368	+1.51	4.186	+1.33	2.791	1.047
69	Oral resonance (R_ORAL)vn_R_ORAL_reg	3.172	+1.34	2.905	+0.97	2.184	0.741
70	Throat resonance (R_THRT)vn_R_THRT_reg	2.556	+0.60	2.427	+0.44	2.070	0.803
71	Smoothness (SMTH)vn_SMTH_reg	1.810	-0.30	1.707	-0.40	2.143	1.093
72	Stance (STNC)vn_STNC_reg	2.382	-0.22	2.254	-0.33	2.633	1.137
73	Speech structure (STRU)vn_STRU_reg	1.676	-0.48	1.536	-0.63	2.137	0.958
74	ASMR style (S_ASMR)vn_S_ASMR_reg	0.305	-0.75	0.057	-0.93	1.370	1.411
75	Authoritative style (S_AUTH)vn_S_AUTH_reg	0.684	-0.39	0.473	-0.59	1.088	1.043
76	Cartoonish style (S_CART)vn_S_CART_reg	3.209	+1.18	3.134	+1.12	1.560	1.401
77	Casual style (S_CASU)vn_S_CASU_reg	5.206	+1.11	5.325	+1.20	3.793	1.278
78	Conversational style (S_CONV)vn_S_CONV_reg	4.604	+1.52	4.400	+1.37	2.594	1.318
79	Dramatic style (S_DRAM)vn_S_DRAM_reg	2.912	+0.17	2.825	+0.09	2.721	1.148
80	Formal style (S_FORM)vn_S_FORM_reg	0.623	-0.56	0.466	-0.71	1.195	1.021
81	Monologue style (S_MONO)vn_S_MONO_reg	1.284	-1.20	1.294	-1.19	2.824	1.284
82	Narrator style (S_NARR)vn_S_NARR_reg	0.769	-0.37	0.968	-0.23	1.307	1.446
83	Newsreader style (S_NEWS)vn_S_NEWS_reg	0.411	+0.01	0.270	-0.24	0.408	0.568
84	Playful style (S_PLAY)vn_S_PLAY_reg	3.751	+1.06	3.721	+1.04	2.352	1.315
85	Ranting or angry style (S_RANT)vn_S_RANT_reg	-0.171	-1.07	-0.041	-0.97	1.213	1.289
86	Storytelling style (S_STRY)vn_S_STRY_reg	4.628	+1.57	4.291	+1.32	2.480	1.366
87	Teacher or didactic style (S_TECH)vn_S_TECH_reg	0.375	-0.22	0.112	-0.44	0.646	1.227
88	Whispered talking style (S_WHIS)vn_S_WHIS_reg	1.645	+0.03	1.705	+0.07	1.597	1.618
89	Tempo (TEMP)vn_TEMP_reg	2.242	+0.11	2.229	+0.09	2.117	1.190
90	Tension (TENS)vn_TENS_reg	1.531	-0.03	1.470	-0.10	1.559	0.852
91	Valence (VALN)vn_VALN_reg	2.897	+0.51	2.674	+0.31	2.328	1.118
92	Valence shift (VALS)vn_VALS_reg	3.043	+0.49	2.569	+0.05	2.518	1.079
93	Velocity flux (VFLX)vn_VFLX_reg	3.315	+0.88	3.098	+0.70	2.256	1.208
94	Volatility (VOLT)vn_VOLT_reg	3.166	+0.65	3.183	+0.67	2.586	0.886
95	Vulnerability (VULN)vn_VULN_reg	3.189	+0.55	3.363	+0.73	2.648	0.984
96	Warmth (WARM)vn_WARM_reg	1.665	-1.00	1.573	-1.11	2.578	0.909
Genuineness, blend, and legacy quality Genuineness and vocal-burst blend are predicted. R_quality has Ladder training labels but no valid P3 test labels.
97	Genuineness (0–6)genuineness_0_6	4.206	+1.16	4.294	+1.21	2.332	1.621
98	Vocal-burst blend (0–10)blend_0_10	4.765	-0.70	5.365	-0.48	6.676	2.738
99	Legacy R_quality (no P3 test labels)R_quality	1.185	+0.27	1.250	+0.46	1.095	0.338
Empathic Insight Plus extra scores Nineteen additional clip-level teacher scores, including background noise and content enjoyment.
100	Ageeiv_extra:Age	2.780	-1.60	1.614	-5.58	3.250	0.293
101	Arousaleiv_extra:Arousal	1.357	+0.16	1.238	-0.12	1.289	0.435
102	Authenticityeiv_extra:Authenticity	2.715	+0.31	2.759	+0.60	2.667	0.153
103	Background Noiseeiv_extra:Background_Noise	0.838	+0.12	0.818	+0.04	0.808	0.264
104	Confident vs. Hesitanteiv_extra:Confident_vs._Hesitant	1.886	+2.80	1.829	+2.61	1.040	0.303
105	Gendereiv_extra:Gender	0.811	+1.43	0.627	+1.25	-0.621	0.999
106	High-Pitched vs. Low-Pitchedeiv_extra:High-Pitched_vs._Low-Pitched	1.571	-1.02	1.520	-1.23	1.827	0.250
107	Monotone vs. Expressiveeiv_extra:Monotone_vs._Expressive	2.039	+0.38	1.939	+0.17	1.859	0.470
108	Recording Qualityeiv_extra:Recording_Quality	1.762	-1.15	1.720	-1.28	2.144	0.332
109	Serious vs. Humorouseiv_extra:Serious_vs._Humorous	1.053	+0.36	1.036	+0.31	0.929	0.340
110	Soft vs. Harsheiv_extra:Soft_vs._Harsh	0.730	+1.40	0.922	+2.01	0.281	0.320
111	Submissive vs. Dominanteiv_extra:Submissive_vs._Dominant	0.204	-0.53	0.005	-1.14	0.376	0.324
112	Valenceeiv_extra:Valence	0.020	+0.04	-0.050	-0.15	0.005	0.380
113	Vulnerable vs. Emotionally Detachedeiv_extra:Vulnerable_vs._Emotionally_Detached	1.248	-1.07	1.228	-1.11	1.715	0.437
114	Warm vs. Coldeiv_extra:Warm_vs._Cold	0.133	+0.27	0.145	+0.31	0.051	0.300
115	score background qualityeiv_extra:score_background_quality	3.319	+0.03	3.300	-0.00	3.301	0.693
116	score content enjoymenteiv_extra:score_content_enjoyment	4.209	-0.98	4.176	-1.09	4.507	0.303
117	score overall qualityeiv_extra:score_overall_quality	2.565	-0.17	2.504	-0.29	2.652	0.507
118	score speech qualityeiv_extra:score_speech_quality	1.909	+0.69	1.932	+0.86	1.808	0.146
Meta AudioBox Aesthetics Four AudioBox aesthetic teacher outputs. Expansions follow the official Meta model card.
119	Content enjoyment (CE)audiobox:CE	4.760	-0.04	4.841	+0.04	4.799	1.018
120	Content usefulness (CU)audiobox:CU	5.321	-0.33	5.525	-0.12	5.649	1.001
121	Production complexity (PC)audiobox:PC	1.820	-0.32	1.700	-0.39	2.331	1.617
122	Production quality (PQ)audiobox:PQ	6.665	-0.43	6.781	-0.30	7.044	0.879
Microsoft DNSMOS Seven DNSMOS teacher outputs: raw and calibrated SIG/BAK/OVRL estimates plus P.808 MOS.
123	Speech signal quality, rawdnsmos:SIG_raw	3.495	-0.61	3.615	-0.43	3.900	0.669
124	Background quality, rawdnsmos:BAK_raw	3.680	+0.42	3.599	+0.35	3.211	1.124
125	Overall quality, rawdnsmos:OVRL_raw	3.106	+0.03	3.050	-0.04	3.085	0.812
126	Speech signal quality, calibrateddnsmos:SIG	3.235	-0.51	3.327	-0.32	3.488	0.501
127	Background quality, calibrateddnsmos:BAK	3.647	+0.28	3.633	+0.26	3.389	0.928
128	Overall quality, calibrateddnsmos:OVRL	2.826	-0.02	2.809	-0.05	2.840	0.606
129	P.808 MOS estimatednsmos:P808_MOS	3.291	-0.26	3.204	-0.44	3.421	0.496
Vocal-burst count The regression target is log(1 + count). A separate table also reports count error after inverse transformation.
130	Vocal-burst count, log(1 + count)burst_count_log1p	0.056	+0.09	0.002	+0.00	0.000	0.647
VoiceCLAP attributes Sixty-one individual VoiceCLAP attribute teacher scores. The raw 768D VoiceCLAP embedding is stored in sidecars but is not a model output.
131	Affectionvoiceclap_attribute:Affection	1.270	+0.58	1.125	+0.32	0.947	0.554
132	Agevoiceclap_attribute:Age	1.331	-3.47	0.796	-4.45	3.229	0.547
133	Amusementvoiceclap_attribute:Amusement	0.946	+0.97	0.829	+0.76	0.392	0.572
134	Angervoiceclap_attribute:Anger	0.236	-1.49	0.518	-0.94	0.992	0.506
135	Arousalvoiceclap_attribute:Arousal	1.657	+0.38	1.732	+0.50	1.420	0.622
136	Astonishment Surprisevoiceclap_attribute:Astonishment_Surprise	1.100	+1.23	0.820	+0.65	0.509	0.479
137	Authenticityvoiceclap_attribute:Authenticity	2.946	+1.05	2.850	+0.48	2.770	0.167
138	Awevoiceclap_attribute:Awe	0.319	-0.85	0.335	-0.78	0.539	0.259
139	Background Noisevoiceclap_attribute:Background_Noise	0.533	-0.13	0.562	-0.02	0.567	0.264
140	Bitternessvoiceclap_attribute:Bitterness	0.212	-1.62	0.235	-1.52	0.592	0.236
141	Concentrationvoiceclap_attribute:Concentration	0.360	-1.61	0.448	-1.44	1.214	0.531
142	Confident vs. Hesitantvoiceclap_attribute:Confident_vs._Hesitant	1.760	+1.48	2.005	+2.00	1.069	0.468
143	Confusionvoiceclap_attribute:Confusion	0.827	+0.55	0.860	+0.65	0.643	0.334
144	Contemplationvoiceclap_attribute:Contemplation	0.028	-1.86	0.151	-1.55	0.780	0.406
145	Contemptvoiceclap_attribute:Contempt	0.584	-0.37	0.546	-0.48	0.709	0.339
146	Contentmentvoiceclap_attribute:Contentment	0.684	+0.31	0.561	-0.09	0.588	0.307
147	Disappointmentvoiceclap_attribute:Disappointment	0.320	-1.51	0.472	-0.99	0.760	0.291
148	Disgustvoiceclap_attribute:Disgust	0.386	-1.15	0.398	-1.09	0.625	0.207
149	Distressvoiceclap_attribute:Distress	0.445	-1.38	0.634	-0.84	0.927	0.350
150	Doubtvoiceclap_attribute:Doubt	0.570	+0.19	0.684	+0.80	0.535	0.188
151	Elationvoiceclap_attribute:Elation	0.751	+0.53	0.678	+0.35	0.539	0.397
152	Embarrassmentvoiceclap_attribute:Embarrassment	0.548	+0.77	0.385	+0.25	0.307	0.314
153	Emotional Numbnessvoiceclap_attribute:Emotional_Numbness	0.436	-0.86	0.519	-0.54	0.664	0.266
154	Fatigue Exhaustionvoiceclap_attribute:Fatigue_Exhaustion	0.361	-0.39	0.299	-0.62	0.462	0.261
155	Fearvoiceclap_attribute:Fear	0.421	-0.93	0.488	-0.61	0.618	0.212
156	Gendervoiceclap_attribute:Gender	0.850	+1.00	0.956	+1.10	-0.151	1.005
157	Helplessnessvoiceclap_attribute:Helplessness	0.560	-0.37	0.601	-0.21	0.658	0.268
158	High-Pitched vs. Low-Pitchedvoiceclap_attribute:High-Pitched_vs._Low-Pitched	1.434	-1.08	1.426	-1.11	1.840	0.375
159	Hope Enthusiasm Optimismvoiceclap_attribute:Hope_Enthusiasm_Optimism	1.004	+0.75	0.919	+0.54	0.705	0.396
160	Impatience and Irritabilityvoiceclap_attribute:Impatience_and_Irritability	0.870	-0.34	0.921	-0.24	1.052	0.541
161	Infatuationvoiceclap_attribute:Infatuation	0.756	+0.45	0.833	+0.68	0.608	0.332
162	Interestvoiceclap_attribute:Interest	1.346	-0.57	1.514	-0.19	1.598	0.440
163	Intoxication Altered States of Consciousnessvoiceclap_attribute:Intoxication_Altered_States_of_Consciousness	0.535	+0.07	0.414	-0.19	0.502	0.463
164	Jealousy & Envyvoiceclap_attribute:Jealousy_&_Envy	0.520	-0.01	0.689	+0.68	0.523	0.245
165	Longingvoiceclap_attribute:Longing	0.634	+0.43	0.753	+0.98	0.538	0.220
166	Malevolence Malicevoiceclap_attribute:Malevolence_Malice	0.408	-1.23	0.398	-1.26	0.833	0.346
167	Monotone vs. Expressivevoiceclap_attribute:Monotone_vs._Expressive	2.203	+0.72	2.313	+0.91	1.775	0.594
168	Painvoiceclap_attribute:Pain	0.128	-1.16	0.216	-0.76	0.381	0.218
169	Pleasure Ecstasyvoiceclap_attribute:Pleasure_Ecstasy	0.719	+0.72	0.666	+0.54	0.503	0.301
170	Pridevoiceclap_attribute:Pride	0.174	-1.74	0.152	-1.80	0.780	0.349
171	Recording Qualityvoiceclap_attribute:Recording_Quality	2.064	-0.76	1.895	-1.28	2.313	0.328
172	Reliefvoiceclap_attribute:Relief	0.805	-0.53	0.605	-1.01	1.025	0.415
173	Sadnessvoiceclap_attribute:Sadness	0.591	-0.51	0.802	+0.16	0.752	0.313
174	Serious vs. Humorousvoiceclap_attribute:Serious_vs._Humorous	1.646	+1.48	1.543	+1.30	0.803	0.568
175	Sexual Lustvoiceclap_attribute:Sexual_Lust	0.412	-0.53	0.433	-0.48	0.635	0.419
176	Shamevoiceclap_attribute:Shame	0.368	-0.56	0.294	-0.82	0.526	0.283
177	Soft vs. Harshvoiceclap_attribute:Soft_vs._Harsh	0.970	+2.25	0.925	+2.13	0.160	0.360
178	Sournessvoiceclap_attribute:Sourness	0.488	-0.75	0.537	-0.58	0.706	0.291
179	Submissive vs. Dominantvoiceclap_attribute:Submissive_vs._Dominant	0.222	-1.12	0.185	-1.22	0.623	0.359
180	Teasingvoiceclap_attribute:Teasing	0.928	+1.02	0.817	+0.73	0.540	0.379
181	Thankfulness Gratitudevoiceclap_attribute:Thankfulness_Gratitude	0.988	-0.75	0.560	-1.56	1.384	0.529
182	Triumphvoiceclap_attribute:Triumph	0.202	-1.43	0.117	-1.67	0.716	0.359
183	Valencevoiceclap_attribute:Valence	0.390	+0.62	0.395	+0.63	-0.007	0.635
184	Vulnerable vs. Emotionally Detachedvoiceclap_attribute:Vulnerable_vs._Emotionally_Detached	0.988	-1.17	1.036	-1.08	1.638	0.556
185	Warm vs. Coldvoiceclap_attribute:Warm_vs._Cold	0.773	+2.10	0.658	+1.81	-0.066	0.400
186	durationvoiceclap_attribute:duration	3.867	-1.11	3.322	-1.19	10.914	6.354
187	score background qualityvoiceclap_attribute:score_background_quality	3.288	+0.09	3.321	+0.15	3.245	0.498
188	score content enjoymentvoiceclap_attribute:score_content_enjoyment	4.550	-0.72	4.537	-0.80	4.656	0.147
189	score overall qualityvoiceclap_attribute:score_overall_quality	2.419	-0.52	2.434	-0.49	2.635	0.412
190	score speech qualityvoiceclap_attribute:score_speech_quality	2.040	+2.15	2.057	+2.40	1.891	0.069
191	talking speedvoiceclap_attribute:talking_speed	10.515	+0.40	11.446	+0.64	9.028	3.756

All Orange embedding components

The cosine above is the meaningful vector-level comparison; component values have no standalone semantic label.

Timbre — all 128 vector components

Dimension	Tiny	Base	Orange teacher
0	0.1316	0.0712	-0.0814
1	0.0729	0.0402	-0.0540
2	-0.0625	-0.0459	-0.0003
3	-0.0436	-0.0662	-0.0829
4	-0.0804	-0.0810	-0.0768
5	-0.1107	-0.0885	-0.1035
6	0.0472	0.0807	0.0227
7	0.1824	0.1823	0.1780
8	0.0392	0.0407	0.1646
9	0.0007	-0.0453	-0.0027
10	-0.0742	-0.0679	-0.0760
11	-0.0964	-0.0971	-0.0066
12	-0.0814	-0.0744	-0.0823
13	-0.0076	-0.0280	0.0695
14	0.0462	0.0121	-0.0120
15	0.0371	0.0639	-0.0064
16	-0.0886	-0.0741	-0.0069
17	-0.0798	-0.0872	-0.0850
18	-0.0791	-0.0676	-0.0754
19	-0.0912	-0.0590	-0.0773
20	-0.0168	0.0161	0.0549
21	-0.0303	-0.0892	-0.0752
22	0.0049	-0.0512	-0.0769
23	-0.0931	-0.1076	0.0070
24	0.0206	0.0233	-0.0169
25	0.0332	0.0505	0.1494
26	-0.0729	-0.0718	-0.0767
27	-0.0632	-0.0374	-0.0763
28	-0.0873	-0.0977	-0.0901
29	-0.0485	-0.0443	-0.0614
30	-0.0107	0.0498	0.0687
31	-0.0321	-0.0449	-0.0191
32	0.0505	0.0853	0.0403
33	-0.0811	-0.1017	-0.0901
34	-0.0938	-0.0741	-0.0733
35	0.1036	0.1207	-0.0025
36	-0.0983	-0.1128	-0.0879
37	-0.0970	-0.0931	-0.0969
38	0.1355	0.1207	0.1116
39	-0.0905	-0.0741	-0.0825
40	0.1250	0.1010	0.1128
41	-0.0254	-0.0639	-0.1078
42	-0.0899	-0.1023	-0.0825
43	0.0100	-0.0065	0.1125
44	0.0736	0.0643	0.0736
45	0.1433	0.1128	0.1458
46	-0.0241	0.0036	-0.0056
47	-0.0697	-0.0758	0.0143
48	-0.0746	-0.0721	-0.0798
49	0.1446	0.1141	0.0622
50	0.0313	-0.0298	-0.0099
51	0.1094	0.1351	0.1143
52	-0.0557	-0.0551	0.0665
53	-0.0329	-0.0308	0.0363
54	-0.0951	-0.1089	-0.0915
55	0.0742	0.0279	-0.0267
56	-0.0847	-0.0820	-0.0776
57	-0.0309	-0.0630	-0.0897
58	0.1407	0.1469	0.1584
59	0.0713	0.1030	0.0900
60	0.2084	0.1600	0.1273
61	0.1544	0.1436	0.0806
62	0.0778	0.0810	0.0964
63	0.0944	0.1167	0.1606
64	0.0531	0.0341	0.0947
65	-0.0729	-0.0685	-0.0667
66	0.1583	0.2191	0.1520
67	-0.0762	-0.0738	-0.0789
68	-0.0824	-0.0239	0.0052
69	-0.0593	-0.0872	-0.0294
70	0.1042	0.1377	0.0362
71	0.2358	0.2322	0.1719
72	-0.0918	-0.0958	-0.0792
73	0.0165	0.0014	-0.1000
74	0.0019	-0.0274	0.0784
75	0.1224	0.1128	0.0221
76	0.0944	0.0817	0.0197
77	-0.0795	-0.0761	-0.0747
78	-0.0736	-0.0603	-0.0728
79	-0.0521	-0.0346	-0.0709
80	-0.0677	-0.0656	-0.0740
81	0.1661	0.1174	0.1353
82	-0.0847	-0.0833	-0.0782
83	0.1329	0.1312	0.0688
84	0.0056	-0.0009	0.0223
85	-0.0075	-0.0408	-0.0869
86	0.0511	0.0305	-0.0525
87	-0.0990	-0.0905	-0.0944
88	-0.0257	-0.0067	-0.0584
89	-0.0752	-0.0892	-0.0670
90	0.1107	0.1541	0.0513
91	-0.0368	-0.0354	-0.0752
92	-0.0765	-0.0738	-0.0794
93	0.0655	0.0456	0.1061
94	0.0269	0.0659	-0.0127
95	-0.0089	-0.0479	-0.0561
96	-0.0655	-0.0780	0.0940
97	0.2110	0.2217	0.2805
98	-0.0847	-0.0931	-0.0729
99	0.0957	0.0790	-0.0687
100	0.1544	0.2099	0.0232
101	-0.0821	-0.0872	-0.0790
102	-0.0023	0.0200	0.0577
103	-0.1009	-0.1043	-0.0863
104	-0.0077	0.0065	0.0314
105	-0.0977	-0.0679	-0.0789
106	-0.0321	-0.0071	0.0082
107	-0.0778	-0.0682	-0.0762
108	-0.0892	-0.0964	-0.0887
109	0.0651	0.0823	0.0091
110	0.0681	0.0682	0.1852
111	0.0309	0.0155	0.1504
112	-0.1055	-0.0846	-0.0806
113	-0.0661	-0.0777	-0.1081
114	0.0436	0.0185	-0.0236
115	0.1094	0.0653	0.0565
116	0.1517	0.1226	0.0958
117	0.0118	0.0538	0.1322
118	-0.0752	-0.0728	-0.0796
119	-0.0068	0.0004	-0.0403
120	0.0449	0.0323	-0.0841
121	0.1426	0.1286	0.1678
122	-0.0602	-0.0567	0.0586
123	0.0174	0.0100	0.1064
124	0.0655	0.0502	-0.0390
125	-0.0114	0.0234	-0.0815
126	-0.0306	-0.0167	-0.0427
127	0.1824	0.1902	0.1580

Identity — all 250 vector components

Dimension	Tiny	Base	Orange teacher
0	0.1097	0.1195	0.1185
1	-0.0661	-0.0432	-0.0423
2	-0.0476	-0.0798	-0.0538
3	-0.0031	-0.0300	-0.0303
4	0.0098	0.0453	-0.0398
5	0.1452	0.1314	0.0320
6	0.0726	0.0478	0.0358
7	-0.0071	-0.0112	-0.0443
8	-0.0111	0.0307	0.0698
9	0.1992	0.1857	0.1930
10	0.0439	0.0644	0.0098
11	-0.0867	-0.1054	-0.0591
12	0.0732	0.0641	0.0302
13	0.2544	0.2379	0.0681
14	-0.0625	-0.0334	-0.0624
15	-0.0153	-0.0085	-0.0515
16	0.0861	0.0375	0.1017
17	-0.0974	-0.0722	-0.0525
18	0.0726	0.0231	-0.0202
19	-0.0839	-0.0722	-0.0086
20	0.0397	0.0405	0.0189
21	-0.0509	-0.0394	-0.0405
22	-0.0325	0.0103	-0.0453
23	-0.0675	-0.0831	-0.0423
24	-0.0332	-0.0451	-0.0373
25	0.0339	0.0511	0.0369
26	0.0571	0.0402	0.0483
27	-0.0633	-0.0383	-0.0355
28	-0.0155	-0.0147	-0.0415
29	-0.0450	-0.0119	-0.0421
30	0.0168	0.0581	0.0005
31	0.1328	0.1347	0.0487
32	0.1531	0.1423	0.1063
33	-0.0473	-0.0625	-0.0392
34	0.1677	0.1179	0.0688
35	-0.0371	-0.0424	-0.0563
36	0.0622	0.0075	-0.0462
37	-0.0134	-0.0071	0.0051
38	-0.0021	-0.0101	-0.0318
39	-0.0805	-0.0549	-0.0651
40	-0.0405	-0.0182	-0.0506
41	-0.0805	-0.0538	-0.0502
42	0.0249	-0.0139	-0.0434
43	0.0228	0.0494	0.0138
44	0.0017	-0.0367	-0.0526
45	-0.0119	0.0432	0.0467
46	-0.0793	-0.0744	-0.0642
47	0.0974	0.0036	0.0531
48	0.0934	0.0999	0.1206
49	-0.0495	-0.0364	-0.0423
50	0.0349	0.0367	-0.0609
51	0.1114	0.0305	0.0458
52	0.0402	0.0633	-0.0183
53	-0.0726	-0.0771	-0.0423
54	-0.0208	0.0037	0.0203
55	0.0459	0.0551	0.0130
56	-0.0546	-0.0258	-0.0601
57	0.0400	0.0633	-0.0035
58	-0.0495	-0.0228	-0.0420
59	-0.0227	0.0037	-0.0609
60	-0.0574	-0.0733	-0.0458
61	-0.0523	-0.0303	-0.0406
62	-0.0263	-0.0853	-0.0370
63	0.0467	0.0258	0.0268
64	-0.0777	-0.0809	-0.0487
65	0.0537	0.1048	0.1407
66	0.0990	0.0798	-0.0230
67	-0.0360	-0.0831	-0.0211
68	0.0917	0.1070	0.0577
69	0.0298	0.0248	-0.0004
70	0.0055	-0.0115	-0.0634
71	-0.0310	-0.0426	-0.0458
72	0.0069	0.0224	0.0077
73	0.0456	0.0606	0.0011
74	-0.0929	-0.0956	-0.0472
75	-0.0105	-0.0126	-0.0172
76	0.0352	0.0300	0.0008
77	0.0069	0.0151	0.1444
78	0.0366	0.0972	0.0795
79	-0.0647	-0.0749	-0.0468
80	0.0501	0.0994	0.1206
81	-0.0380	-0.0023	0.0036
82	0.0329	0.0185	-0.0420
83	0.0481	0.0513	0.0300
84	-0.0082	0.0172	0.0188
85	-0.0297	-0.0289	-0.0467
86	-0.0227	-0.0492	-0.0417
87	-0.0591	-0.0633	-0.0372
88	0.1384	0.1162	0.0723
89	-0.0644	-0.0383	-0.0422
90	0.0339	-0.0388	-0.0462
91	0.1187	0.0820	0.0912
92	-0.0098	-0.0549	-0.0403
93	0.0917	0.1249	0.1135
94	0.0046	0.0115	-0.0367
95	0.0242	-0.0267	0.0130
96	-0.0347	-0.0229	-0.0417
97	-0.0248	0.0238	0.0326
98	-0.0200	-0.0494	-0.0493
99	0.0026	0.0185	0.0525
100	0.0478	-0.0154	-0.0526
101	-0.0602	-0.0614	-0.0441
102	-0.0442	-0.0318	0.0233
103	-0.0568	-0.0227	-0.0559
104	-0.1300	-0.1249	-0.0608
105	-0.0900	-0.0535	-0.0607
106	0.0799	0.0858	0.1333
107	-0.0428	-0.0581	-0.0418
108	-0.0228	-0.0551	-0.0347
109	-0.0591	-0.0329	-0.0449
110	-0.0414	-0.0358	0.0081
111	-0.0262	-0.0394	-0.0385
112	-0.0613	-0.0380	-0.0377
113	-0.1024	-0.1206	-0.0796
114	-0.1097	-0.0853	-0.0651
115	0.0203	0.0234	0.1199
116	0.0183	0.0262	0.0386
117	-0.0305	-0.0388	-0.0548
118	0.0433	0.0755	0.0628
119	0.1390	0.0934	0.1584
120	-0.0183	-0.0137	-0.0289
121	0.0782	0.0630	0.1125
122	-0.0450	-0.0394	-0.0441
123	-0.0170	-0.0074	-0.0248
124	0.0473	0.0722	0.0919
125	0.1767	0.1825	0.1885
126	0.0670	0.0880	0.0400
127	0.0360	0.0026	0.0318
128	-0.0633	-0.0323	0.0083
129	0.1103	0.1331	0.1531
130	0.0459	0.0687	0.1849
131	-0.0257	-0.0684	-0.0408
132	0.0518	0.1314	0.0492
133	0.0291	0.0080	-0.0443
134	0.0777	-0.0293	-0.0642
135	0.0293	0.0286	0.0830
136	-0.0549	-0.0595	-0.0500
137	-0.0447	-0.0443	-0.0433
138	-0.0532	-0.0472	-0.0412
139	-0.0425	-0.0798	-0.0477
140	0.0103	0.0099	0.0228
141	0.0281	0.0413	0.0864
142	-0.0248	-0.0581	-0.0238
143	-0.0124	-0.0267	-0.0280
144	-0.0026	-0.0364	0.0718
145	-0.0805	-0.0443	-0.0577
146	0.0490	0.0983	0.0882
147	-0.0929	-0.0831	-0.0415
148	-0.0692	-0.0825	-0.0515
149	-0.0175	-0.0478	0.0067
150	-0.0056	-0.0221	-0.0205
151	-0.0895	-0.0820	-0.0532
152	-0.0506	-0.0472	-0.0518
153	-0.0591	-0.0673	-0.0660
154	0.0308	-0.0625	0.0069
155	-0.0302	0.0025	-0.0609
156	0.0286	0.0208	0.0338
157	0.0467	0.0706	-0.0150
158	-0.0270	-0.0136	-0.0067
159	0.0732	0.0500	0.0893
160	-0.0001	-0.0573	-0.0443
161	0.0771	0.1108	0.0349
162	0.0033	0.0196	0.0382
163	-0.0394	-0.0208	-0.0343
164	-0.0506	-0.0261	-0.0410
165	0.0566	0.1189	0.0914
166	-0.0346	-0.0432	-0.0543
167	-0.0416	-0.0097	-0.0591
168	0.0236	0.0232	0.0560
169	0.0028	-0.0652	-0.0020
170	-0.0568	-0.0809	-0.0437
171	0.0554	0.0410	0.0149
172	0.0349	0.0333	-0.0311
173	-0.0419	-0.0111	-0.0547
174	0.0319	0.0224	0.0132
175	0.0878	0.0578	0.0133
176	-0.0605	-0.0573	-0.0397
177	-0.0551	-0.0644	-0.0385
178	0.0698	0.0581	-0.0137
179	-0.0219	-0.0013	-0.0351
180	0.0484	0.0467	0.0702
181	0.0184	-0.0464	-0.0572
182	-0.0349	-0.0047	0.0463
183	-0.0193	-0.0885	0.0023
184	-0.0176	-0.0486	-0.0474
185	0.0360	0.0267	0.0211
186	-0.0137	-0.0086	-0.0365
187	0.0433	0.1043	0.1133
188	0.0023	0.0383	-0.0096
189	-0.0083	0.0206	0.0284
190	-0.0509	-0.0346	-0.0813
191	-0.0706	-0.0592	-0.0623
192	-0.0042	0.0223	-0.0565
193	-0.0535	-0.0540	-0.0492
194	0.0678	0.0853	0.0450
195	-0.0239	-0.0319	-0.0443
196	-0.0481	-0.0234	-0.0453
197	0.1052	0.0717	0.0470
198	-0.0644	-0.0842	-0.0451
199	0.1745	0.1325	0.2595
200	-0.0340	0.0115	-0.0068
201	-0.0137	-0.0156	-0.0439
202	0.0238	0.0085	-0.0412
203	0.0689	0.0679	0.1236
204	-0.0149	-0.0204	-0.0185
205	-0.0689	-0.0472	-0.0812
206	0.0599	0.0513	-0.0481
207	-0.0833	-0.0521	-0.0630
208	-0.0402	-0.0262	-0.0484
209	-0.0642	-0.0329	-0.0751
210	-0.0793	-0.0809	-0.0607
211	0.0900	0.0815	-0.0146
212	-0.0867	-0.0310	-0.0609
213	0.0391	0.0760	-0.0300
214	-0.0726	-0.0155	-0.0092
215	0.0084	0.0090	-0.0026
216	0.0833	0.0543	0.0319
217	0.0013	-0.0098	-0.0631
218	-0.0201	-0.0535	-0.0541
219	0.0154	0.0316	0.0820
220	-0.0591	-0.1016	-0.0515
221	0.0346	0.0190	0.0093
222	0.1368	0.1032	0.0729
223	0.0347	-0.0303	-0.0374
224	-0.0675	-0.0003	-0.0426
225	-0.0436	-0.0361	-0.0388
226	0.0467	0.0238	0.0332
227	0.0374	0.0771	0.1539
228	0.0608	0.0041	-0.0064
229	0.0090	-0.0511	-0.0511
230	-0.0433	-0.0285	-0.0475
231	0.0425	0.0755	0.0655
232	0.0411	0.0771	0.0372
233	0.0701	0.0353	0.0365
234	0.0619	0.0994	-0.0010
235	0.0307	-0.0023	-0.0032
236	-0.0602	-0.0635	-0.0401
237	0.0203	0.0239	0.0794
238	-0.0532	-0.0546	-0.0512
239	0.0242	0.0815	0.0133
240	0.0091	0.0345	0.0101
241	-0.0159	0.0242	-0.0630
242	-0.1097	-0.0950	-0.0687
243	-0.0183	-0.0235	-0.0303
244	-0.0108	-0.0220	-0.0496
245	-0.0582	-0.0459	-0.0443
246	0.0985	0.1320	0.2145
247	0.0675	0.0896	0.1510
248	0.0019	0.0027	-0.0417
249	-0.0242	0.0025	-0.0594

Source: Emolia / Emilia source archive · SHA-256 82c7725e3e3a3683…

e09KoreanEmolia / Emilia

Emolia KO · KO_B00000_S00030_W000053

Natural speech · Original speech · 8.9 s

다행히도 방송상 렉은 없고 뭐 화면이 급변하는 게임은 아니니까. 그 다음에 이게 아무도 없는 행성이고 플레이어 4가

Tiny Base · values are model estimates, not ground truth

Strongest emotions relative to training

Concentration

z +1.49 / +1.72raw 1.74 / 1.91

Contemplation

z +1.05 / +1.32raw 0.71 / 0.87

Contentment

z +1.12 / +0.98raw 0.58 / 0.51

Interest

z +0.48 / +0.53raw 2.02 / 2.07

Confusion

z +0.38 / +0.14raw 0.21 / 0.08

Doubt

z +0.36 / +0.09raw 0.17 / 0.05

Hope Enthusiasm Optimism

z +0.17 / +0.21raw 0.24 / 0.28

The center of each bar is the S9 teacher median. Positive z is to the right; negative z is to the left. Ranking uses z, not raw teacher units.

Strongest VoiceNet dimensions relative to training

Teacher or didactic style (S_TECH)

z +1.76 / +2.09raw 2.80 / 3.21

Authoritative style (S_AUTH)

z +1.67 / +1.84raw 2.83 / 3.01

Mixed resonance (R_MIXD)

z +1.36 / +1.69raw 2.58 / 2.85

Throat resonance (R_THRT)

z +1.45 / +1.46raw 3.23 / 3.24

Formal style (S_FORM)

z +1.07 / +1.28raw 2.29 / 2.51

Oral resonance (R_ORAL)

z +1.22 / +1.28raw 3.09 / 3.13

Head resonance (R_HEAD)

z +0.94 / +1.25raw 2.92 / 3.17

All 57 VoiceNet predictions, including raw units, are in the full table below. These seven are ranked by z; the top values may differ from the strongest raw dimensions.

Voice, speed and quality scores in context

Genuineness (0–6)z +0.60 / +0.63raw 3.31 / 3.35

Vocal-burst blend (0–10)z -1.38 / -1.34raw 2.91 / 3.01

Content enjoyment (CE)z +0.53 / +0.37raw 5.34 / 5.18

Production quality (PQ)z -0.38 / -0.42raw 6.71 / 6.67

Speech signal quality, calibratedz +0.08 / -0.01raw 3.53 / 3.48

Background quality, calibratedz +0.56 / +0.65raw 3.90 / 3.99

Overall quality, calibratedz +0.54 / +0.55raw 3.17 / 3.18

P.808 MOS estimatez +0.66 / +0.64raw 3.75 / 3.74

score content enjoymentz +0.18 / +0.20raw 4.56 / 4.57

score overall qualityz +0.64 / +0.63raw 2.97 / 2.97

Background Noisez +0.16 / +0.16raw 0.85 / 0.85

Tempo (TEMP)z +0.59 / +0.70raw 2.82 / 2.95

Arousal (AROU)z -0.05 / -0.04raw 2.31 / 2.31

Valence (VALN)z +0.50 / +0.71raw 2.89 / 3.12

Recording quality (RCQL)z -0.04 / -0.03raw 2.72 / 2.73

Background noise (BKGN)z +0.25 / +0.22raw 2.90 / 2.87

talking speedz +0.48 / +0.65raw 10.82 / 11.46

Characters per second (CPS): 7.18 raw · z -0.49

Orange speaker embedding reconstruction

Cosine against Orange on this same clip (higher means closer to that teacher vector):

Embedding	Tiny	Base
Timbre · 128D	0.838	0.880
Identity · 250D	0.691	0.768

Vocal-burst regions

Tiny

Base

0 s8.9 s

Verified burst intervals are unavailable for this clip.

Tiny: 0 regions, count-head estimate 0.02; Base: 0 regions, count-head estimate 0.00.

Exact predicted start and end times

Model	Region	Start (s)	End (s)	Duration (s)

All 192 score slots · raw and z values

#	Target	Tiny raw	Tiny z	Base raw	Base z	Train median	Train SD
Emotion scores Forty clip-level Empathic Insight emotion teacher outputs. Each row evaluates one named emotion score.
0	Affectionemo_Affection	0.007	-0.00	0.004	-0.01	0.007	0.570
1	Amusementemo_Amusement	0.041	+0.05	0.020	+0.02	-0.001	0.885
2	Angeremo_Anger	0.018	+0.02	0.082	+0.13	0.004	0.613
3	Astonishment Surpriseemo_Astonishment_Surprise	0.029	+0.04	0.047	+0.07	0.005	0.572
4	Aweemo_Awe	-0.020	-0.05	-0.011	-0.02	0.000	0.427
5	Bitternessemo_Bitterness	0.022	+0.02	0.020	+0.02	0.013	0.415
6	Concentrationemo_Concentration	1.738	+1.49	1.909	+1.72	0.634	0.741
7	Confusionemo_Confusion	0.207	+0.38	0.075	+0.14	0.001	0.540
8	Contemplationemo_Contemplation	0.708	+1.05	0.869	+1.32	0.082	0.598
9	Contemptemo_Contempt	0.017	+0.04	0.004	+0.01	-0.000	0.464
10	Contentmentemo_Contentment	0.578	+1.12	0.506	+0.98	0.000	0.514
11	Disappointmentemo_Disappointment	0.008	+0.01	0.040	+0.06	0.000	0.700
12	Disgustemo_Disgust	0.010	+0.01	-0.003	-0.02	0.007	0.489
13	Distressemo_Distress	0.031	+0.04	0.053	+0.07	0.000	0.821
14	Doubtemo_Doubt	0.174	+0.36	0.046	+0.09	0.006	0.466
15	Elationemo_Elation	0.011	-0.00	0.014	+0.00	0.012	0.728
16	Embarrassmentemo_Embarrassment	-0.017	-0.14	-0.013	-0.13	0.043	0.430
17	Emotional Numbnessemo_Emotional_Numbness	0.030	+0.03	0.113	+0.12	0.004	0.917
18	Fatigue Exhaustionemo_Fatigue_Exhaustion	0.047	+0.04	0.035	+0.01	0.028	0.539
19	Fearemo_Fear	-0.034	-0.08	0.009	-0.01	0.015	0.610
20	Helplessnessemo_Helplessness	0.016	+0.03	0.013	+0.02	-0.004	0.696
21	Hope Enthusiasm Optimismemo_Hope_Enthusiasm_Optimism	0.243	+0.17	0.279	+0.21	0.117	0.760
22	Impatience and Irritabilityemo_Impatience_and_Irritability	-0.071	-0.31	-0.055	-0.29	0.149	0.705
23	Infatuationemo_Infatuation	-0.043	-0.05	-0.020	-0.01	-0.015	0.533
24	Interestemo_Interest	2.020	+0.48	2.074	+0.53	1.589	0.907
25	Intoxication Altered States of Consciousnessemo_Intoxication_Altered_States_of_Consciousness	-0.022	+0.01	-0.043	-0.03	-0.025	0.559
26	Jealousy and Envyemo_Jealousy_and_Envy	0.044	-0.03	0.033	-0.06	0.059	0.442
27	Longingemo_Longing	-0.019	-0.17	0.038	-0.08	0.087	0.632
28	Malevolence Maliceemo_Malevolence_Malice	0.053	-0.00	0.045	-0.02	0.055	0.534
29	Painemo_Pain	0.033	+0.06	0.006	+0.01	-0.002	0.579
30	Pleasure Ecstasyemo_Pleasure_Ecstasy	-0.003	-0.03	0.025	+0.01	0.017	0.614
31	Prideemo_Pride	0.044	+0.08	0.100	+0.19	0.002	0.509
32	Reliefemo_Relief	0.040	+0.01	0.010	-0.03	0.033	0.681
33	Sadnessemo_Sadness	0.023	+0.03	0.005	+0.01	0.000	0.759
34	Sexual Lustemo_Sexual_Lust	-0.015	-0.09	-0.006	-0.07	0.030	0.494
35	Shameemo_Shame	0.010	-0.01	-0.011	-0.05	0.013	0.510
36	Sournessemo_Sourness	-0.025	-0.04	0.008	+0.03	-0.005	0.439
37	Teasingemo_Teasing	0.020	+0.04	0.047	+0.09	0.000	0.545
38	Thankfulness Gratitudeemo_Thankfulness_Gratitude	0.102	+0.09	0.031	-0.01	0.041	0.697
39	Triumphemo_Triumph	-0.027	-0.04	-0.010	-0.01	-0.007	0.521
VoiceNet dimensions Fifty-seven VoiceNet voice, delivery, style, and recording dimensions. Codes are expanded in the target column.
40	Perceived voice age (AGEV)vn_AGEV_reg	2.403	-0.47	2.347	-0.51	2.984	1.238
41	Arousal (AROU)vn_AROU_reg	2.306	-0.05	2.311	-0.04	2.359	1.147
42	Arousal shift (ARSH)vn_ARSH_reg	2.456	-0.14	2.627	+0.05	2.580	0.867
43	Vocal attack (ATCK)vn_ATCK_reg	1.746	-0.32	1.887	-0.21	2.162	1.295
44	Background noise (BKGN)vn_BKGN_reg	2.896	+0.25	2.869	+0.22	2.703	0.761
45	Brightness (BRGT)vn_BRGT_reg	1.758	-0.29	2.067	+0.09	1.991	0.813
46	Speech chunking (CHNK)vn_CHNK_reg	2.880	+0.83	2.934	+0.88	1.847	1.239
47	Articulation clarity (CLRT)vn_CLRT_reg	1.855	-0.17	1.824	-0.21	2.018	0.945
48	Cognitive load (COGL)vn_COGL_reg	2.627	+0.50	2.557	+0.44	2.094	1.061
49	Dynamic arc (DARC)vn_DARC_reg	1.677	+0.05	1.753	+0.10	1.615	1.380
50	Disfluency (DFLU)vn_DFLU_reg	3.009	+0.44	3.392	+0.76	2.488	1.184
51	Emphasis (EMPH)vn_EMPH_reg	3.031	+0.28	3.123	+0.34	2.607	1.524
52	Esthetics (ESTH)vn_ESTH_reg	2.488	+0.11	2.685	+0.36	2.402	0.782
53	Content appropriateness (EXPL)vn_EXPL_reg	0.137	+0.16	0.122	+0.11	0.086	0.322
54	Focus (FOCS)vn_FOCS_reg	1.600	-0.68	1.582	-0.69	2.344	1.102
55	Fullness (FULL)vn_FULL_reg	2.596	+0.92	2.634	+0.96	1.778	0.889
56	Perceived gender (GEND)vn_GEND_reg	3.695	-0.23	3.894	-0.10	4.055	1.588
57	Harmonicity (HARM)vn_HARM_reg	2.844	+0.43	3.077	+0.71	2.480	0.836
58	Metallic character (METL)vn_METL_reg	2.324	+0.73	2.357	+0.77	1.621	0.958
59	Pitch range (RANG)vn_RANG_reg	2.644	-0.30	2.498	-0.46	2.914	0.897
60	Recording quality (RCQL)vn_RCQL_reg	2.719	-0.04	2.727	-0.03	2.754	0.888
61	Vocal register (REGS)vn_REGS_reg	0.853	-0.27	0.976	-0.18	1.198	1.268
62	Respiration (RESP)vn_RESP_reg	2.266	-0.39	2.095	-0.55	2.680	1.056
63	Roughness (ROUG)vn_ROUG_reg	2.225	+0.22	2.328	+0.33	2.033	0.887
64	Chest resonance (R_CHST)vn_R_CHST_reg	2.678	+0.64	2.768	+0.75	2.135	0.844
65	Head resonance (R_HEAD)vn_R_HEAD_reg	2.922	+0.94	3.173	+1.25	2.148	0.822
66	Mask resonance (R_MASK)vn_R_MASK_reg	2.163	+0.25	2.570	+0.66	1.908	1.005
67	Mixed resonance (R_MIXD)vn_R_MIXD_reg	2.579	+1.36	2.854	+1.69	1.436	0.841
68	Nasal resonance (R_NASL)vn_R_NASL_reg	3.054	+0.25	3.159	+0.35	2.791	1.047
69	Oral resonance (R_ORAL)vn_R_ORAL_reg	3.085	+1.22	3.132	+1.28	2.184	0.741
70	Throat resonance (R_THRT)vn_R_THRT_reg	3.232	+1.45	3.244	+1.46	2.070	0.803
71	Smoothness (SMTH)vn_SMTH_reg	2.879	+0.67	2.844	+0.64	2.143	1.093
72	Stance (STNC)vn_STNC_reg	2.668	+0.03	2.774	+0.12	2.633	1.137
73	Speech structure (STRU)vn_STRU_reg	2.900	+0.80	2.984	+0.88	2.137	0.958
74	ASMR style (S_ASMR)vn_S_ASMR_reg	1.945	+0.41	1.848	+0.34	1.370	1.411
75	Authoritative style (S_AUTH)vn_S_AUTH_reg	2.827	+1.67	3.005	+1.84	1.088	1.043
76	Cartoonish style (S_CART)vn_S_CART_reg	1.070	-0.35	0.733	-0.59	1.560	1.401
77	Casual style (S_CASU)vn_S_CASU_reg	3.623	-0.13	3.409	-0.30	3.793	1.278
78	Conversational style (S_CONV)vn_S_CONV_reg	2.944	+0.27	2.890	+0.22	2.594	1.318
79	Dramatic style (S_DRAM)vn_S_DRAM_reg	1.373	-1.17	1.159	-1.36	2.721	1.148
80	Formal style (S_FORM)vn_S_FORM_reg	2.285	+1.07	2.506	+1.28	1.195	1.021
81	Monologue style (S_MONO)vn_S_MONO_reg	3.804	+0.76	3.978	+0.90	2.824	1.284
82	Narrator style (S_NARR)vn_S_NARR_reg	1.803	+0.34	1.400	+0.06	1.307	1.446
83	Newsreader style (S_NEWS)vn_S_NEWS_reg	0.178	-0.41	0.029	-0.67	0.408	0.568
84	Playful style (S_PLAY)vn_S_PLAY_reg	2.489	+0.10	2.596	+0.19	2.352	1.315
85	Ranting or angry style (S_RANT)vn_S_RANT_reg	-0.918	-1.65	-1.197	-1.87	1.213	1.289
86	Storytelling style (S_STRY)vn_S_STRY_reg	1.748	-0.54	1.531	-0.70	2.480	1.366
87	Teacher or didactic style (S_TECH)vn_S_TECH_reg	2.803	+1.76	3.212	+2.09	0.646	1.227
88	Whispered talking style (S_WHIS)vn_S_WHIS_reg	2.551	+0.59	2.395	+0.49	1.597	1.618
89	Tempo (TEMP)vn_TEMP_reg	2.823	+0.59	2.954	+0.70	2.117	1.190
90	Tension (TENS)vn_TENS_reg	1.572	+0.02	1.458	-0.12	1.559	0.852
91	Valence (VALN)vn_VALN_reg	2.888	+0.50	3.117	+0.71	2.328	1.118
92	Valence shift (VALS)vn_VALS_reg	3.283	+0.71	3.588	+0.99	2.518	1.079
93	Velocity flux (VFLX)vn_VFLX_reg	2.183	-0.06	2.322	+0.05	2.256	1.208
94	Volatility (VOLT)vn_VOLT_reg	1.836	-0.85	1.680	-1.02	2.586	0.886
95	Vulnerability (VULN)vn_VULN_reg	2.059	-0.60	1.974	-0.69	2.648	0.984
96	Warmth (WARM)vn_WARM_reg	2.490	-0.10	2.421	-0.17	2.578	0.909
Genuineness, blend, and legacy quality Genuineness and vocal-burst blend are predicted. R_quality has Ladder training labels but no valid P3 test labels.
97	Genuineness (0–6)genuineness_0_6	3.312	+0.60	3.349	+0.63	2.332	1.621
98	Vocal-burst blend (0–10)blend_0_10	2.907	-1.38	3.013	-1.34	6.676	2.738
99	Legacy R_quality (no P3 test labels)R_quality	0.862	-0.69	0.874	-0.65	1.095	0.338
Empathic Insight Plus extra scores Nineteen additional clip-level teacher scores, including background noise and content enjoyment.
100	Ageeiv_extra:Age	3.301	+0.17	3.241	-0.03	3.250	0.293
101	Arousaleiv_extra:Arousal	0.961	-0.75	1.063	-0.52	1.289	0.435
102	Authenticityeiv_extra:Authenticity	2.702	+0.23	2.647	-0.13	2.667	0.153
103	Background Noiseeiv_extra:Background_Noise	0.851	+0.16	0.851	+0.16	0.808	0.264
104	Confident vs. Hesitanteiv_extra:Confident_vs._Hesitant	1.092	+0.17	1.162	+0.40	1.040	0.303
105	Gendereiv_extra:Gender	-1.079	-0.46	-1.017	-0.40	-0.621	0.999
106	High-Pitched vs. Low-Pitchedeiv_extra:High-Pitched_vs._Low-Pitched	1.971	+0.57	1.896	+0.27	1.827	0.250
107	Monotone vs. Expressiveeiv_extra:Monotone_vs._Expressive	1.692	-0.36	1.739	-0.26	1.859	0.470
108	Recording Qualityeiv_extra:Recording_Quality	2.192	+0.14	2.171	+0.08	2.144	0.332
109	Serious vs. Humorouseiv_extra:Serious_vs._Humorous	1.136	+0.61	1.027	+0.29	0.929	0.340
110	Soft vs. Harsheiv_extra:Soft_vs._Harsh	0.253	-0.09	0.242	-0.12	0.281	0.320
111	Submissive vs. Dominanteiv_extra:Submissive_vs._Dominant	0.268	-0.33	0.258	-0.36	0.376	0.324
112	Valenceeiv_extra:Valence	-0.054	-0.16	-0.060	-0.17	0.005	0.380
113	Vulnerable vs. Emotionally Detachedeiv_extra:Vulnerable_vs._Emotionally_Detached	2.099	+0.88	2.096	+0.87	1.715	0.437
114	Warm vs. Coldeiv_extra:Warm_vs._Cold	0.138	+0.29	0.133	+0.27	0.051	0.300
115	score background qualityeiv_extra:score_background_quality	3.613	+0.45	3.681	+0.55	3.301	0.693
116	score content enjoymenteiv_extra:score_content_enjoyment	4.563	+0.18	4.568	+0.20	4.507	0.303
117	score overall qualityeiv_extra:score_overall_quality	2.975	+0.64	2.973	+0.63	2.652	0.507
118	score speech qualityeiv_extra:score_speech_quality	1.883	+0.52	1.882	+0.51	1.808	0.146
Meta AudioBox Aesthetics Four AudioBox aesthetic teacher outputs. Expansions follow the official Meta model card.
119	Content enjoyment (CE)audiobox:CE	5.340	+0.53	5.179	+0.37	4.799	1.018
120	Content usefulness (CU)audiobox:CU	5.798	+0.15	5.717	+0.07	5.649	1.001
121	Production complexity (PC)audiobox:PC	1.795	-0.33	1.694	-0.39	2.331	1.617
122	Production quality (PQ)audiobox:PQ	6.709	-0.38	6.674	-0.42	7.044	0.879
Microsoft DNSMOS Seven DNSMOS teacher outputs: raw and calibrated SIG/BAK/OVRL estimates plus P.808 MOS.
123	Speech signal quality, rawdnsmos:SIG_raw	3.981	+0.12	3.901	+0.00	3.900	0.669
124	Background quality, rawdnsmos:BAK_raw	4.026	+0.72	4.162	+0.85	3.211	1.124
125	Overall quality, rawdnsmos:OVRL_raw	3.576	+0.61	3.608	+0.64	3.085	0.812
126	Speech signal quality, calibrateddnsmos:SIG	3.528	+0.08	3.483	-0.01	3.488	0.501
127	Background quality, calibrateddnsmos:BAK	3.905	+0.56	3.992	+0.65	3.389	0.928
128	Overall quality, calibrateddnsmos:OVRL	3.167	+0.54	3.176	+0.55	2.840	0.606
129	P.808 MOS estimatednsmos:P808_MOS	3.750	+0.66	3.738	+0.64	3.421	0.496
Vocal-burst count The regression target is log(1 + count). A separate table also reports count error after inverse transformation.
130	Vocal-burst count, log(1 + count)burst_count_log1p	0.018	+0.03	0.002	+0.00	0.000	0.647
VoiceCLAP attributes Sixty-one individual VoiceCLAP attribute teacher scores. The raw 768D VoiceCLAP embedding is stored in sidecars but is not a model output.
131	Affectionvoiceclap_attribute:Affection	0.966	+0.03	0.926	-0.04	0.947	0.554
132	Agevoiceclap_attribute:Age	3.032	-0.36	3.148	-0.15	3.229	0.547
133	Amusementvoiceclap_attribute:Amusement	0.142	-0.44	0.119	-0.48	0.392	0.572
134	Angervoiceclap_attribute:Anger	0.323	-1.32	0.264	-1.44	0.992	0.506
135	Arousalvoiceclap_attribute:Arousal	0.832	-0.94	0.968	-0.73	1.420	0.622
136	Astonishment Surprisevoiceclap_attribute:Astonishment_Surprise	0.191	-0.66	0.297	-0.44	0.509	0.479
137	Authenticityvoiceclap_attribute:Authenticity	2.681	-0.54	2.732	-0.23	2.770	0.167
138	Awevoiceclap_attribute:Awe	0.345	-0.75	0.397	-0.55	0.539	0.259
139	Background Noisevoiceclap_attribute:Background_Noise	0.534	-0.13	0.578	+0.04	0.567	0.264
140	Bitternessvoiceclap_attribute:Bitterness	0.130	-1.96	0.124	-1.99	0.592	0.236
141	Concentrationvoiceclap_attribute:Concentration	1.720	+0.95	1.861	+1.22	1.214	0.531
142	Confident vs. Hesitantvoiceclap_attribute:Confident_vs._Hesitant	1.373	+0.65	1.414	+0.74	1.069	0.468
143	Confusionvoiceclap_attribute:Confusion	0.854	+0.63	0.850	+0.62	0.643	0.334
144	Contemplationvoiceclap_attribute:Contemplation	1.103	+0.80	1.049	+0.66	0.780	0.406
145	Contemptvoiceclap_attribute:Contempt	0.014	-2.05	0.040	-1.97	0.709	0.339
146	Contentmentvoiceclap_attribute:Contentment	0.593	+0.02	0.510	-0.25	0.588	0.307
147	Disappointmentvoiceclap_attribute:Disappointment	0.409	-1.21	0.411	-1.20	0.760	0.291
148	Disgustvoiceclap_attribute:Disgust	0.254	-1.79	0.238	-1.87	0.625	0.207
149	Distressvoiceclap_attribute:Distress	0.511	-1.19	0.382	-1.56	0.927	0.350
150	Doubtvoiceclap_attribute:Doubt	0.467	-0.36	0.448	-0.46	0.535	0.188
151	Elationvoiceclap_attribute:Elation	0.296	-0.61	0.399	-0.35	0.539	0.397
152	Embarrassmentvoiceclap_attribute:Embarrassment	0.235	-0.23	0.273	-0.11	0.307	0.314
153	Emotional Numbnessvoiceclap_attribute:Emotional_Numbness	0.680	+0.06	0.608	-0.21	0.664	0.266
154	Fatigue Exhaustionvoiceclap_attribute:Fatigue_Exhaustion	0.397	-0.25	0.272	-0.73	0.462	0.261
155	Fearvoiceclap_attribute:Fear	0.455	-0.77	0.272	-1.63	0.618	0.212
156	Gendervoiceclap_attribute:Gender	-0.830	-0.68	-0.794	-0.64	-0.151	1.005
157	Helplessnessvoiceclap_attribute:Helplessness	0.638	-0.07	0.579	-0.30	0.658	0.268
158	High-Pitched vs. Low-Pitchedvoiceclap_attribute:High-Pitched_vs._Low-Pitched	1.936	+0.25	1.984	+0.38	1.840	0.375
159	Hope Enthusiasm Optimismvoiceclap_attribute:Hope_Enthusiasm_Optimism	0.456	-0.63	0.582	-0.31	0.705	0.396
160	Impatience and Irritabilityvoiceclap_attribute:Impatience_and_Irritability	0.235	-1.51	0.206	-1.57	1.052	0.541
161	Infatuationvoiceclap_attribute:Infatuation	0.483	-0.38	0.421	-0.56	0.608	0.332
162	Interestvoiceclap_attribute:Interest	1.733	+0.31	1.832	+0.53	1.598	0.440
163	Intoxication Altered States of Consciousnessvoiceclap_attribute:Intoxication_Altered_States_of_Consciousness	0.225	-0.60	0.075	-0.92	0.502	0.463
164	Jealousy & Envyvoiceclap_attribute:Jealousy_&_Envy	0.242	-1.15	0.162	-1.47	0.523	0.245
165	Longingvoiceclap_attribute:Longing	0.498	-0.18	0.416	-0.56	0.538	0.220
166	Malevolence Malicevoiceclap_attribute:Malevolence_Malice	0.230	-1.74	0.165	-1.93	0.833	0.346
167	Monotone vs. Expressivevoiceclap_attribute:Monotone_vs._Expressive	1.336	-0.74	1.411	-0.61	1.775	0.594
168	Painvoiceclap_attribute:Pain	0.178	-0.93	0.109	-1.25	0.381	0.218
169	Pleasure Ecstasyvoiceclap_attribute:Pleasure_Ecstasy	0.199	-1.01	0.262	-0.80	0.503	0.301
170	Pridevoiceclap_attribute:Pride	0.517	-0.75	0.438	-0.98	0.780	0.349
171	Recording Qualityvoiceclap_attribute:Recording_Quality	2.232	-0.25	2.289	-0.08	2.313	0.328
172	Reliefvoiceclap_attribute:Relief	0.849	-0.42	0.615	-0.99	1.025	0.415
173	Sadnessvoiceclap_attribute:Sadness	0.484	-0.86	0.440	-1.00	0.752	0.313
174	Serious vs. Humorousvoiceclap_attribute:Serious_vs._Humorous	0.777	-0.05	0.750	-0.09	0.803	0.568
175	Sexual Lustvoiceclap_attribute:Sexual_Lust	0.239	-0.95	0.154	-1.15	0.635	0.419
176	Shamevoiceclap_attribute:Shame	0.468	-0.21	0.371	-0.55	0.526	0.283
177	Soft vs. Harshvoiceclap_attribute:Soft_vs._Harsh	0.322	+0.45	0.306	+0.41	0.160	0.360
178	Sournessvoiceclap_attribute:Sourness	0.210	-1.70	0.167	-1.85	0.706	0.291
179	Submissive vs. Dominantvoiceclap_attribute:Submissive_vs._Dominant	0.191	-1.21	0.180	-1.24	0.623	0.359
180	Teasingvoiceclap_attribute:Teasing	0.078	-1.22	0.113	-1.13	0.540	0.379
181	Thankfulness Gratitudevoiceclap_attribute:Thankfulness_Gratitude	1.433	+0.09	1.069	-0.59	1.384	0.529
182	Triumphvoiceclap_attribute:Triumph	0.423	-0.82	0.403	-0.87	0.716	0.359
183	Valencevoiceclap_attribute:Valence	0.219	+0.36	0.227	+0.37	-0.007	0.635
184	Vulnerable vs. Emotionally Detachedvoiceclap_attribute:Vulnerable_vs._Emotionally_Detached	2.374	+1.32	2.400	+1.37	1.638	0.556
185	Warm vs. Coldvoiceclap_attribute:Warm_vs._Cold	0.169	+0.59	0.183	+0.62	-0.066	0.400
186	durationvoiceclap_attribute:duration	8.889	-0.32	9.780	-0.18	10.914	6.354
187	score background qualityvoiceclap_attribute:score_background_quality	3.525	+0.56	3.583	+0.68	3.245	0.498
188	score content enjoymentvoiceclap_attribute:score_content_enjoyment	4.636	-0.13	4.641	-0.10	4.656	0.147
189	score overall qualityvoiceclap_attribute:score_overall_quality	2.865	+0.56	2.886	+0.61	2.635	0.412
190	score speech qualityvoiceclap_attribute:score_speech_quality	1.958	+0.97	1.964	+1.06	1.891	0.069
191	talking speedvoiceclap_attribute:talking_speed	10.823	+0.48	11.460	+0.65	9.028	3.756

All Orange embedding components

The cosine above is the meaningful vector-level comparison; component values have no standalone semantic label.

Timbre — all 128 vector components

Dimension	Tiny	Base	Orange teacher
0	0.0515	0.0381	0.0730
1	0.1486	0.0774	0.0115
2	0.0069	0.0043	0.0919
3	-0.0562	-0.0598	-0.0908
4	0.1790	0.1426	0.1426
5	-0.0193	-0.0272	0.0336
6	0.0197	0.0485	0.0852
7	-0.0030	0.0065	-0.0468
8	-0.1371	-0.1288	-0.0861
9	-0.0525	-0.0056	0.0284
10	0.0128	-0.0214	0.0083
11	-0.0690	-0.1096	-0.0764
12	-0.0661	-0.0866	-0.0688
13	-0.0751	-0.0881	-0.0660
14	-0.0060	-0.0383	-0.0746
15	0.0101	0.0171	-0.0457
16	-0.0511	-0.0487	0.0550
17	-0.0575	-0.0427	0.0221
18	0.0020	0.0242	-0.0048
19	-0.0599	-0.0674	-0.0847
20	-0.0825	-0.0536	-0.0897
21	-0.0517	-0.0475	-0.0824
22	-0.0800	-0.0927	-0.0842
23	-0.0993	-0.0970	-0.1022
24	-0.0661	-0.0674	-0.0723
25	-0.1002	-0.0878	-0.0787
26	-0.0028	0.0274	0.0533
27	-0.0821	-0.0851	-0.0836
28	-0.1207	-0.1242	-0.0987
29	0.1051	0.1142	0.1418
30	0.2676	0.3387	0.3608
31	-0.0201	-0.0194	-0.0425
32	0.2808	0.2836	0.2764
33	-0.0571	-0.0728	0.0015
34	-0.0948	-0.0521	-0.0645
35	0.1215	0.1073	0.0131
36	-0.0092	0.0257	-0.0068
37	0.0146	0.0151	-0.0474
38	-0.0681	-0.0824	-0.0894
39	-0.0415	-0.0310	-0.0362
40	-0.0739	-0.0778	-0.0864
41	-0.0328	0.0006	0.0471
42	-0.0277	0.0225	0.0098
43	-0.0878	-0.1050	-0.0922
44	-0.0192	0.0219	-0.0052
45	0.0238	0.0498	0.1088
46	0.0575	0.0648	0.1207
47	-0.0542	-0.0805	-0.0906
48	0.0117	-0.0114	-0.0031
49	-0.0850	-0.1081	-0.0905
50	-0.0013	-0.0477	-0.0626
51	-0.0027	0.0143	-0.0178
52	-0.0866	-0.0851	-0.0876
53	-0.0587	-0.0410	-0.0710
54	-0.0361	-0.0303	0.0063
55	-0.1067	-0.1042	-0.0862
56	0.0026	0.0322	-0.0270
57	-0.0862	-0.0540	-0.0983
58	-0.1190	-0.0889	-0.0953
59	-0.0507	-0.0548	-0.0898
60	0.1075	0.0908	-0.0220
61	0.0285	0.0310	0.0173
62	0.0050	0.0041	-0.0410
63	0.0199	0.0164	0.0271
64	0.0462	0.0140	0.1153
65	-0.0503	-0.0443	0.0589
66	0.1437	0.1027	0.0892
67	0.0269	-0.0042	0.0278
68	0.1272	0.1180	0.1803
69	-0.0591	-0.0529	-0.0534
70	-0.0530	-0.0506	-0.0831
71	-0.0110	-0.0024	-0.0246
72	-0.0223	-0.0431	-0.0132
73	0.0413	0.0222	0.0150
74	-0.1305	-0.1058	-0.0979
75	0.1174	0.0469	0.1085
76	0.1913	0.1747	0.1331
77	-0.0969	-0.1127	-0.0818
78	0.0698	0.1525	0.1422
79	-0.0866	-0.0774	-0.0777
80	0.1453	0.0962	0.1231
81	-0.0302	-0.0174	-0.0134
82	-0.0193	0.0253	-0.0242
83	0.0887	0.0736	0.0186
84	-0.1034	-0.1050	-0.0782
85	-0.1014	-0.0828	-0.0728
86	0.0086	-0.0264	-0.0747
87	-0.1084	-0.0989	-0.0243
88	0.1149	0.1096	0.0819
89	0.0837	0.0709	0.0508
90	0.0965	0.0966	0.1566
91	0.1305	0.1632	0.1477
92	-0.0940	-0.0947	-0.0870
93	-0.0841	-0.0786	-0.0875
94	0.0183	0.0947	0.1523
95	0.0649	0.0858	0.0550
96	-0.1305	-0.1081	-0.0837
97	0.1511	0.1456	0.1007
98	-0.1067	-0.1088	-0.0905
99	0.1929	0.1947	0.1683
100	0.1576	0.1441	0.1470
101	-0.0072	-0.0510	0.0157
102	-0.0685	-0.0671	-0.0959
103	-0.1051	-0.1058	-0.0691
104	0.0283	0.0628	0.1653
105	-0.0792	-0.0690	-0.0864
106	-0.0821	-0.1165	-0.0572
107	0.0003	-0.0185	-0.0303
108	0.0883	0.0812	0.1041
109	-0.0681	-0.0575	-0.0879
110	-0.0181	0.0176	0.0425
111	-0.1215	-0.1226	-0.1039
112	-0.0384	-0.0368	0.0184
113	0.0087	0.0456	0.0684
114	-0.0685	-0.0295	-0.0093
115	0.0427	0.0395	0.0770
116	-0.0101	-0.0245	-0.0064
117	-0.0854	-0.0858	-0.0614
118	-0.0562	-0.0659	-0.0121
119	-0.0260	-0.0422	-0.0488
120	0.2348	0.2146	0.0720
121	-0.0525	-0.0410	-0.0622
122	-0.0956	-0.0927	-0.0001
123	0.0093	-0.0705	-0.0097
124	0.0174	0.0282	0.0057
125	-0.0837	-0.0939	-0.0893
126	-0.0616	-0.0870	-0.0772
127	0.0887	0.0858	0.0975

Identity — all 250 vector components

Dimension	Tiny	Base	Orange teacher
0	-0.1053	-0.0909	-0.0552
1	0.0451	0.0563	0.0750
2	-0.0916	-0.0343	-0.0617
3	0.0602	0.0677	0.0437
4	0.0087	-0.0192	-0.0457
5	-0.0784	-0.0727	-0.0525
6	0.0853	0.0540	-0.0344
7	0.0080	0.0732	0.0380
8	0.0260	0.0374	-0.0577
9	-0.0342	-0.0100	-0.0014
10	-0.0529	-0.0146	-0.0527
11	-0.0739	-0.0803	-0.0679
12	-0.0154	-0.0207	-0.0549
13	0.0247	0.0176	-0.0443
14	0.0264	0.0503	0.0449
15	0.1135	0.0073	0.0317
16	0.1277	0.0833	0.1858
17	-0.0465	-0.0525	-0.0603
18	0.0435	0.0092	0.0377
19	-0.0394	0.0029	-0.0797
20	-0.0176	0.0074	-0.0503
21	-0.0269	-0.0213	-0.0465
22	0.0169	0.0117	-0.0272
23	-0.0093	0.0088	-0.0345
24	-0.0147	-0.0366	-0.0428
25	-0.0684	0.0016	0.0413
26	0.0793	0.1030	-0.0245
27	-0.0638	-0.0677	-0.0408
28	0.0188	0.0495	0.1152
29	-0.0251	-0.0520	-0.0483
30	-0.0050	-0.0268	-0.0436
31	-0.1222	-0.0894	-0.0630
32	0.1359	0.0677	0.0987
33	-0.0780	-0.0849	-0.0450
34	0.0670	0.0808	0.0411
35	-0.0492	-0.0285	-0.0646
36	-0.0802	-0.0523	-0.0530
37	-0.0374	-0.0641	-0.0347
38	-0.1277	-0.0869	-0.0696
39	-0.0206	-0.0006	0.0369
40	-0.0518	-0.0692	-0.0581
41	-0.0321	-0.0641	-0.0576
42	-0.0264	-0.0069	-0.0499
43	-0.0074	-0.0104	0.0080
44	-0.0463	-0.0245	-0.0498
45	-0.0524	-0.0475	-0.0576
46	0.0278	0.0467	0.0707
47	0.0467	-0.0111	-0.0550
48	-0.0907	-0.0919	-0.0536
49	-0.0843	-0.0849	-0.0894
50	-0.0169	-0.0371	0.0009
51	-0.0948	-0.0798	-0.0509
52	-0.0716	-0.0520	-0.0073
53	-0.0264	-0.0439	-0.0486
54	0.0258	0.0874	0.0462
55	0.1769	0.1536	0.1379
56	0.0141	0.0140	0.0238
57	0.2407	0.2212	0.1527
58	-0.0524	-0.0477	-0.0482
59	0.0130	0.0356	0.0632
60	0.0752	0.0308	0.0044
61	0.0707	0.1182	0.1632
62	-0.1053	-0.0879	-0.0441
63	-0.0435	-0.0503	-0.0545
64	0.0317	0.0072	-0.0303
65	-0.0812	-0.0970	-0.0612
66	-0.0152	0.0302	-0.0632
67	0.0310	0.0121	-0.0528
68	0.0002	-0.0546	-0.0300
69	0.0499	0.0216	-0.0175
70	-0.0422	-0.0366	-0.0493
71	-0.0177	-0.0251	-0.0526
72	-0.0310	-0.0263	-0.0111
73	0.0766	0.0833	0.1483
74	-0.0880	-0.0818	-0.0542
75	-0.0317	-0.0069	-0.0440
76	0.0638	0.1273	0.0759
77	-0.0333	-0.0465	0.0267
78	0.1053	0.1445	0.1149
79	-0.0825	-0.0798	-0.0537
80	-0.0290	-0.0548	0.0123
81	0.0021	0.0029	0.0242
82	-0.0926	-0.0934	-0.0482
83	-0.0798	-0.0722	-0.0446
84	-0.0037	0.0134	0.0148
85	-0.0182	-0.0019	-0.0536
86	0.0926	0.0692	0.0108
87	-0.0172	-0.0117	0.0175
88	-0.0467	0.0376	0.0167
89	0.0524	0.0304	-0.0485
90	0.0720	0.0578	0.0609
91	0.0145	0.0119	-0.0110
92	-0.0716	-0.0899	-0.0463
93	-0.0048	0.0193	0.0338
94	-0.0054	-0.0129	-0.0615
95	-0.0117	-0.0359	-0.0109
96	-0.0401	-0.0586	-0.0479
97	-0.0397	-0.0508	-0.0521
98	-0.0137	-0.0151	-0.0566
99	-0.0319	-0.0624	-0.0617
100	0.0611	0.0758	0.0084
101	-0.0394	-0.0402	-0.0507
102	-0.0693	-0.0672	-0.0532
103	0.0939	0.0753	0.0084
104	-0.0643	-0.0975	-0.0698
105	-0.0199	-0.0150	0.0201
106	-0.0458	-0.0314	-0.0413
107	-0.0119	-0.0609	-0.0480
108	0.0871	0.0641	-0.0279
109	0.0657	0.0515	0.0554
110	-0.0556	-0.0945	-0.0638
111	0.1040	0.0687	0.0106
112	-0.0362	-0.0298	-0.0433
113	-0.0739	-0.0525	-0.0914
114	0.0238	0.0386	0.1129
115	-0.0527	-0.0412	-0.0380
116	0.0579	0.0813	0.1392
117	0.0223	0.0082	0.0551
118	0.0486	0.0599	0.0795
119	-0.0502	0.0004	0.0071
120	-0.0106	0.0450	0.0538
121	0.0135	0.0326	-0.0084
122	-0.0277	-0.0568	-0.0506
123	-0.0376	-0.0333	-0.0124
124	-0.0588	-0.0707	-0.0534
125	-0.0198	-0.0092	-0.0521
126	0.0775	0.0386	0.0800
127	-0.0388	-0.0336	-0.0551
128	-0.0263	-0.0274	-0.0101
129	-0.0771	-0.0634	-0.0395
130	-0.0821	-0.0940	-0.0538
131	-0.0547	-0.0712	-0.0469
132	0.0229	0.0460	0.0493
133	0.0108	0.0192	-0.0530
134	0.0625	0.0515	0.1266
135	-0.0752	-0.0692	-0.0539
136	0.0012	-0.0343	-0.0574
137	-0.0894	-0.0838	-0.0498
138	0.0088	-0.0356	-0.0473
139	-0.0312	-0.0149	-0.0424
140	-0.0784	-0.0318	0.0039
141	0.1144	0.0808	0.0177
142	-0.0419	-0.0657	-0.0463
143	-0.0026	-0.0117	-0.0220
144	-0.0561	-0.0551	-0.0558
145	-0.0666	-0.0639	-0.0681
146	0.0050	-0.0058	-0.0066
147	-0.0109	0.0049	-0.0012
148	-0.0035	-0.0235	-0.0591
149	-0.0866	-0.0652	-0.0690
150	-0.0220	-0.0139	-0.0527
151	0.0117	-0.0123	-0.0611
152	0.0611	0.0168	-0.0561
153	-0.0005	0.0563	-0.0649
154	-0.0198	0.0087	-0.0522
155	-0.0035	-0.0427	-0.0699
156	-0.0319	-0.0356	-0.0537
157	0.1559	0.1889	0.1256
158	-0.0378	-0.0447	-0.0630
159	-0.0454	-0.0304	-0.0627
160	-0.1044	-0.0950	-0.0509
161	-0.0333	0.0071	-0.0529
162	-0.0584	-0.0904	-0.0622
163	0.0353	0.0667	0.0668
164	0.0060	0.0151	-0.0466
165	0.0351	0.0889	0.1335
166	-0.0022	-0.0302	-0.0623
167	0.1081	0.0727	0.1727
168	-0.0926	-0.0356	-0.0757
169	-0.0179	-0.0662	-0.0611
170	-0.0730	-0.0753	-0.0502
171	0.0862	0.0442	0.0492
172	-0.1094	-0.0798	-0.0621
173	0.1350	0.0990	0.0588
174	-0.0283	-0.0490	-0.0333
175	-0.0848	-0.0515	-0.0887
176	0.0675	0.0354	-0.0456
177	-0.0317	-0.0389	-0.0442
178	0.0866	0.1066	0.0722
179	0.0935	0.1202	0.0336
180	-0.0527	-0.0596	-0.0608
181	-0.0342	-0.0093	0.0073
182	-0.0419	-0.0379	-0.0463
183	0.0013	0.0179	0.0206
184	0.0027	-0.0364	-0.0344
185	0.0581	0.0417	0.0932
186	0.0046	-0.0261	-0.0646
187	0.0429	0.0528	0.0322
188	0.0422	0.0513	0.0214
189	0.0052	0.0778	0.1396
190	0.0515	-0.0100	-0.0311
191	0.0062	0.0366	0.0226
192	-0.0807	-0.0480	0.0069
193	-0.0358	-0.0798	-0.0522
194	0.0388	0.0596	-0.0521
195	0.0072	0.0138	0.0097
196	0.0303	0.0626	-0.0045
197	-0.0426	-0.0157	-0.0750
198	-0.0766	-0.0773	-0.0518
199	-0.0518	-0.0414	0.0381
200	-0.1126	-0.0753	-0.0619
201	0.0693	-0.0095	-0.0505
202	-0.0752	-0.0414	-0.0748
203	0.0017	-0.0333	-0.0321
204	-0.0513	-0.0470	-0.0627
205	-0.0889	-0.0470	-0.0894
206	-0.0515	-0.0174	-0.0552
207	-0.0296	0.0284	0.1013
208	-0.0761	-0.0798	-0.0556
209	0.0029	0.0188	-0.0187
210	-0.0217	-0.0576	-0.0697
211	-0.0472	-0.0331	-0.0412
212	0.0456	0.0399	-0.0212
213	0.1751	0.1435	0.1445
214	0.0802	0.1465	0.0745
215	0.1760	0.1707	0.1527
216	-0.0280	-0.0149	-0.0641
217	0.0807	0.0793	0.1520
218	-0.0698	-0.0604	-0.0280
219	-0.0670	-0.0904	-0.0698
220	-0.0780	-0.1061	-0.0591
221	-0.0147	0.0005	-0.0465
222	0.0055	0.0098	-0.0388
223	0.0015	-0.0384	-0.0430
224	-0.0135	-0.0294	-0.0489
225	0.0559	0.0265	-0.0446
226	0.0962	0.0889	0.0652
227	0.0285	0.0583	0.0837
228	-0.0894	-0.0697	-0.0867
229	0.0219	-0.0045	-0.0009
230	0.0141	0.0586	0.1074
231	0.1030	0.1384	0.0695
232	0.0584	0.1536	0.1298
233	-0.1231	-0.1576	-0.1094
234	0.0495	0.0439	0.0410
235	-0.0693	-0.0402	0.0067
236	-0.0652	-0.0743	-0.0460
237	0.0104	0.0050	-0.0547
238	0.0577	0.0326	-0.0588
239	0.0342	0.0094	0.0058
240	-0.0688	-0.0748	-0.0546
241	0.0024	-0.0284	0.0079
242	0.0100	-0.0407	-0.0789
243	-0.1195	-0.1293	-0.0688
244	0.0342	0.0429	-0.0569
245	-0.0137	-0.0414	-0.0509
246	-0.0406	-0.0778	-0.0434
247	-0.0305	-0.0178	-0.0389
248	-0.0522	-0.0823	-0.0355
249	0.0299	0.0158	0.1168

Source: Emolia / Emilia source archive · SHA-256 bc068846a09df6c2…

e10KoreanEmolia / Emilia

Emolia KO · KO_B00000_S00030_W000205

Natural speech · Original speech · 7.1 s

그 마찰력 없는 움직임, 허공을 부유하고 있는 움직임을 들어줘, 예. WSD의 움직임이.

Tiny Base · values are model estimates, not ground truth

Strongest emotions relative to training

Contemplation

z +1.48 / +0.93raw 0.97 / 0.64

Concentration

z +1.43 / +1.24raw 1.69 / 1.56

Doubt

z +1.03 / +0.71raw 0.48 / 0.33

Confusion

z +0.81 / +0.68raw 0.44 / 0.37

Anger

z +0.18 / +0.39raw 0.12 / 0.24

Contentment

z +0.35 / +0.14raw 0.18 / 0.07

Interest

z +0.25 / +0.17raw 1.82 / 1.74

The center of each bar is the S9 teacher median. Positive z is to the right; negative z is to the left. Ranking uses z, not raw teacher units.

Strongest VoiceNet dimensions relative to training

Authoritative style (S_AUTH)

z +1.85 / +1.92raw 3.01 / 3.09

Mixed resonance (R_MIXD)

z +1.73 / +1.87raw 2.89 / 3.01

Teacher or didactic style (S_TECH)

z +1.61 / +1.62raw 2.62 / 2.63

Formal style (S_FORM)

z +1.23 / +1.35raw 2.45 / 2.58

Oral resonance (R_ORAL)

z +1.32 / +1.34raw 3.16 / 3.18

Throat resonance (R_THRT)

z +1.17 / +0.98raw 3.01 / 2.86

Head resonance (R_HEAD)

z +0.66 / +0.93raw 2.69 / 2.91

All 57 VoiceNet predictions, including raw units, are in the full table below. These seven are ranked by z; the top values may differ from the strongest raw dimensions.

Voice, speed and quality scores in context

Genuineness (0–6)z +0.78 / +0.93raw 3.59 / 3.84

Vocal-burst blend (0–10)z -0.89 / -0.63raw 4.24 / 4.95

Content enjoyment (CE)z +0.34 / +0.22raw 5.14 / 5.02

Production quality (PQ)z -0.21 / -0.14raw 6.86 / 6.92

Speech signal quality, calibratedz -0.10 / -0.11raw 3.44 / 3.43

Background quality, calibratedz +0.63 / +0.67raw 3.97 / 4.01

Overall quality, calibratedz +0.48 / +0.50raw 3.13 / 3.14

P.808 MOS estimatez +0.94 / +0.74raw 3.89 / 3.79

score content enjoymentz -0.21 / -0.28raw 4.44 / 4.42

score overall qualityz +0.67 / +0.67raw 2.99 / 2.99

Background Noisez -0.27 / -0.08raw 0.74 / 0.79

Tempo (TEMP)z +0.65 / +0.77raw 2.89 / 3.03

Arousal (AROU)z -0.06 / -0.12raw 2.29 / 2.22

Valence (VALN)z +0.49 / +0.45raw 2.87 / 2.83

Recording quality (RCQL)z +0.10 / +0.20raw 2.84 / 2.93

Background noise (BKGN)z +0.47 / +0.33raw 3.06 / 2.95

talking speedz +0.67 / +1.12raw 11.53 / 13.22

Characters per second (CPS): 6.89 raw · z -0.57

Orange speaker embedding reconstruction

Cosine against Orange on this same clip (higher means closer to that teacher vector):

Embedding	Tiny	Base
Timbre · 128D	0.827	0.856
Identity · 250D	0.803	0.811

Vocal-burst regions

Tiny

Base

0 s7.1 s

Verified burst intervals are unavailable for this clip.

Tiny: 0 regions, count-head estimate 0.08; Base: 0 regions, count-head estimate 0.02.

Exact predicted start and end times

Model	Region	Start (s)	End (s)	Duration (s)

All 192 score slots · raw and z values

#	Target	Tiny raw	Tiny z	Base raw	Base z	Train median	Train SD
Emotion scores Forty clip-level Empathic Insight emotion teacher outputs. Each row evaluates one named emotion score.
0	Affectionemo_Affection	0.031	+0.04	0.041	+0.06	0.007	0.570
1	Amusementemo_Amusement	-0.027	-0.03	-0.010	-0.01	-0.001	0.885
2	Angeremo_Anger	0.116	+0.18	0.243	+0.39	0.004	0.613
3	Astonishment Surpriseemo_Astonishment_Surprise	0.020	+0.03	0.018	+0.02	0.005	0.572
4	Aweemo_Awe	0.007	+0.02	0.002	+0.00	0.000	0.427
5	Bitternessemo_Bitterness	0.014	+0.00	0.003	-0.02	0.013	0.415
6	Concentrationemo_Concentration	1.692	+1.43	1.555	+1.24	0.634	0.741
7	Confusionemo_Confusion	0.439	+0.81	0.366	+0.68	0.001	0.540
8	Contemplationemo_Contemplation	0.968	+1.48	0.636	+0.93	0.082	0.598
9	Contemptemo_Contempt	0.047	+0.10	0.005	+0.01	-0.000	0.464
10	Contentmentemo_Contentment	0.180	+0.35	0.071	+0.14	0.000	0.514
11	Disappointmentemo_Disappointment	0.019	+0.03	-0.012	-0.02	0.000	0.700
12	Disgustemo_Disgust	0.055	+0.10	0.006	-0.00	0.007	0.489
13	Distressemo_Distress	0.028	+0.03	0.022	+0.03	0.000	0.821
14	Doubtemo_Doubt	0.485	+1.03	0.334	+0.71	0.006	0.466
15	Elationemo_Elation	0.017	+0.01	-0.067	-0.11	0.012	0.728
16	Embarrassmentemo_Embarrassment	0.022	-0.05	0.012	-0.07	0.043	0.430
17	Emotional Numbnessemo_Emotional_Numbness	0.154	+0.16	0.154	+0.16	0.004	0.917
18	Fatigue Exhaustionemo_Fatigue_Exhaustion	0.022	-0.01	0.027	-0.00	0.028	0.539
19	Fearemo_Fear	0.011	-0.01	0.002	-0.02	0.015	0.610
20	Helplessnessemo_Helplessness	0.030	+0.05	-0.009	-0.01	-0.004	0.696
21	Hope Enthusiasm Optimismemo_Hope_Enthusiasm_Optimism	0.080	-0.05	0.053	-0.08	0.117	0.760
22	Impatience and Irritabilityemo_Impatience_and_Irritability	0.079	-0.10	0.248	+0.14	0.149	0.705
23	Infatuationemo_Infatuation	-0.049	-0.06	-0.006	+0.02	-0.015	0.533
24	Interestemo_Interest	1.815	+0.25	1.744	+0.17	1.589	0.907
25	Intoxication Altered States of Consciousnessemo_Intoxication_Altered_States_of_Consciousness	-0.015	+0.02	-0.005	+0.04	-0.025	0.559
26	Jealousy and Envyemo_Jealousy_and_Envy	0.027	-0.07	0.037	-0.05	0.059	0.442
27	Longingemo_Longing	0.144	+0.09	0.058	-0.05	0.087	0.632
28	Malevolence Maliceemo_Malevolence_Malice	0.066	+0.02	0.041	-0.03	0.055	0.534
29	Painemo_Pain	0.017	+0.03	0.021	+0.04	-0.002	0.579
30	Pleasure Ecstasyemo_Pleasure_Ecstasy	-0.025	-0.07	0.030	+0.02	0.017	0.614
31	Prideemo_Pride	-0.019	-0.04	-0.008	-0.02	0.002	0.509
32	Reliefemo_Relief	0.007	-0.04	0.021	-0.02	0.033	0.681
33	Sadnessemo_Sadness	0.029	+0.04	0.017	+0.02	0.000	0.759
34	Sexual Lustemo_Sexual_Lust	-0.008	-0.08	-0.052	-0.17	0.030	0.494
35	Shameemo_Shame	0.002	-0.02	0.010	-0.01	0.013	0.510
36	Sournessemo_Sourness	0.010	+0.03	-0.011	-0.01	-0.005	0.439
37	Teasingemo_Teasing	0.009	+0.02	0.028	+0.05	0.000	0.545
38	Thankfulness Gratitudeemo_Thankfulness_Gratitude	0.045	+0.01	0.042	+0.00	0.041	0.697
39	Triumphemo_Triumph	-0.055	-0.09	-0.019	-0.02	-0.007	0.521
VoiceNet dimensions Fifty-seven VoiceNet voice, delivery, style, and recording dimensions. Codes are expanded in the target column.
40	Perceived voice age (AGEV)vn_AGEV_reg	2.419	-0.46	2.344	-0.52	2.984	1.238
41	Arousal (AROU)vn_AROU_reg	2.289	-0.06	2.217	-0.12	2.359	1.147
42	Arousal shift (ARSH)vn_ARSH_reg	2.348	-0.27	2.529	-0.06	2.580	0.867
43	Vocal attack (ATCK)vn_ATCK_reg	1.978	-0.14	1.974	-0.15	2.162	1.295
44	Background noise (BKGN)vn_BKGN_reg	3.064	+0.47	2.953	+0.33	2.703	0.761
45	Brightness (BRGT)vn_BRGT_reg	1.943	-0.06	2.092	+0.12	1.991	0.813
46	Speech chunking (CHNK)vn_CHNK_reg	2.827	+0.79	2.890	+0.84	1.847	1.239
47	Articulation clarity (CLRT)vn_CLRT_reg	1.851	-0.18	1.857	-0.17	2.018	0.945
48	Cognitive load (COGL)vn_COGL_reg	2.754	+0.62	2.559	+0.44	2.094	1.061
49	Dynamic arc (DARC)vn_DARC_reg	1.575	-0.03	1.515	-0.07	1.615	1.380
50	Disfluency (DFLU)vn_DFLU_reg	2.868	+0.32	3.175	+0.58	2.488	1.184
51	Emphasis (EMPH)vn_EMPH_reg	2.991	+0.25	2.994	+0.25	2.607	1.524
52	Esthetics (ESTH)vn_ESTH_reg	2.513	+0.14	2.562	+0.20	2.402	0.782
53	Content appropriateness (EXPL)vn_EXPL_reg	0.051	-0.11	0.022	-0.20	0.086	0.322
54	Focus (FOCS)vn_FOCS_reg	1.786	-0.51	1.881	-0.42	2.344	1.102
55	Fullness (FULL)vn_FULL_reg	2.307	+0.59	2.424	+0.73	1.778	0.889
56	Perceived gender (GEND)vn_GEND_reg	4.167	+0.07	4.273	+0.14	4.055	1.588
57	Harmonicity (HARM)vn_HARM_reg	2.498	+0.02	2.454	-0.03	2.480	0.836
58	Metallic character (METL)vn_METL_reg	2.413	+0.83	2.275	+0.68	1.621	0.958
59	Pitch range (RANG)vn_RANG_reg	2.623	-0.32	2.649	-0.29	2.914	0.897
60	Recording quality (RCQL)vn_RCQL_reg	2.841	+0.10	2.927	+0.20	2.754	0.888
61	Vocal register (REGS)vn_REGS_reg	0.476	-0.57	0.544	-0.52	1.198	1.268
62	Respiration (RESP)vn_RESP_reg	2.040	-0.61	1.961	-0.68	2.680	1.056
63	Roughness (ROUG)vn_ROUG_reg	2.379	+0.39	2.353	+0.36	2.033	0.887
64	Chest resonance (R_CHST)vn_R_CHST_reg	2.831	+0.82	2.847	+0.84	2.135	0.844
65	Head resonance (R_HEAD)vn_R_HEAD_reg	2.687	+0.66	2.909	+0.93	2.148	0.822
66	Mask resonance (R_MASK)vn_R_MASK_reg	2.189	+0.28	2.331	+0.42	1.908	1.005
67	Mixed resonance (R_MIXD)vn_R_MIXD_reg	2.893	+1.73	3.011	+1.87	1.436	0.841
68	Nasal resonance (R_NASL)vn_R_NASL_reg	2.791	-0.00	2.805	+0.01	2.791	1.047
69	Oral resonance (R_ORAL)vn_R_ORAL_reg	3.161	+1.32	3.178	+1.34	2.184	0.741
70	Throat resonance (R_THRT)vn_R_THRT_reg	3.012	+1.17	2.861	+0.98	2.070	0.803
71	Smoothness (SMTH)vn_SMTH_reg	2.727	+0.53	2.744	+0.55	2.143	1.093
72	Stance (STNC)vn_STNC_reg	2.690	+0.05	2.699	+0.06	2.633	1.137
73	Speech structure (STRU)vn_STRU_reg	2.969	+0.87	2.823	+0.72	2.137	0.958
74	ASMR style (S_ASMR)vn_S_ASMR_reg	2.185	+0.58	1.856	+0.34	1.370	1.411
75	Authoritative style (S_AUTH)vn_S_AUTH_reg	3.013	+1.85	3.094	+1.92	1.088	1.043
76	Cartoonish style (S_CART)vn_S_CART_reg	0.899	-0.47	0.925	-0.45	1.560	1.401
77	Casual style (S_CASU)vn_S_CASU_reg	3.524	-0.21	3.481	-0.24	3.793	1.278
78	Conversational style (S_CONV)vn_S_CONV_reg	3.380	+0.60	3.400	+0.61	2.594	1.318
79	Dramatic style (S_DRAM)vn_S_DRAM_reg	1.680	-0.91	1.747	-0.85	2.721	1.148
80	Formal style (S_FORM)vn_S_FORM_reg	2.451	+1.23	2.577	+1.35	1.195	1.021
81	Monologue style (S_MONO)vn_S_MONO_reg	3.265	+0.34	3.412	+0.46	2.824	1.284
82	Narrator style (S_NARR)vn_S_NARR_reg	1.737	+0.30	1.623	+0.22	1.307	1.446
83	Newsreader style (S_NEWS)vn_S_NEWS_reg	0.467	+0.10	0.377	-0.05	0.408	0.568
84	Playful style (S_PLAY)vn_S_PLAY_reg	2.434	+0.06	2.606	+0.19	2.352	1.315
85	Ranting or angry style (S_RANT)vn_S_RANT_reg	-0.141	-1.05	-0.091	-1.01	1.213	1.289
86	Storytelling style (S_STRY)vn_S_STRY_reg	2.174	-0.22	2.258	-0.16	2.480	1.366
87	Teacher or didactic style (S_TECH)vn_S_TECH_reg	2.622	+1.61	2.632	+1.62	0.646	1.227
88	Whispered talking style (S_WHIS)vn_S_WHIS_reg	2.238	+0.40	2.137	+0.33	1.597	1.618
89	Tempo (TEMP)vn_TEMP_reg	2.894	+0.65	3.034	+0.77	2.117	1.190
90	Tension (TENS)vn_TENS_reg	1.496	-0.07	1.377	-0.21	1.559	0.852
91	Valence (VALN)vn_VALN_reg	2.870	+0.49	2.835	+0.45	2.328	1.118
92	Valence shift (VALS)vn_VALS_reg	3.304	+0.73	3.210	+0.64	2.518	1.079
93	Velocity flux (VFLX)vn_VFLX_reg	2.290	+0.03	2.451	+0.16	2.256	1.208
94	Volatility (VOLT)vn_VOLT_reg	1.938	-0.73	1.908	-0.77	2.586	0.886
95	Vulnerability (VULN)vn_VULN_reg	1.734	-0.93	1.881	-0.78	2.648	0.984
96	Warmth (WARM)vn_WARM_reg	2.600	+0.02	2.637	+0.06	2.578	0.909
Genuineness, blend, and legacy quality Genuineness and vocal-burst blend are predicted. R_quality has Ladder training labels but no valid P3 test labels.
97	Genuineness (0–6)genuineness_0_6	3.594	+0.78	3.836	+0.93	2.332	1.621
98	Vocal-burst blend (0–10)blend_0_10	4.245	-0.89	4.945	-0.63	6.676	2.738
99	Legacy R_quality (no P3 test labels)R_quality	1.036	-0.17	1.143	+0.14	1.095	0.338
Empathic Insight Plus extra scores Nineteen additional clip-level teacher scores, including background noise and content enjoyment.
100	Ageeiv_extra:Age	3.331	+0.27	3.301	+0.17	3.250	0.293
101	Arousaleiv_extra:Arousal	0.983	-0.70	1.080	-0.48	1.289	0.435
102	Authenticityeiv_extra:Authenticity	2.664	-0.02	2.599	-0.44	2.667	0.153
103	Background Noiseeiv_extra:Background_Noise	0.737	-0.27	0.787	-0.08	0.808	0.264
104	Confident vs. Hesitanteiv_extra:Confident_vs._Hesitant	1.378	+1.12	1.389	+1.16	1.040	0.303
105	Gendereiv_extra:Gender	-0.904	-0.28	-0.911	-0.29	-0.621	0.999
106	High-Pitched vs. Low-Pitchedeiv_extra:High-Pitched_vs._Low-Pitched	1.877	+0.20	1.792	-0.14	1.827	0.250
107	Monotone vs. Expressiveeiv_extra:Monotone_vs._Expressive	1.661	-0.42	1.647	-0.45	1.859	0.470
108	Recording Qualityeiv_extra:Recording_Quality	2.071	-0.22	1.989	-0.47	2.144	0.332
109	Serious vs. Humorouseiv_extra:Serious_vs._Humorous	1.129	+0.59	1.148	+0.64	0.929	0.340
110	Soft vs. Harsheiv_extra:Soft_vs._Harsh	0.184	-0.30	0.090	-0.60	0.281	0.320
111	Submissive vs. Dominanteiv_extra:Submissive_vs._Dominant	0.390	+0.04	0.261	-0.35	0.376	0.324
112	Valenceeiv_extra:Valence	0.013	+0.02	0.019	+0.04	0.005	0.380
113	Vulnerable vs. Emotionally Detachedeiv_extra:Vulnerable_vs._Emotionally_Detached	1.943	+0.52	1.970	+0.58	1.715	0.437
114	Warm vs. Coldeiv_extra:Warm_vs._Cold	0.064	+0.04	0.129	+0.26	0.051	0.300
115	score background qualityeiv_extra:score_background_quality	3.645	+0.50	3.708	+0.59	3.301	0.693
116	score content enjoymenteiv_extra:score_content_enjoyment	4.445	-0.21	4.421	-0.28	4.507	0.303
117	score overall qualityeiv_extra:score_overall_quality	2.992	+0.67	2.992	+0.67	2.652	0.507
118	score speech qualityeiv_extra:score_speech_quality	1.890	+0.56	1.915	+0.73	1.808	0.146
Meta AudioBox Aesthetics Four AudioBox aesthetic teacher outputs. Expansions follow the official Meta model card.
119	Content enjoyment (CE)audiobox:CE	5.141	+0.34	5.024	+0.22	4.799	1.018
120	Content usefulness (CU)audiobox:CU	5.673	+0.02	5.720	+0.07	5.649	1.001
121	Production complexity (PC)audiobox:PC	1.751	-0.36	1.852	-0.30	2.331	1.617
122	Production quality (PQ)audiobox:PQ	6.861	-0.21	6.923	-0.14	7.044	0.879
Microsoft DNSMOS Seven DNSMOS teacher outputs: raw and calibrated SIG/BAK/OVRL estimates plus P.808 MOS.
123	Speech signal quality, rawdnsmos:SIG_raw	3.828	-0.11	3.815	-0.13	3.900	0.669
124	Background quality, rawdnsmos:BAK_raw	4.109	+0.80	4.166	+0.85	3.211	1.124
125	Overall quality, rawdnsmos:OVRL_raw	3.519	+0.53	3.545	+0.57	3.085	0.812
126	Speech signal quality, calibrateddnsmos:SIG	3.439	-0.10	3.435	-0.11	3.488	0.501
127	Background quality, calibrateddnsmos:BAK	3.974	+0.63	4.014	+0.67	3.389	0.928
128	Overall quality, calibrateddnsmos:OVRL	3.129	+0.48	3.143	+0.50	2.840	0.606
129	P.808 MOS estimatednsmos:P808_MOS	3.888	+0.94	3.787	+0.74	3.421	0.496
Vocal-burst count The regression target is log(1 + count). A separate table also reports count error after inverse transformation.
130	Vocal-burst count, log(1 + count)burst_count_log1p	0.078	+0.12	0.018	+0.03	0.000	0.647
VoiceCLAP attributes Sixty-one individual VoiceCLAP attribute teacher scores. The raw 768D VoiceCLAP embedding is stored in sidecars but is not a model output.
131	Affectionvoiceclap_attribute:Affection	0.992	+0.08	0.801	-0.26	0.947	0.554
132	Agevoiceclap_attribute:Age	3.157	-0.13	3.233	+0.01	3.229	0.547
133	Amusementvoiceclap_attribute:Amusement	0.115	-0.49	0.146	-0.43	0.392	0.572
134	Angervoiceclap_attribute:Anger	0.315	-1.34	0.375	-1.22	0.992	0.506
135	Arousalvoiceclap_attribute:Arousal	0.997	-0.68	1.080	-0.55	1.420	0.622
136	Astonishment Surprisevoiceclap_attribute:Astonishment_Surprise	0.307	-0.42	0.451	-0.12	0.509	0.479
137	Authenticityvoiceclap_attribute:Authenticity	2.687	-0.50	2.736	-0.21	2.770	0.167
138	Awevoiceclap_attribute:Awe	0.304	-0.91	0.396	-0.55	0.539	0.259
139	Background Noisevoiceclap_attribute:Background_Noise	0.429	-0.52	0.417	-0.57	0.567	0.264
140	Bitternessvoiceclap_attribute:Bitterness	0.186	-1.72	0.227	-1.55	0.592	0.236
141	Concentrationvoiceclap_attribute:Concentration	1.533	+0.60	1.610	+0.75	1.214	0.531
142	Confident vs. Hesitantvoiceclap_attribute:Confident_vs._Hesitant	1.507	+0.94	1.511	+0.94	1.069	0.468
143	Confusionvoiceclap_attribute:Confusion	1.017	+1.12	0.989	+1.04	0.643	0.334
144	Contemplationvoiceclap_attribute:Contemplation	1.142	+0.89	1.041	+0.64	0.780	0.406
145	Contemptvoiceclap_attribute:Contempt	0.160	-1.62	0.290	-1.24	0.709	0.339
146	Contentmentvoiceclap_attribute:Contentment	0.467	-0.39	0.287	-0.98	0.588	0.307
147	Disappointmentvoiceclap_attribute:Disappointment	0.536	-0.77	0.523	-0.81	0.760	0.291
148	Disgustvoiceclap_attribute:Disgust	0.242	-1.85	0.308	-1.53	0.625	0.207
149	Distressvoiceclap_attribute:Distress	0.582	-0.99	0.533	-1.13	0.927	0.350
150	Doubtvoiceclap_attribute:Doubt	0.637	+0.54	0.640	+0.56	0.535	0.188
151	Elationvoiceclap_attribute:Elation	0.283	-0.64	0.322	-0.55	0.539	0.397
152	Embarrassmentvoiceclap_attribute:Embarrassment	0.257	-0.16	0.311	+0.01	0.307	0.314
153	Emotional Numbnessvoiceclap_attribute:Emotional_Numbness	0.729	+0.25	0.732	+0.26	0.664	0.266
154	Fatigue Exhaustionvoiceclap_attribute:Fatigue_Exhaustion	0.226	-0.90	0.189	-1.05	0.462	0.261
155	Fearvoiceclap_attribute:Fear	0.414	-0.96	0.327	-1.37	0.618	0.212
156	Gendervoiceclap_attribute:Gender	-0.673	-0.52	-0.704	-0.55	-0.151	1.005
157	Helplessnessvoiceclap_attribute:Helplessness	0.614	-0.16	0.559	-0.37	0.658	0.268
158	High-Pitched vs. Low-Pitchedvoiceclap_attribute:High-Pitched_vs._Low-Pitched	1.761	-0.21	1.822	-0.05	1.840	0.375
159	Hope Enthusiasm Optimismvoiceclap_attribute:Hope_Enthusiasm_Optimism	0.513	-0.48	0.462	-0.61	0.705	0.396
160	Impatience and Irritabilityvoiceclap_attribute:Impatience_and_Irritability	0.413	-1.18	0.472	-1.07	1.052	0.541
161	Infatuationvoiceclap_attribute:Infatuation	0.433	-0.53	0.398	-0.63	0.608	0.332
162	Interestvoiceclap_attribute:Interest	1.665	+0.15	1.735	+0.31	1.598	0.440
163	Intoxication Altered States of Consciousnessvoiceclap_attribute:Intoxication_Altered_States_of_Consciousness	0.175	-0.71	0.089	-0.89	0.502	0.463
164	Jealousy & Envyvoiceclap_attribute:Jealousy_&_Envy	0.329	-0.79	0.264	-1.06	0.523	0.245
165	Longingvoiceclap_attribute:Longing	0.520	-0.08	0.472	-0.30	0.538	0.220
166	Malevolence Malicevoiceclap_attribute:Malevolence_Malice	0.303	-1.53	0.352	-1.39	0.833	0.346
167	Monotone vs. Expressivevoiceclap_attribute:Monotone_vs._Expressive	1.350	-0.72	1.425	-0.59	1.775	0.594
168	Painvoiceclap_attribute:Pain	0.158	-1.02	0.145	-1.08	0.381	0.218
169	Pleasure Ecstasyvoiceclap_attribute:Pleasure_Ecstasy	0.196	-1.02	0.206	-0.99	0.503	0.301
170	Pridevoiceclap_attribute:Pride	0.500	-0.80	0.389	-1.12	0.780	0.349
171	Recording Qualityvoiceclap_attribute:Recording_Quality	2.246	-0.20	2.277	-0.11	2.313	0.328
172	Reliefvoiceclap_attribute:Relief	0.595	-1.04	0.498	-1.27	1.025	0.415
173	Sadnessvoiceclap_attribute:Sadness	0.530	-0.71	0.575	-0.56	0.752	0.313
174	Serious vs. Humorousvoiceclap_attribute:Serious_vs._Humorous	0.798	-0.01	0.869	+0.11	0.803	0.568
175	Sexual Lustvoiceclap_attribute:Sexual_Lust	0.157	-1.14	0.196	-1.05	0.635	0.419
176	Shamevoiceclap_attribute:Shame	0.472	-0.19	0.431	-0.34	0.526	0.283
177	Soft vs. Harshvoiceclap_attribute:Soft_vs._Harsh	0.297	+0.38	0.258	+0.27	0.160	0.360
178	Sournessvoiceclap_attribute:Sourness	0.342	-1.25	0.326	-1.31	0.706	0.291
179	Submissive vs. Dominantvoiceclap_attribute:Submissive_vs._Dominant	0.244	-1.06	0.258	-1.02	0.623	0.359
180	Teasingvoiceclap_attribute:Teasing	0.146	-1.04	0.202	-0.89	0.540	0.379
181	Thankfulness Gratitudevoiceclap_attribute:Thankfulness_Gratitude	1.371	-0.02	1.044	-0.64	1.384	0.529
182	Triumphvoiceclap_attribute:Triumph	0.406	-0.86	0.417	-0.83	0.716	0.359
183	Valencevoiceclap_attribute:Valence	0.074	+0.13	0.068	+0.12	-0.007	0.635
184	Vulnerable vs. Emotionally Detachedvoiceclap_attribute:Vulnerable_vs._Emotionally_Detached	2.248	+1.10	2.213	+1.03	1.638	0.556
185	Warm vs. Coldvoiceclap_attribute:Warm_vs._Cold	0.120	+0.47	0.096	+0.41	-0.066	0.400
186	durationvoiceclap_attribute:duration	7.330	-0.56	7.454	-0.54	10.914	6.354
187	score background qualityvoiceclap_attribute:score_background_quality	3.569	+0.65	3.550	+0.61	3.245	0.498
188	score content enjoymentvoiceclap_attribute:score_content_enjoyment	4.635	-0.14	4.636	-0.13	4.656	0.147
189	score overall qualityvoiceclap_attribute:score_overall_quality	2.832	+0.48	2.828	+0.47	2.635	0.412
190	score speech qualityvoiceclap_attribute:score_speech_quality	1.999	+1.56	1.994	+1.48	1.891	0.069
191	talking speedvoiceclap_attribute:talking_speed	11.534	+0.67	13.219	+1.12	9.028	3.756

All Orange embedding components

The cosine above is the meaningful vector-level comparison; component values have no standalone semantic label.

Timbre — all 128 vector components

Dimension	Tiny	Base	Orange teacher
0	0.0484	0.0711	0.0814
1	0.0520	0.0638	-0.0666
2	0.0415	0.0132	0.0716
3	-0.0747	-0.0450	-0.0939
4	0.1684	0.1530	0.1570
5	-0.0064	0.0130	0.0795
6	0.0264	-0.0063	0.0558
7	-0.0455	-0.0551	-0.0561
8	-0.1214	-0.1653	-0.1200
9	-0.1077	-0.0634	0.0202
10	-0.0292	-0.0703	-0.0136
11	-0.0812	-0.1102	-0.0932
12	-0.1055	-0.1131	-0.0684
13	-0.0652	-0.0798	-0.0379
14	0.0093	0.0209	-0.0444
15	-0.0298	0.0096	-0.0649
16	-0.0561	-0.0819	0.0305
17	-0.0618	-0.0131	0.0579
18	-0.0732	0.0158	-0.0187
19	-0.0683	-0.0787	-0.0876
20	-0.0842	-0.0740	-0.0927
21	-0.0941	-0.0721	-0.0852
22	-0.0415	-0.0754	-0.0871
23	-0.0914	-0.1095	-0.1096
24	-0.0336	-0.0276	-0.0748
25	-0.0736	-0.0750	-0.0814
26	-0.0142	0.0337	0.0858
27	-0.0789	-0.0765	-0.0864
28	-0.1032	-0.1240	-0.1021
29	0.0986	0.1233	0.1525
30	0.1927	0.2973	0.3103
31	-0.0493	-0.0299	-0.0441
32	0.3444	0.2741	0.2817
33	-0.0929	-0.0758	0.0213
34	-0.0596	-0.0234	0.0117
35	0.0196	0.0682	0.0053
36	0.0427	0.0711	0.0346
37	-0.0486	-0.0281	-0.0783
38	-0.0907	-0.0779	-0.0925
39	-0.0055	-0.0036	-0.0334
40	-0.0880	-0.0696	-0.0893
41	-0.0486	0.0071	-0.0107
42	0.0467	0.0239	0.0349
43	-0.0634	-0.0885	-0.0953
44	-0.0660	-0.0254	-0.0431
45	0.0546	0.0696	0.1058
46	0.0622	0.0243	0.1065
47	-0.0873	-0.0924	-0.0936
48	-0.0026	0.0076	-0.0023
49	-0.0283	-0.0620	-0.0936
50	-0.0311	-0.0642	-0.0329
51	0.0645	-0.0008	-0.0374
52	-0.0812	-0.0754	-0.1052
53	-0.0793	-0.0678	-0.0944
54	-0.0706	-0.0290	0.0084
55	-0.0785	-0.0921	-0.0891
56	-0.0736	-0.0591	-0.0878
57	-0.0971	-0.0743	-0.1016
58	-0.1320	-0.1088	-0.0985
59	-0.0759	-0.0779	-0.0929
60	0.1221	0.1457	-0.0080
61	-0.0127	-0.0381	-0.0688
62	0.0907	0.0653	-0.0277
63	-0.0377	-0.0022	-0.0092
64	0.0410	0.0214	0.1102
65	-0.0237	-0.0373	0.0340
66	0.1358	0.1109	0.0900
67	0.0952	0.0500	0.0986
68	0.0812	0.0776	0.1449
69	-0.0569	-0.0761	-0.0848
70	-0.0444	-0.0053	-0.0259
71	-0.0448	-0.0468	-0.0377
72	0.0230	0.0180	0.0092
73	0.0016	-0.0301	-0.0394
74	-0.1146	-0.1037	-0.1012
75	0.1115	0.1080	0.1431
76	0.1290	0.1472	0.1425
77	-0.0774	-0.0866	-0.0705
78	0.0907	0.1218	0.1447
79	-0.0497	-0.0750	-0.0803
80	0.1813	0.1617	0.1725
81	-0.0252	-0.0823	-0.0628
82	-0.0396	-0.0054	-0.0236
83	0.0690	0.0464	-0.0050
84	-0.0964	-0.1066	-0.0974
85	-0.1009	-0.1022	-0.0872
86	-0.1032	-0.0877	-0.0940
87	-0.0713	-0.1066	-0.0098
88	0.0630	0.0627	0.0251
89	0.0126	0.0479	0.0657
90	0.1586	0.1762	0.1401
91	-0.0360	-0.0079	0.0895
92	-0.0431	-0.0772	-0.0899
93	-0.0971	-0.0703	-0.0905
94	0.0933	0.1225	0.1349
95	0.1199	0.1102	0.0217
96	-0.1138	-0.1073	-0.0623
97	0.1889	0.2074	0.0920
98	-0.0918	-0.1182	-0.0936
99	0.1540	0.1269	0.1025
100	0.1973	0.1443	0.1252
101	-0.0470	-0.0624	0.0290
102	-0.1085	-0.0852	-0.0991
103	-0.0755	-0.0895	-0.0544
104	0.0709	0.0595	0.1362
105	-0.0835	-0.1001	-0.0893
106	-0.0690	-0.0914	-0.0247
107	-0.0429	-0.0319	-0.0206
108	0.0876	0.0714	0.1298
109	-0.0804	-0.0558	-0.0908
110	0.0489	0.0442	0.0772
111	-0.1085	-0.1131	-0.1074
112	0.0217	0.0232	0.0398
113	-0.0554	0.0101	0.0297
114	-0.0694	-0.0645	0.0158
115	0.0317	0.0489	0.0519
116	-0.0182	-0.0247	-0.0794
117	-0.0903	-0.0885	-0.0164
118	-0.0994	-0.1059	-0.0696
119	-0.0812	-0.0682	-0.0844
120	0.1662	0.1472	0.0792
121	-0.0092	-0.0761	-0.0939
122	-0.0899	-0.0874	-0.0047
123	0.0229	0.0170	0.0215
124	-0.0298	-0.0008	-0.0406
125	-0.0721	-0.0544	-0.0923
126	-0.0804	-0.0852	-0.0798
127	0.0808	0.0943	0.0632

Identity — all 250 vector components

Dimension	Tiny	Base	Orange teacher
0	-0.0931	-0.0912	-0.0576
1	0.0410	0.0221	0.1057
2	-0.0656	-0.0485	-0.0511
3	0.0674	0.0605	0.0527
4	-0.0132	-0.0131	-0.0374
5	-0.0686	-0.0794	-0.0547
6	0.0626	0.0370	-0.0312
7	0.0236	0.0275	0.0381
8	0.0059	0.0316	-0.0769
9	-0.0182	-0.0456	-0.0095
10	-0.0230	-0.0188	-0.0550
11	-0.0543	-0.0781	-0.0709
12	-0.0704	-0.0539	-0.0573
13	-0.0093	-0.0059	-0.0462
14	-0.0045	0.0032	-0.0161
15	0.0450	0.0183	0.0766
16	0.1733	0.1788	0.1967
17	-0.0729	-0.1097	-0.0629
18	0.0174	0.0023	0.0453
19	-0.0138	0.0086	-0.0495
20	-0.0181	0.0015	-0.0524
21	-0.0510	-0.0309	-0.0486
22	0.0233	-0.0221	-0.0024
23	-0.0262	0.0296	-0.0078
24	-0.0639	-0.0456	-0.0447
25	-0.0087	-0.0126	0.0174
26	0.0811	0.0831	-0.0538
27	-0.0500	-0.0636	-0.0426
28	0.0083	0.0062	0.0534
29	-0.0498	-0.0627	-0.0504
30	-0.0281	-0.0187	-0.0358
31	-0.0716	-0.0767	-0.0658
32	0.1990	0.1923	0.1148
33	-0.0300	-0.0849	-0.0470
34	0.0159	0.0429	0.0022
35	-0.0403	-0.0332	-0.0344
36	-0.1000	-0.0831	-0.0554
37	-0.0442	-0.0659	-0.0362
38	-0.0974	-0.0727	-0.0727
39	-0.0239	-0.0063	-0.0245
40	-0.0622	-0.0641	-0.0607
41	-0.0012	-0.0325	-0.0602
42	-0.0315	-0.0499	-0.0521
43	0.0631	0.0605	0.0327
44	-0.0420	-0.0404	-0.0256
45	-0.0776	-0.0557	-0.0601
46	0.0362	0.0330	0.1099
47	-0.0020	-0.0090	-0.0267
48	-0.0789	-0.0849	-0.0559
49	-0.0798	-0.0912	-0.0932
50	-0.0222	-0.0467	-0.0074
51	-0.0678	-0.1052	-0.0531
52	-0.0751	-0.0591	0.0034
53	-0.0373	-0.0320	-0.0507
54	0.0579	0.1201	0.0883
55	0.1141	0.1363	0.0820
56	-0.0480	-0.0246	-0.0714
57	0.1948	0.2122	0.1569
58	-0.0147	-0.0111	-0.0503
59	-0.0010	0.0406	0.0483
60	0.0420	0.0343	-0.0349
61	0.1450	0.1327	0.1548
62	-0.1201	-0.1020	-0.0460
63	-0.0252	-0.0458	-0.0569
64	0.0543	0.0281	0.0149
65	-0.0918	-0.1101	-0.0639
66	-0.0643	-0.0237	-0.0660
67	0.0250	0.0167	-0.0551
68	-0.0161	-0.0618	-0.0229
69	-0.0326	-0.0388	-0.0399
70	-0.0401	-0.0623	-0.0488
71	-0.0609	-0.0609	-0.0549
72	-0.0305	-0.0386	-0.0341
73	0.1042	0.1034	0.1360
74	-0.0867	-0.0794	-0.0565
75	-0.0772	-0.0517	-0.0762
76	0.0776	0.1038	0.0567
77	0.0051	0.0138	0.0700
78	0.1270	0.1110	0.0441
79	-0.0875	-0.0790	-0.0560
80	0.0405	0.0289	0.0604
81	-0.0014	0.0095	0.0134
82	-0.0982	-0.1043	-0.0503
83	-0.0631	-0.0664	-0.0465
84	-0.0245	-0.0225	-0.0035
85	-0.0418	-0.0200	-0.0559
86	0.0952	0.0925	0.1085
87	-0.0144	-0.0488	-0.0388
88	0.0343	0.0300	-0.0080
89	-0.0609	-0.0071	-0.0506
90	0.0128	0.0438	0.0216
91	-0.0386	-0.0077	-0.0043
92	-0.0772	-0.0989	-0.0483
93	0.0175	0.0418	0.0587
94	-0.0746	-0.0641	-0.0905
95	-0.0725	-0.0481	-0.0584
96	-0.0468	-0.0521	-0.0500
97	0.0382	0.0072	0.0054
98	-0.0145	-0.0172	-0.0567
99	-0.0365	-0.0467	-0.0443
100	0.1072	0.1038	0.0427
101	-0.0922	-0.0591	-0.0529
102	-0.0057	-0.0220	0.0002
103	0.0041	0.0288	-0.0513
104	-0.0768	-0.0790	-0.0729
105	0.0047	-0.0048	0.0033
106	-0.0125	-0.0018	-0.0431
107	-0.0358	-0.0357	-0.0501
108	0.0281	0.0359	-0.0070
109	0.0871	0.0542	0.0699
110	-0.0480	-0.0133	-0.0666
111	0.0052	0.0244	-0.0052
112	-0.0253	-0.0393	-0.0451
113	-0.0824	-0.0754	-0.0953
114	-0.0073	0.0104	0.0392
115	-0.0408	-0.0219	-0.0396
116	0.0768	0.0971	0.0956
117	-0.0236	-0.0221	0.0185
118	0.0224	0.0641	0.0761
119	-0.0423	-0.0451	-0.0115
120	0.0087	0.0124	0.0583
121	-0.0515	-0.0318	-0.0602
122	-0.0643	-0.0894	-0.0528
123	0.0186	-0.0056	-0.0031
124	-0.0609	-0.0458	-0.0558
125	-0.0375	-0.0010	-0.0544
126	0.1081	0.0975	0.1181
127	-0.0510	-0.0600	-0.0575
128	-0.0472	-0.0447	-0.0696
129	-0.0828	-0.0695	-0.0593
130	-0.0862	-0.0858	-0.0562
131	-0.0541	-0.0524	-0.0489
132	0.0181	0.0506	0.0444
133	-0.0016	0.0012	-0.0553
134	0.0081	-0.0013	0.1179
135	-0.0158	-0.0533	-0.0563
136	0.0129	-0.0519	-0.0599
137	-0.1133	-0.0822	-0.0519
138	-0.0332	-0.0363	-0.0493
139	-0.0313	-0.0121	-0.0509
140	-0.0298	-0.0418	-0.0112
141	0.0558	0.0916	0.0977
142	-0.0440	-0.0485	-0.0483
143	-0.0476	-0.0108	-0.0260
144	-0.0867	-0.0740	-0.0583
145	-0.0652	-0.0695	-0.0710
146	0.0128	-0.0152	0.0240
147	0.0513	0.0269	0.0826
148	-0.0487	-0.0038	-0.0617
149	-0.0918	-0.0817	-0.0720
150	-0.0257	-0.0393	-0.0550
151	-0.0547	-0.0311	-0.0456
152	0.0746	-0.0104	-0.0141
153	0.0013	0.0184	-0.0326
154	-0.0579	-0.0267	-0.0545
155	-0.0588	-0.0488	-0.0729
156	-0.0538	-0.0316	-0.0560
157	0.1227	0.1381	0.1053
158	-0.0001	-0.0096	-0.0696
159	-0.0609	-0.0636	-0.0655
160	-0.0939	-0.1065	-0.0531
161	-0.0324	-0.0571	-0.0497
162	-0.0618	-0.0772	-0.0649
163	-0.0129	-0.0289	0.0228
164	0.0082	-0.0073	-0.0491
165	0.0815	0.0677	0.0978
166	-0.0307	-0.0257	-0.0651
167	0.0132	0.0288	0.1406
168	-0.0871	-0.0772	-0.0790
169	-0.0704	-0.0438	-0.0638
170	-0.0849	-0.0957	-0.0523
171	0.1647	0.0803	0.0548
172	-0.0871	-0.0925	-0.0648
173	0.0970	0.0889	0.0517
174	-0.0105	-0.0204	-0.0473
175	-0.0871	-0.0740	-0.0762
176	-0.0100	-0.0090	-0.0475
177	-0.0367	-0.0429	-0.0461
178	0.0909	0.0395	0.0400
179	0.0414	0.0673	-0.0170
180	-0.0789	-0.0952	-0.0618
181	-0.0423	-0.0510	-0.0420
182	-0.0035	-0.0314	-0.0483
183	-0.0144	0.0258	0.0224
184	-0.0571	-0.0609	-0.0568
185	0.0140	0.0275	0.0914
186	0.0091	-0.0032	-0.0507
187	-0.0172	0.0137	0.0330
188	0.0285	0.0092	0.0106
189	0.0538	0.0510	0.0941
190	0.0251	-0.0262	-0.0169
191	-0.0506	-0.0485	-0.0518
192	-0.0751	-0.0524	-0.0425
193	0.1107	0.0209	0.0661
194	0.0862	0.0578	-0.0053
195	0.0909	0.0490	0.1082
196	0.0234	0.0225	-0.0240
197	0.0256	-0.0048	-0.0126
198	-0.0738	-0.0731	-0.0540
199	-0.0013	0.0018	0.0193
200	-0.0691	-0.0740	-0.0646
201	-0.0571	-0.0758	-0.0526
202	-0.0901	-0.0557	-0.0867
203	0.0592	0.0440	0.0478
204	-0.0957	-0.1165	-0.0654
205	-0.0948	-0.0966	-0.0818
206	-0.0305	-0.0420	-0.0576
207	0.0343	0.0571	0.1451
208	-0.0884	-0.0898	-0.0580
209	-0.0362	-0.0300	-0.0165
210	-0.0729	-0.0889	-0.0728
211	-0.0243	-0.0488	-0.0430
212	-0.0418	-0.0085	-0.0591
213	0.1484	0.1616	0.1382
214	0.1124	0.1088	0.0523
215	0.1150	0.1408	0.1852
216	-0.0255	-0.0399	-0.0669
217	0.0635	0.0664	0.1442
218	-0.0474	-0.0591	-0.0124
219	-0.0678	-0.0880	-0.0728
220	-0.0725	-0.0889	-0.0617
221	0.0003	0.0492	-0.0468
222	0.0296	0.0118	-0.0656
223	0.0157	-0.0492	-0.0448
224	-0.0123	-0.0388	-0.0510
225	0.0613	0.0424	-0.0465
226	0.0622	0.0718	0.0567
227	0.0358	0.0275	0.0878
228	-0.0845	-0.0790	-0.0905
229	0.0032	-0.0096	0.0240
230	0.0373	0.0262	0.0834
231	0.0674	0.1119	0.0756
232	0.0661	0.0718	0.0860
233	-0.1476	-0.1264	-0.1141
234	0.0195	0.0497	0.0323
235	-0.0029	-0.0207	0.0563
236	-0.0504	-0.0627	-0.0480
237	0.0324	0.0436	0.0097
238	0.0609	0.0341	0.0173
239	0.0759	0.0210	0.0145
240	-0.0708	-0.0889	-0.0570
241	0.0371	-0.0264	-0.0010
242	-0.0117	-0.0418	-0.0823
243	-0.1227	-0.1237	-0.0718
244	-0.0254	0.0080	-0.0411
245	-0.0219	-0.0497	-0.0531
246	-0.0513	-0.0704	-0.0453
247	0.0077	0.0022	0.0098
248	-0.0300	-0.0370	0.0200
249	0.0071	0.0043	0.0788

Source: Emolia / Emilia source archive · SHA-256 7a85fbdf8f787486…

e11ChineseEmolia / Emilia

Emolia ZH · ZH_B00000_S00110_W000032

Natural speech · Original speech · 8.4 s

万事达卡提出三管齐下的加密支持战略，cryto点com app已启用通过sana网络存取USDT的功能。

Tiny Base · values are model estimates, not ground truth

Strongest emotions relative to training

Concentration

z +1.44 / +1.36raw 1.70 / 1.64

Contemplation

z +0.53 / +0.41raw 0.40 / 0.33

Contentment

z +0.27 / +0.44raw 0.14 / 0.23

Emotional Numbness

z +0.15 / +0.27raw 0.14 / 0.25

Teasing

z +0.21 / -0.04raw 0.12 / -0.02

Interest

z +0.20 / +0.15raw 1.77 / 1.73

Contempt

z +0.16 / +0.10raw 0.08 / 0.05

The center of each bar is the S9 teacher median. Positive z is to the right; negative z is to the left. Ranking uses z, not raw teacher units.

Strongest VoiceNet dimensions relative to training

Newsreader style (S_NEWS)

z +4.69 / +4.69raw 3.07 / 3.07

Formal style (S_FORM)

z +2.76 / +2.82raw 4.01 / 4.07

Teacher or didactic style (S_TECH)

z +1.91 / +2.42raw 2.98 / 3.61

Speech structure (STRU)

z +1.90 / +2.15raw 3.95 / 4.20

Authoritative style (S_AUTH)

z +1.99 / +1.92raw 3.16 / 3.09

Mixed resonance (R_MIXD)

z +1.31 / +1.70raw 2.54 / 2.87

Fullness (FULL)

z +1.02 / +1.65raw 2.68 / 3.25

All 57 VoiceNet predictions, including raw units, are in the full table below. These seven are ranked by z; the top values may differ from the strongest raw dimensions.

Voice, speed and quality scores in context

Genuineness (0–6)z -1.04 / -1.33raw 0.64 / 0.18

Vocal-burst blend (0–10)z -1.59 / -1.59raw 2.33 / 2.33

Content enjoyment (CE)z +1.09 / +0.74raw 5.91 / 5.55

Production quality (PQ)z +0.80 / +0.37raw 7.75 / 7.37

Speech signal quality, calibratedz +0.27 / +0.36raw 3.62 / 3.67

Background quality, calibratedz +1.05 / +0.94raw 4.37 / 4.26

Overall quality, calibratedz +1.05 / +1.04raw 3.48 / 3.47

P.808 MOS estimatez +0.93 / +1.01raw 3.88 / 3.92

score content enjoymentz +0.70 / +0.87raw 4.72 / 4.77

score overall qualityz +0.75 / +1.04raw 3.03 / 3.18

Background Noisez -1.91 / -2.05raw 0.30 / 0.27

Tempo (TEMP)z +1.00 / +1.03raw 3.31 / 3.34

Arousal (AROU)z +0.29 / +0.25raw 2.69 / 2.65

Valence (VALN)z +0.50 / +0.33raw 2.89 / 2.69

Recording quality (RCQL)z +1.55 / +1.53raw 4.13 / 4.11

Background noise (BKGN)z +1.00 / +1.04raw 3.47 / 3.49

talking speedz +1.67 / +1.39raw 15.29 / 14.26

Characters per second (CPS): 6.20 raw · z -0.75

Orange speaker embedding reconstruction

Cosine against Orange on this same clip (higher means closer to that teacher vector):

Embedding	Tiny	Base
Timbre · 128D	0.858	0.863
Identity · 250D	0.800	0.783

Vocal-burst regions

Tiny

Base

0 s8.4 s

Verified burst intervals are unavailable for this clip.

Tiny: 0 regions, count-head estimate 0.03; Base: 0 regions, count-head estimate 0.00.

Exact predicted start and end times

Model	Region	Start (s)	End (s)	Duration (s)

All 192 score slots · raw and z values

#	Target	Tiny raw	Tiny z	Base raw	Base z	Train median	Train SD
Emotion scores Forty clip-level Empathic Insight emotion teacher outputs. Each row evaluates one named emotion score.
0	Affectionemo_Affection	0.049	+0.07	0.041	+0.06	0.007	0.570
1	Amusementemo_Amusement	0.061	+0.07	0.027	+0.03	-0.001	0.885
2	Angeremo_Anger	0.094	+0.15	0.092	+0.14	0.004	0.613
3	Astonishment Surpriseemo_Astonishment_Surprise	-0.020	-0.04	-0.033	-0.07	0.005	0.572
4	Aweemo_Awe	0.009	+0.02	0.017	+0.04	0.000	0.427
5	Bitternessemo_Bitterness	0.057	+0.10	0.024	+0.03	0.013	0.415
6	Concentrationemo_Concentration	1.704	+1.44	1.641	+1.36	0.634	0.741
7	Confusionemo_Confusion	-0.016	-0.03	-0.003	-0.01	0.001	0.540
8	Contemplationemo_Contemplation	0.399	+0.53	0.326	+0.41	0.082	0.598
9	Contemptemo_Contempt	0.076	+0.16	0.046	+0.10	-0.000	0.464
10	Contentmentemo_Contentment	0.137	+0.27	0.226	+0.44	0.000	0.514
11	Disappointmentemo_Disappointment	0.005	+0.01	0.060	+0.09	0.000	0.700
12	Disgustemo_Disgust	0.017	+0.02	0.040	+0.07	0.007	0.489
13	Distressemo_Distress	-0.001	-0.00	0.095	+0.12	0.000	0.821
14	Doubtemo_Doubt	0.006	+0.00	0.004	-0.00	0.006	0.466
15	Elationemo_Elation	-0.020	-0.04	0.009	-0.01	0.012	0.728
16	Embarrassmentemo_Embarrassment	-0.042	-0.20	-0.022	-0.15	0.043	0.430
17	Emotional Numbnessemo_Emotional_Numbness	0.144	+0.15	0.252	+0.27	0.004	0.917
18	Fatigue Exhaustionemo_Fatigue_Exhaustion	0.023	-0.01	0.031	+0.01	0.028	0.539
19	Fearemo_Fear	-0.032	-0.08	-0.034	-0.08	0.015	0.610
20	Helplessnessemo_Helplessness	0.035	+0.06	0.063	+0.10	-0.004	0.696
21	Hope Enthusiasm Optimismemo_Hope_Enthusiasm_Optimism	0.098	-0.03	0.068	-0.06	0.117	0.760
22	Impatience and Irritabilityemo_Impatience_and_Irritability	0.036	-0.16	0.020	-0.18	0.149	0.705
23	Infatuationemo_Infatuation	-0.031	-0.03	-0.000	+0.03	-0.015	0.533
24	Interestemo_Interest	1.767	+0.20	1.728	+0.15	1.589	0.907
25	Intoxication Altered States of Consciousnessemo_Intoxication_Altered_States_of_Consciousness	-0.012	+0.02	-0.013	+0.02	-0.025	0.559
26	Jealousy and Envyemo_Jealousy_and_Envy	0.068	+0.02	0.079	+0.04	0.059	0.442
27	Longingemo_Longing	0.000	-0.14	0.010	-0.12	0.087	0.632
28	Malevolence Maliceemo_Malevolence_Malice	0.102	+0.09	0.031	-0.04	0.055	0.534
29	Painemo_Pain	0.022	+0.04	-0.033	-0.05	-0.002	0.579
30	Pleasure Ecstasyemo_Pleasure_Ecstasy	0.030	+0.02	0.006	-0.02	0.017	0.614
31	Prideemo_Pride	0.062	+0.12	0.078	+0.15	0.002	0.509
32	Reliefemo_Relief	0.026	-0.01	0.031	-0.00	0.033	0.681
33	Sadnessemo_Sadness	0.038	+0.05	0.017	+0.02	0.000	0.759
34	Sexual Lustemo_Sexual_Lust	0.051	+0.04	-0.027	-0.11	0.030	0.494
35	Shameemo_Shame	0.011	-0.00	0.048	+0.07	0.013	0.510
36	Sournessemo_Sourness	0.036	+0.09	0.001	+0.01	-0.005	0.439
37	Teasingemo_Teasing	0.117	+0.21	-0.020	-0.04	0.000	0.545
38	Thankfulness Gratitudeemo_Thankfulness_Gratitude	0.031	-0.01	0.099	+0.08	0.041	0.697
39	Triumphemo_Triumph	-0.006	+0.00	-0.029	-0.04	-0.007	0.521
VoiceNet dimensions Fifty-seven VoiceNet voice, delivery, style, and recording dimensions. Codes are expanded in the target column.
40	Perceived voice age (AGEV)vn_AGEV_reg	2.891	-0.08	2.776	-0.17	2.984	1.238
41	Arousal (AROU)vn_AROU_reg	2.693	+0.29	2.648	+0.25	2.359	1.147
42	Arousal shift (ARSH)vn_ARSH_reg	2.533	-0.05	2.762	+0.21	2.580	0.867
43	Vocal attack (ATCK)vn_ATCK_reg	2.025	-0.11	1.747	-0.32	2.162	1.295
44	Background noise (BKGN)vn_BKGN_reg	3.468	+1.00	3.494	+1.04	2.703	0.761
45	Brightness (BRGT)vn_BRGT_reg	2.078	+0.11	2.128	+0.17	1.991	0.813
46	Speech chunking (CHNK)vn_CHNK_reg	2.400	+0.45	2.435	+0.47	1.847	1.239
47	Articulation clarity (CLRT)vn_CLRT_reg	3.328	+1.39	3.396	+1.46	2.018	0.945
48	Cognitive load (COGL)vn_COGL_reg	1.087	-0.95	0.943	-1.09	2.094	1.061
49	Dynamic arc (DARC)vn_DARC_reg	2.006	+0.28	1.746	+0.09	1.615	1.380
50	Disfluency (DFLU)vn_DFLU_reg	0.545	-1.64	0.490	-1.69	2.488	1.184
51	Emphasis (EMPH)vn_EMPH_reg	2.482	-0.08	2.466	-0.09	2.607	1.524
52	Esthetics (ESTH)vn_ESTH_reg	2.710	+0.39	2.653	+0.32	2.402	0.782
53	Content appropriateness (EXPL)vn_EXPL_reg	0.002	-0.26	-0.042	-0.40	0.086	0.322
54	Focus (FOCS)vn_FOCS_reg	2.573	+0.21	2.770	+0.39	2.344	1.102
55	Fullness (FULL)vn_FULL_reg	2.683	+1.02	3.249	+1.65	1.778	0.889
56	Perceived gender (GEND)vn_GEND_reg	4.009	-0.03	4.391	+0.21	4.055	1.588
57	Harmonicity (HARM)vn_HARM_reg	3.196	+0.86	2.847	+0.44	2.480	0.836
58	Metallic character (METL)vn_METL_reg	1.702	+0.08	1.687	+0.07	1.621	0.958
59	Pitch range (RANG)vn_RANG_reg	2.723	-0.21	2.787	-0.14	2.914	0.897
60	Recording quality (RCQL)vn_RCQL_reg	4.130	+1.55	4.109	+1.53	2.754	0.888
61	Vocal register (REGS)vn_REGS_reg	1.086	-0.09	1.101	-0.08	1.198	1.268
62	Respiration (RESP)vn_RESP_reg	1.535	-1.08	1.510	-1.11	2.680	1.056
63	Roughness (ROUG)vn_ROUG_reg	1.637	-0.45	1.437	-0.67	2.033	0.887
64	Chest resonance (R_CHST)vn_R_CHST_reg	2.638	+0.60	2.930	+0.94	2.135	0.844
65	Head resonance (R_HEAD)vn_R_HEAD_reg	2.562	+0.50	2.546	+0.48	2.148	0.822
66	Mask resonance (R_MASK)vn_R_MASK_reg	2.169	+0.26	1.940	+0.03	1.908	1.005
67	Mixed resonance (R_MIXD)vn_R_MIXD_reg	2.540	+1.31	2.867	+1.70	1.436	0.841
68	Nasal resonance (R_NASL)vn_R_NASL_reg	2.122	-0.64	2.041	-0.72	2.791	1.047
69	Oral resonance (R_ORAL)vn_R_ORAL_reg	2.331	+0.20	2.348	+0.22	2.184	0.741
70	Throat resonance (R_THRT)vn_R_THRT_reg	2.235	+0.20	2.145	+0.09	2.070	0.803
71	Smoothness (SMTH)vn_SMTH_reg	3.686	+1.41	3.773	+1.49	2.143	1.093
72	Stance (STNC)vn_STNC_reg	2.932	+0.26	2.532	-0.09	2.633	1.137
73	Speech structure (STRU)vn_STRU_reg	3.955	+1.90	4.202	+2.15	2.137	0.958
74	ASMR style (S_ASMR)vn_S_ASMR_reg	0.677	-0.49	0.478	-0.63	1.370	1.411
75	Authoritative style (S_AUTH)vn_S_AUTH_reg	3.159	+1.99	3.094	+1.92	1.088	1.043
76	Cartoonish style (S_CART)vn_S_CART_reg	0.417	-0.82	0.310	-0.89	1.560	1.401
77	Casual style (S_CASU)vn_S_CASU_reg	2.006	-1.40	1.777	-1.58	3.793	1.278
78	Conversational style (S_CONV)vn_S_CONV_reg	1.483	-0.84	1.955	-0.48	2.594	1.318
79	Dramatic style (S_DRAM)vn_S_DRAM_reg	2.359	-0.32	2.103	-0.54	2.721	1.148
80	Formal style (S_FORM)vn_S_FORM_reg	4.011	+2.76	4.074	+2.82	1.195	1.021
81	Monologue style (S_MONO)vn_S_MONO_reg	3.759	+0.73	3.630	+0.63	2.824	1.284
82	Narrator style (S_NARR)vn_S_NARR_reg	2.742	+0.99	2.708	+0.97	1.307	1.446
83	Newsreader style (S_NEWS)vn_S_NEWS_reg	3.070	+4.69	3.070	+4.69	0.408	0.568
84	Playful style (S_PLAY)vn_S_PLAY_reg	1.626	-0.55	1.799	-0.42	2.352	1.315
85	Ranting or angry style (S_RANT)vn_S_RANT_reg	0.323	-0.69	0.482	-0.57	1.213	1.289
86	Storytelling style (S_STRY)vn_S_STRY_reg	1.659	-0.60	1.808	-0.49	2.480	1.366
87	Teacher or didactic style (S_TECH)vn_S_TECH_reg	2.984	+1.91	3.612	+2.42	0.646	1.227
88	Whispered talking style (S_WHIS)vn_S_WHIS_reg	1.024	-0.35	1.186	-0.25	1.597	1.618
89	Tempo (TEMP)vn_TEMP_reg	3.306	+1.00	3.344	+1.03	2.117	1.190
90	Tension (TENS)vn_TENS_reg	1.903	+0.40	1.615	+0.07	1.559	0.852
91	Valence (VALN)vn_VALN_reg	2.888	+0.50	2.691	+0.33	2.328	1.118
92	Valence shift (VALS)vn_VALS_reg	2.965	+0.42	2.869	+0.33	2.518	1.079
93	Velocity flux (VFLX)vn_VFLX_reg	2.544	+0.24	2.492	+0.20	2.256	1.208
94	Volatility (VOLT)vn_VOLT_reg	1.382	-1.36	1.314	-1.44	2.586	0.886
95	Vulnerability (VULN)vn_VULN_reg	1.939	-0.72	1.595	-1.07	2.648	0.984
96	Warmth (WARM)vn_WARM_reg	2.900	+0.35	3.006	+0.47	2.578	0.909
Genuineness, blend, and legacy quality Genuineness and vocal-burst blend are predicted. R_quality has Ladder training labels but no valid P3 test labels.
97	Genuineness (0–6)genuineness_0_6	0.641	-1.04	0.177	-1.33	2.332	1.621
98	Vocal-burst blend (0–10)blend_0_10	2.333	-1.59	2.333	-1.59	6.676	2.738
99	Legacy R_quality (no P3 test labels)R_quality	0.350	-2.21	0.283	-2.40	1.095	0.338
Empathic Insight Plus extra scores Nineteen additional clip-level teacher scores, including background noise and content enjoyment.
100	Ageeiv_extra:Age	3.249	-0.01	3.262	+0.04	3.250	0.293
101	Arousaleiv_extra:Arousal	1.022	-0.61	0.997	-0.67	1.289	0.435
102	Authenticityeiv_extra:Authenticity	2.708	+0.27	2.669	+0.01	2.667	0.153
103	Background Noiseeiv_extra:Background_Noise	0.303	-1.91	0.266	-2.05	0.808	0.264
104	Confident vs. Hesitanteiv_extra:Confident_vs._Hesitant	0.919	-0.40	0.961	-0.26	1.040	0.303
105	Gendereiv_extra:Gender	-0.717	-0.10	-1.060	-0.44	-0.621	0.999
106	High-Pitched vs. Low-Pitchedeiv_extra:High-Pitched_vs._Low-Pitched	1.889	+0.25	1.887	+0.24	1.827	0.250
107	Monotone vs. Expressiveeiv_extra:Monotone_vs._Expressive	1.382	-1.02	1.391	-1.00	1.859	0.470
108	Recording Qualityeiv_extra:Recording_Quality	2.544	+1.20	2.554	+1.24	2.144	0.332
109	Serious vs. Humorouseiv_extra:Serious_vs._Humorous	0.840	-0.26	0.870	-0.17	0.929	0.340
110	Soft vs. Harsheiv_extra:Soft_vs._Harsh	0.151	-0.41	0.104	-0.55	0.281	0.320
111	Submissive vs. Dominanteiv_extra:Submissive_vs._Dominant	0.307	-0.21	0.251	-0.39	0.376	0.324
112	Valenceeiv_extra:Valence	0.017	+0.03	-0.007	-0.03	0.005	0.380
113	Vulnerable vs. Emotionally Detachedeiv_extra:Vulnerable_vs._Emotionally_Detached	2.416	+1.61	2.406	+1.58	1.715	0.437
114	Warm vs. Coldeiv_extra:Warm_vs._Cold	0.073	+0.07	0.016	-0.12	0.051	0.300
115	score background qualityeiv_extra:score_background_quality	3.743	+0.64	3.832	+0.77	3.301	0.693
116	score content enjoymenteiv_extra:score_content_enjoyment	4.719	+0.70	4.771	+0.87	4.507	0.303
117	score overall qualityeiv_extra:score_overall_quality	3.030	+0.75	3.179	+1.04	2.652	0.507
118	score speech qualityeiv_extra:score_speech_quality	1.921	+0.78	1.931	+0.85	1.808	0.146
Meta AudioBox Aesthetics Four AudioBox aesthetic teacher outputs. Expansions follow the official Meta model card.
119	Content enjoyment (CE)audiobox:CE	5.911	+1.09	5.550	+0.74	4.799	1.018
120	Content usefulness (CU)audiobox:CU	6.530	+0.88	6.183	+0.53	5.649	1.001
121	Production complexity (PC)audiobox:PC	1.511	-0.51	1.612	-0.44	2.331	1.617
122	Production quality (PQ)audiobox:PQ	7.747	+0.80	7.366	+0.37	7.044	0.879
Microsoft DNSMOS Seven DNSMOS teacher outputs: raw and calibrated SIG/BAK/OVRL estimates plus P.808 MOS.
123	Speech signal quality, rawdnsmos:SIG_raw	4.152	+0.38	4.212	+0.47	3.900	0.669
124	Background quality, rawdnsmos:BAK_raw	4.667	+1.30	4.553	+1.19	3.211	1.124
125	Overall quality, rawdnsmos:OVRL_raw	4.043	+1.18	4.043	+1.18	3.085	0.812
126	Speech signal quality, calibrateddnsmos:SIG	3.624	+0.27	3.667	+0.36	3.488	0.501
127	Background quality, calibrateddnsmos:BAK	4.365	+1.05	4.264	+0.94	3.389	0.928
128	Overall quality, calibrateddnsmos:OVRL	3.477	+1.05	3.473	+1.04	2.840	0.606
129	P.808 MOS estimatednsmos:P808_MOS	3.880	+0.93	3.923	+1.01	3.421	0.496
Vocal-burst count The regression target is log(1 + count). A separate table also reports count error after inverse transformation.
130	Vocal-burst count, log(1 + count)burst_count_log1p	0.033	+0.05	0.002	+0.00	0.000	0.647
VoiceCLAP attributes Sixty-one individual VoiceCLAP attribute teacher scores. The raw 768D VoiceCLAP embedding is stored in sidecars but is not a model output.
131	Affectionvoiceclap_attribute:Affection	0.106	-1.52	0.253	-1.25	0.947	0.554
132	Agevoiceclap_attribute:Age	3.071	-0.29	3.351	+0.22	3.229	0.547
133	Amusementvoiceclap_attribute:Amusement	-0.047	-0.77	-0.056	-0.78	0.392	0.572
134	Angervoiceclap_attribute:Anger	0.236	-1.49	0.232	-1.50	0.992	0.506
135	Arousalvoiceclap_attribute:Arousal	0.745	-1.08	0.842	-0.93	1.420	0.622
136	Astonishment Surprisevoiceclap_attribute:Astonishment_Surprise	0.262	-0.51	0.331	-0.37	0.509	0.479
137	Authenticityvoiceclap_attribute:Authenticity	2.690	-0.48	2.670	-0.60	2.770	0.167
138	Awevoiceclap_attribute:Awe	0.324	-0.83	0.227	-1.20	0.539	0.259
139	Background Noisevoiceclap_attribute:Background_Noise	0.255	-1.18	0.199	-1.40	0.567	0.264
140	Bitternessvoiceclap_attribute:Bitterness	0.253	-1.44	0.124	-1.99	0.592	0.236
141	Concentrationvoiceclap_attribute:Concentration	1.606	+0.74	1.542	+0.62	1.214	0.531
142	Confident vs. Hesitantvoiceclap_attribute:Confident_vs._Hesitant	1.058	-0.03	0.934	-0.29	1.069	0.468
143	Confusionvoiceclap_attribute:Confusion	0.273	-1.11	0.197	-1.34	0.643	0.334
144	Contemplationvoiceclap_attribute:Contemplation	0.587	-0.48	0.281	-1.23	0.780	0.406
145	Contemptvoiceclap_attribute:Contempt	0.104	-1.79	0.035	-1.99	0.709	0.339
146	Contentmentvoiceclap_attribute:Contentment	0.237	-1.14	0.359	-0.75	0.588	0.307
147	Disappointmentvoiceclap_attribute:Disappointment	0.291	-1.61	0.232	-1.81	0.760	0.291
148	Disgustvoiceclap_attribute:Disgust	0.275	-1.69	0.135	-2.37	0.625	0.207
149	Distressvoiceclap_attribute:Distress	0.155	-2.21	0.068	-2.46	0.927	0.350
150	Doubtvoiceclap_attribute:Doubt	0.201	-1.78	0.105	-2.28	0.535	0.188
151	Elationvoiceclap_attribute:Elation	0.174	-0.92	0.336	-0.51	0.539	0.397
152	Embarrassmentvoiceclap_attribute:Embarrassment	0.098	-0.66	0.137	-0.54	0.307	0.314
153	Emotional Numbnessvoiceclap_attribute:Emotional_Numbness	0.751	+0.33	0.773	+0.41	0.664	0.266
154	Fatigue Exhaustionvoiceclap_attribute:Fatigue_Exhaustion	0.087	-1.44	0.014	-1.72	0.462	0.261
155	Fearvoiceclap_attribute:Fear	0.304	-1.48	0.175	-2.09	0.618	0.212
156	Gendervoiceclap_attribute:Gender	-0.441	-0.29	-1.006	-0.85	-0.151	1.005
157	Helplessnessvoiceclap_attribute:Helplessness	0.363	-1.10	0.164	-1.84	0.658	0.268
158	High-Pitched vs. Low-Pitchedvoiceclap_attribute:High-Pitched_vs._Low-Pitched	1.783	-0.15	1.762	-0.21	1.840	0.375
159	Hope Enthusiasm Optimismvoiceclap_attribute:Hope_Enthusiasm_Optimism	0.395	-0.78	0.501	-0.52	0.705	0.396
160	Impatience and Irritabilityvoiceclap_attribute:Impatience_and_Irritability	0.087	-1.78	0.011	-1.93	1.052	0.541
161	Infatuationvoiceclap_attribute:Infatuation	0.316	-0.88	0.339	-0.81	0.608	0.332
162	Interestvoiceclap_attribute:Interest	1.742	+0.33	1.842	+0.55	1.598	0.440
163	Intoxication Altered States of Consciousnessvoiceclap_attribute:Intoxication_Altered_States_of_Consciousness	0.144	-0.77	0.182	-0.69	0.502	0.463
164	Jealousy & Envyvoiceclap_attribute:Jealousy_&_Envy	0.399	-0.50	0.186	-1.38	0.523	0.245
165	Longingvoiceclap_attribute:Longing	0.121	-1.90	-0.014	-2.51	0.538	0.220
166	Malevolence Malicevoiceclap_attribute:Malevolence_Malice	0.214	-1.79	0.089	-2.15	0.833	0.346
167	Monotone vs. Expressivevoiceclap_attribute:Monotone_vs._Expressive	1.423	-0.59	1.458	-0.54	1.775	0.594
168	Painvoiceclap_attribute:Pain	0.076	-1.40	0.060	-1.47	0.381	0.218
169	Pleasure Ecstasyvoiceclap_attribute:Pleasure_Ecstasy	-0.072	-1.91	0.053	-1.50	0.503	0.301
170	Pridevoiceclap_attribute:Pride	0.565	-0.62	0.579	-0.58	0.780	0.349
171	Recording Qualityvoiceclap_attribute:Recording_Quality	2.679	+1.12	2.740	+1.30	2.313	0.328
172	Reliefvoiceclap_attribute:Relief	0.299	-1.75	0.416	-1.47	1.025	0.415
173	Sadnessvoiceclap_attribute:Sadness	0.276	-1.52	0.171	-1.86	0.752	0.313
174	Serious vs. Humorousvoiceclap_attribute:Serious_vs._Humorous	0.776	-0.05	0.689	-0.20	0.803	0.568
175	Sexual Lustvoiceclap_attribute:Sexual_Lust	0.271	-0.87	0.190	-1.06	0.635	0.419
176	Shamevoiceclap_attribute:Shame	0.163	-1.28	0.207	-1.13	0.526	0.283
177	Soft vs. Harshvoiceclap_attribute:Soft_vs._Harsh	0.247	+0.24	0.061	-0.27	0.160	0.360
178	Sournessvoiceclap_attribute:Sourness	0.337	-1.27	0.228	-1.64	0.706	0.291
179	Submissive vs. Dominantvoiceclap_attribute:Submissive_vs._Dominant	0.329	-0.82	0.432	-0.53	0.623	0.359
180	Teasingvoiceclap_attribute:Teasing	-0.091	-1.67	0.087	-1.20	0.540	0.379
181	Thankfulness Gratitudevoiceclap_attribute:Thankfulness_Gratitude	0.085	-2.45	0.403	-1.85	1.384	0.529
182	Triumphvoiceclap_attribute:Triumph	0.344	-1.03	0.436	-0.78	0.716	0.359
183	Valencevoiceclap_attribute:Valence	0.256	+0.41	0.211	+0.34	-0.007	0.635
184	Vulnerable vs. Emotionally Detachedvoiceclap_attribute:Vulnerable_vs._Emotionally_Detached	2.387	+1.35	2.369	+1.31	1.638	0.556
185	Warm vs. Coldvoiceclap_attribute:Warm_vs._Cold	-0.051	+0.04	-0.119	-0.13	-0.066	0.400
186	durationvoiceclap_attribute:duration	10.188	-0.11	9.767	-0.18	10.914	6.354
187	score background qualityvoiceclap_attribute:score_background_quality	3.725	+0.96	3.885	+1.28	3.245	0.498
188	score content enjoymentvoiceclap_attribute:score_content_enjoyment	4.868	+1.44	4.947	+1.98	4.656	0.147
189	score overall qualityvoiceclap_attribute:score_overall_quality	3.035	+0.97	3.261	+1.52	2.635	0.412
190	score speech qualityvoiceclap_attribute:score_speech_quality	2.010	+1.72	2.017	+1.82	1.891	0.069
191	talking speedvoiceclap_attribute:talking_speed	15.286	+1.67	14.260	+1.39	9.028	3.756

All Orange embedding components

The cosine above is the meaningful vector-level comparison; component values have no standalone semantic label.

Timbre — all 128 vector components

Dimension	Tiny	Base	Orange teacher
0	0.2889	0.2732	0.1665
1	-0.0401	-0.0138	-0.0842
2	0.0722	0.1226	0.0593
3	0.1583	0.1324	0.1292
4	0.0926	0.0957	0.1183
5	-0.0688	-0.1376	-0.1072
6	0.0057	0.0383	0.0927
7	-0.0066	-0.0354	0.0679
8	-0.0526	-0.0714	-0.0160
9	0.1060	0.1066	0.1238
10	0.2197	0.2183	0.2725
11	-0.1529	-0.1811	-0.0991
12	-0.0140	-0.0957	-0.0086
13	-0.0024	0.0440	0.0712
14	-0.0319	-0.0241	-0.0431
15	-0.0221	-0.0735	-0.0759
16	-0.0373	-0.0238	0.0135
17	-0.1006	-0.1102	-0.0881
18	0.0811	0.0709	0.0576
19	0.0980	0.0807	0.0572
20	-0.1175	-0.0962	-0.0848
21	0.1168	0.0388	0.0561
22	-0.0012	-0.0091	-0.0545
23	-0.0672	-0.0921	-0.0367
24	-0.0730	-0.0807	-0.0684
25	-0.0903	-0.0859	-0.0744
26	-0.0232	-0.0388	-0.0233
27	-0.0711	-0.0776	-0.0790
28	-0.1291	-0.1247	-0.0933
29	-0.0722	-0.0484	-0.0726
30	-0.0144	-0.0349	-0.0503
31	0.1199	0.1356	0.1170
32	0.0807	0.0807	0.1716
33	0.0411	-0.0022	-0.0732
34	-0.0557	-0.0391	0.0294
35	-0.0807	-0.0968	-0.0979
36	0.0153	0.0440	0.0413
37	-0.0492	-0.0854	-0.1003
38	0.0891	0.0905	0.0493
39	-0.0271	-0.0235	-0.0449
40	0.0799	0.0026	0.0511
41	-0.0472	-0.0092	-0.1218
42	-0.0603	0.0157	0.0738
43	-0.0811	-0.0983	-0.0872
44	-0.0607	-0.0942	-0.0814
45	0.0307	-0.0113	0.0455
46	-0.1037	-0.1014	-0.0799
47	-0.0515	-0.0221	0.0469
48	0.0382	0.0122	0.0061
49	-0.1260	-0.1180	-0.0856
50	0.1037	0.0116	0.1431
51	-0.0218	-0.0492	-0.0155
52	-0.0780	-0.0781	-0.0963
53	-0.0937	-0.1118	-0.0864
54	-0.1168	-0.1376	-0.0948
55	-0.0853	-0.1035	-0.0815
56	0.1260	0.1164	0.1971
57	-0.0569	-0.0952	-0.0930
58	0.0277	0.0952	0.1351
59	-0.0095	-0.0683	0.0001
60	0.0791	0.0486	-0.0320
61	-0.0390	-0.0259	-0.0663
62	-0.0019	0.0512	-0.0024
63	-0.0378	-0.0592	-0.0805
64	0.0507	0.0383	0.0319
65	-0.0960	-0.0435	-0.0691
66	0.2120	0.2142	0.1992
67	0.1898	0.1656	0.2091
68	-0.0145	-0.0261	-0.0126
69	-0.0715	-0.0109	-0.0375
70	-0.0350	-0.0551	-0.0520
71	-0.0499	-0.0828	-0.0115
72	0.0960	0.1366	0.1011
73	0.1129	0.0942	0.0698
74	-0.0903	-0.0719	-0.0926
75	0.1368	0.1169	0.1111
76	-0.0003	-0.0450	0.0365
77	-0.0319	-0.0288	0.0341
78	0.0344	0.0719	0.0564
79	-0.1076	-0.0962	-0.0735
80	0.1137	0.0535	0.0580
81	0.0538	0.0709	0.1003
82	-0.0199	-0.0295	-0.0811
83	0.0811	0.1237	0.1259
84	-0.0384	0.0059	-0.0322
85	-0.0795	-0.0582	-0.0900
86	0.1298	0.0968	0.0637
87	-0.1122	-0.1324	-0.0881
88	0.1782	0.1149	0.1313
89	-0.0061	-0.0056	-0.0367
90	-0.0448	-0.0229	-0.0919
91	0.0530	0.0864	0.1031
92	-0.0634	-0.0213	-0.0452
93	-0.0233	-0.0559	-0.0239
94	-0.0089	-0.0541	-0.0234
95	-0.0968	-0.1138	-0.0910
96	-0.1099	-0.1268	-0.0504
97	-0.0584	-0.0057	-0.0592
98	-0.0653	-0.1190	-0.0513
99	0.0930	0.1216	0.1611
100	0.1137	0.0838	0.1110
101	-0.0279	-0.0797	-0.0819
102	0.0584	0.0327	0.0690
103	-0.0503	0.0370	-0.0420
104	-0.1037	-0.0735	-0.0829
105	-0.0983	-0.0874	-0.0810
106	-0.0860	-0.0962	-0.0681
107	0.1552	0.1531	0.1881
108	-0.0319	-0.0091	0.0166
109	0.0057	0.0595	0.0777
110	0.0315	0.0254	0.1362
111	-0.0822	-0.0585	-0.0743
112	-0.0968	-0.0823	-0.0835
113	0.0236	0.0273	0.0352
114	0.0436	0.0489	0.0903
115	-0.0392	-0.0504	-0.0803
116	-0.0957	-0.0807	-0.0726
117	-0.0005	-0.0416	0.0393
118	-0.0086	0.0109	0.0417
119	-0.1168	-0.0885	-0.0819
120	0.1606	0.1459	0.1157
121	-0.0864	-0.0365	-0.0106
122	-0.0757	-0.0688	-0.0375
123	0.0038	-0.0383	-0.0729
124	0.0638	0.0823	-0.0242
125	-0.1283	-0.1019	-0.0845
126	-0.0699	-0.0900	-0.0731
127	-0.1575	-0.1635	-0.0900

Identity — all 250 vector components

Dimension	Tiny	Base	Orange teacher
0	0.0061	-0.0167	0.0598
1	-0.0381	-0.0461	-0.0403
2	0.0238	0.0222	0.0194
3	-0.0507	-0.0975	-0.0638
4	-0.0049	-0.0288	-0.0379
5	-0.0054	-0.0328	-0.0435
6	-0.0173	-0.0223	-0.0610
7	0.2499	0.2105	0.1876
8	0.0207	0.0020	-0.0287
9	0.0865	0.1248	0.0808
10	0.0060	0.0196	0.0108
11	-0.1094	-0.1004	-0.0563
12	-0.0236	-0.0392	-0.0050
13	0.1782	0.1779	0.1305
14	-0.0139	-0.0039	-0.0594
15	0.0928	0.0906	0.0225
16	0.0230	-0.0018	-0.0673
17	-0.0375	-0.0363	-0.0084
18	0.1020	0.1599	0.1299
19	-0.0917	-0.0681	-0.0660
20	-0.0416	-0.0068	-0.0417
21	-0.0525	-0.0345	-0.0386
22	-0.0348	-0.0455	-0.0432
23	-0.0514	-0.0604	-0.0403
24	-0.0569	-0.0451	-0.0356
25	-0.0136	0.0079	0.0055
26	0.1072	0.1305	0.0566
27	-0.0234	-0.0298	-0.0338
28	0.0080	0.0269	0.0272
29	0.0466	-0.0104	0.1437
30	-0.0595	-0.0636	-0.0362
31	-0.0082	-0.0485	-0.0073
32	0.0529	0.0298	-0.0269
33	0.0640	0.0052	0.0634
34	0.0236	0.0209	0.0004
35	-0.0090	-0.0084	-0.0238
36	-0.0342	-0.0624	-0.0385
37	-0.0079	-0.0133	-0.0288
38	-0.0046	-0.0324	0.0205
39	-0.0464	-0.0628	0.0160
40	-0.0440	-0.0218	-0.0102
41	-0.0384	-0.0308	-0.0478
42	0.0298	0.0175	0.0453
43	0.0629	0.0906	0.1249
44	0.0592	0.0689	0.0555
45	-0.0172	0.0068	0.0099
46	0.0234	0.0645	0.0878
47	-0.0003	-0.0158	-0.0147
48	-0.0507	-0.0290	-0.0444
49	-0.0983	-0.1040	-0.0464
50	0.0000	0.0608	-0.0369
51	0.0022	-0.0434	0.0016
52	-0.0353	-0.0543	-0.0411
53	-0.0052	-0.0312	-0.0403
54	0.0529	0.0284	0.0261
55	0.0769	0.0339	0.0085
56	0.0040	-0.0259	0.0330
57	0.0836	0.0706	0.0515
58	-0.0625	-0.0530	-0.0399
59	0.0481	0.0559	0.0164
60	0.0902	0.0616	0.0091
61	0.1309	0.1567	0.2303
62	0.0081	-0.0234	-0.0366
63	0.0050	0.0213	0.0133
64	-0.0580	-0.0975	-0.0464
65	-0.0290	-0.0418	-0.0014
66	-0.0442	-0.0649	-0.0524
67	-0.0714	-0.0379	-0.0438
68	0.0584	0.0738	0.0641
69	0.0042	-0.0483	-0.0768
70	-0.0836	-0.0632	-0.0604
71	-0.0210	-0.0483	-0.0436
72	-0.0503	-0.0443	-0.0461
73	0.0199	0.0228	-0.0357
74	-0.0573	-0.0742	-0.0449
75	-0.0168	-0.0271	0.0340
76	0.0001	-0.0379	0.0207
77	-0.0201	-0.0465	-0.0218
78	-0.0447	-0.0240	-0.0607
79	0.0138	0.0062	-0.0338
80	-0.0525	-0.1044	-0.0442
81	0.0525	0.0088	-0.0004
82	-0.0566	-0.0787	-0.0399
83	-0.0085	-0.0183	0.0089
84	-0.0073	-0.0320	0.0171
85	-0.0762	-0.0889	-0.0445
86	-0.0283	-0.0191	-0.0397
87	-0.0484	-0.0410	-0.0355
88	0.0998	0.1330	0.0958
89	0.0119	0.0253	-0.0402
90	0.1627	0.1044	0.1299
91	0.2130	0.2399	0.1704
92	-0.0817	-0.0685	-0.0384
93	0.0200	0.0669	-0.0287
94	0.0551	0.0223	0.0390
95	-0.0046	-0.0373	-0.0464
96	0.0384	0.0166	-0.0123
97	-0.0558	-0.0543	-0.0374
98	0.0416	0.0219	0.0462
99	-0.0189	-0.0310	-0.0556
100	0.0998	0.0645	0.0477
101	-0.0743	-0.0849	-0.0420
102	0.0055	-0.0178	0.0695
103	0.0342	0.0099	0.0343
104	-0.0717	-0.0718	-0.0579
105	-0.0858	-0.0475	-0.0578
106	-0.0244	-0.0261	-0.0342
107	0.1279	0.0067	-0.0398
108	-0.0129	-0.0441	-0.0331
109	0.0847	0.0791	0.0660
110	-0.0858	-0.0694	-0.0529
111	0.0924	0.0418	0.0322
112	-0.0222	-0.0151	-0.0352
113	-0.0272	-0.0571	0.0753
114	0.0268	0.0121	0.0016
115	-0.0089	-0.0023	-0.0315
116	0.0137	-0.0304	0.0549
117	0.0473	0.0410	0.0142
118	-0.0065	-0.0371	-0.0033
119	0.0969	0.0979	0.1135
120	0.0161	0.0202	-0.0096
121	0.0414	0.0200	0.0798
122	-0.0349	-0.0383	-0.0420
123	0.0043	-0.0148	-0.0459
124	-0.0470	-0.0632	-0.0443
125	0.0211	-0.0047	0.0861
126	-0.0390	-0.0608	-0.0645
127	-0.0161	-0.0534	0.0703
128	0.0149	-0.0038	0.0282
129	0.0048	-0.0369	0.0239
130	-0.0569	-0.0337	-0.0446
131	-0.0407	-0.0430	-0.0389
132	0.0034	0.0365	-0.0070
133	0.0212	-0.0171	-0.0355
134	0.0264	0.0408	0.0144
135	-0.0470	-0.0608	-0.0447
136	-0.0518	-0.0339	-0.0450
137	0.0044	-0.0070	-0.0413
138	-0.0442	-0.0357	-0.0392
139	0.0765	0.0547	0.1674
140	-0.0242	-0.0555	-0.0524
141	0.0405	0.0381	-0.0440
142	-0.0036	-0.0335	-0.0241
143	-0.0396	-0.0057	-0.0272
144	0.0095	0.0326	0.0650
145	-0.0706	-0.0496	-0.0516
146	-0.0462	-0.0698	-0.0140
147	-0.0270	-0.0477	-0.0395
148	-0.0521	-0.0447	-0.0490
149	0.0828	0.0176	0.0330
150	0.0828	0.0114	0.0358
151	0.0067	0.0379	0.0025
152	-0.0366	-0.0575	-0.0088
153	-0.0157	-0.0010	-0.0407
154	0.0518	-0.0275	0.0180
155	0.0473	0.0118	0.1135
156	-0.0181	-0.0168	-0.0445
157	0.1220	0.1265	0.1105
158	-0.1383	-0.1289	-0.0553
159	-0.0802	-0.0738	-0.0520
160	-0.0234	-0.0575	-0.0151
161	-0.0104	0.0022	0.0288
162	-0.0033	-0.0379	-0.0159
163	0.0205	0.0353	0.0987
164	-0.0039	0.0145	0.0013
165	0.0322	0.0612	0.0316
166	-0.0069	-0.0579	-0.0475
167	0.0603	0.0632	-0.0111
168	-0.0684	-0.0475	-0.0101
169	0.0462	-0.0107	-0.0188
170	-0.0401	-0.0563	-0.0416
171	-0.0606	-0.0530	-0.0391
172	-0.0976	-0.0702	-0.0515
173	0.0274	-0.0211	0.0285
174	-0.0499	-0.0359	-0.0456
175	-0.0381	-0.0108	-0.0673
176	0.1242	0.0520	0.1193
177	-0.0359	-0.0447	-0.0366
178	0.2203	0.1575	0.1609
179	-0.0105	-0.0168	-0.0137
180	0.0880	-0.0062	0.0561
181	0.0314	0.0328	0.0508
182	0.0022	0.0085	0.0249
183	-0.0346	-0.0151	-0.0897
184	-0.0059	0.0107	-0.0129
185	0.0348	0.0187	-0.0226
186	-0.0847	-0.0653	-0.0536
187	0.1664	0.1436	0.2119
188	-0.0137	-0.0187	-0.0417
189	0.0532	0.0490	0.1487
190	-0.0106	-0.0019	-0.0511
191	0.0281	0.0000	-0.0113
192	-0.0383	-0.0481	0.0379
193	0.0795	0.0467	0.0006
194	0.0384	-0.0142	0.0141
195	0.0063	-0.0290	-0.0210
196	-0.0131	0.0012	-0.0432
197	-0.0262	-0.0281	-0.0622
198	-0.0351	-0.0512	-0.0429
199	-0.0240	-0.0665	-0.0093
200	-0.0451	-0.0587	-0.0410
201	0.1272	0.0751	0.0413
202	-0.0390	-0.0127	-0.0014
203	-0.0086	0.0157	0.0074
204	0.1020	0.1273	0.1176
205	-0.0558	-0.0543	-0.0715
206	-0.0151	-0.0636	-0.0458
207	-0.0335	-0.0371	-0.0525
208	-0.0529	-0.0475	-0.0461
209	0.0296	0.0260	0.0328
210	0.0388	0.0587	0.0472
211	0.1065	0.1012	0.1622
212	0.0235	0.0479	-0.0532
213	-0.0005	0.0051	-0.0131
214	0.1398	0.0877	0.1527
215	0.0891	0.1542	0.0923
216	0.0680	0.0575	0.0813
217	0.0843	0.0824	0.0703
218	0.0662	0.1093	0.0900
219	-0.0758	-0.0971	-0.0578
220	-0.1139	-0.1134	-0.0490
221	0.0983	0.1403	0.1515
222	0.0165	-0.0024	-0.0068
223	0.0492	0.0263	-0.0088
224	-0.0325	-0.0386	-0.0406
225	-0.0349	-0.0369	-0.0370
226	0.1642	0.1477	0.1511
227	0.0440	0.0840	0.1123
228	-0.0658	-0.0730	-0.0719
229	0.0272	0.0296	0.0495
230	0.0643	0.0543	0.0268
231	-0.0521	-0.0869	-0.0615
232	-0.0187	0.0073	0.0620
233	0.0303	0.0461	0.0089
234	-0.0294	-0.0512	-0.0377
235	0.1797	0.2032	0.2115
236	-0.0566	-0.0526	-0.0381
237	0.0625	0.0422	0.1198
238	0.0540	0.0640	0.0844
239	-0.0773	-0.1191	-0.0459
240	-0.0636	-0.0475	-0.0453
241	0.0008	-0.0426	-0.0098
242	-0.0654	-0.0500	-0.0654
243	-0.0373	-0.0604	-0.0205
244	0.0887	0.0755	0.0495
245	0.0658	0.0502	0.0276
246	-0.0219	-0.0432	-0.0360
247	-0.0223	0.0105	-0.0374
248	-0.0357	-0.0343	-0.0107
249	0.0138	0.0361	0.0775

Source: Emolia / Emilia source archive · SHA-256 547e07f8272cd3ca…

e12ChineseEmolia / Emilia

Emolia ZH · ZH_B00000_S00120_W000001

Natural speech · Original speech · 13.8 s

从今天开始，为您分享本书的第七章强大原型案例深入解读，让我们再重复一遍推广定律，有效推广定律。

Tiny Base · values are model estimates, not ground truth

Strongest emotions relative to training

Concentration

z +1.47 / +1.52raw 1.73 / 1.76

Contentment

z +1.14 / +1.38raw 0.59 / 0.71

Contemplation

z +0.85 / +0.86raw 0.59 / 0.60

Doubt

z +0.41 / +0.21raw 0.20 / 0.10

Confusion

z +0.40 / +0.20raw 0.22 / 0.11

Hope Enthusiasm Optimism

z +0.38 / +0.23raw 0.40 / 0.29

Sourness

z +0.26 / +0.01raw 0.11 / -0.00

The center of each bar is the S9 teacher median. Positive z is to the right; negative z is to the left. Ranking uses z, not raw teacher units.

Strongest VoiceNet dimensions relative to training

Newsreader style (S_NEWS)

z +4.50 / +4.11raw 2.97 / 2.74

Teacher or didactic style (S_TECH)

z +3.18 / +3.12raw 4.54 / 4.47

Formal style (S_FORM)

z +2.91 / +2.48raw 4.17 / 3.73

Vocal register (REGS)

z +2.34 / +2.32raw 4.17 / 4.14

Articulation clarity (CLRT)

z +2.05 / +1.70raw 3.95 / 3.62

Whispered talking style (S_WHIS)

z +1.56 / +1.87raw 4.13 / 4.63

Authoritative style (S_AUTH)

z +1.86 / +1.73raw 3.03 / 2.89

All 57 VoiceNet predictions, including raw units, are in the full table below. These seven are ranked by z; the top values may differ from the strongest raw dimensions.

Voice, speed and quality scores in context

Genuineness (0–6)z -1.10 / -1.08raw 0.54 / 0.58

Vocal-burst blend (0–10)z -1.55 / -1.49raw 2.44 / 2.61

Content enjoyment (CE)z +0.91 / +0.82raw 5.72 / 5.63

Production quality (PQ)z +0.68 / +0.52raw 7.64 / 7.50

Speech signal quality, calibratedz +0.19 / +0.13raw 3.59 / 3.55

Background quality, calibratedz +0.90 / +0.90raw 4.22 / 4.23

Overall quality, calibratedz +0.86 / +0.81raw 3.36 / 3.33

P.808 MOS estimatez +1.05 / +1.27raw 3.94 / 4.05

score content enjoymentz +0.27 / +0.31raw 4.59 / 4.60

score overall qualityz +0.93 / +1.07raw 3.12 / 3.19

Background Noisez -1.09 / -1.35raw 0.52 / 0.45

Tempo (TEMP)z +0.24 / +0.30raw 2.41 / 2.47

Arousal (AROU)z -0.41 / -0.51raw 1.89 / 1.78

Valence (VALN)z +0.54 / +0.26raw 2.94 / 2.62

Recording quality (RCQL)z +1.48 / +1.45raw 4.07 / 4.04

Background noise (BKGN)z +1.42 / +1.56raw 3.79 / 3.89

talking speedz -0.22 / +0.08raw 8.21 / 9.33

Characters per second (CPS): 3.40 raw · z -1.50

Orange speaker embedding reconstruction

Cosine against Orange on this same clip (higher means closer to that teacher vector):

Embedding	Tiny	Base
Timbre · 128D	0.837	0.828
Identity · 250D	0.818	0.852

Vocal-burst regions

Tiny

Base

0 s13.8 s

Verified burst intervals are unavailable for this clip.

Tiny: 0 regions, count-head estimate 0.03; Base: 0 regions, count-head estimate 0.01.

Exact predicted start and end times

Model	Region	Start (s)	End (s)	Duration (s)

All 192 score slots · raw and z values

#	Target	Tiny raw	Tiny z	Base raw	Base z	Train median	Train SD
Emotion scores Forty clip-level Empathic Insight emotion teacher outputs. Each row evaluates one named emotion score.
0	Affectionemo_Affection	0.053	+0.08	-0.005	-0.02	0.007	0.570
1	Amusementemo_Amusement	-0.004	-0.00	-0.081	-0.09	-0.001	0.885
2	Angeremo_Anger	0.009	+0.01	-0.018	-0.04	0.004	0.613
3	Astonishment Surpriseemo_Astonishment_Surprise	0.003	-0.00	-0.033	-0.07	0.005	0.572
4	Aweemo_Awe	0.034	+0.08	-0.008	-0.02	0.000	0.427
5	Bitternessemo_Bitterness	0.000	-0.03	0.041	+0.07	0.013	0.415
6	Concentrationemo_Concentration	1.727	+1.47	1.761	+1.52	0.634	0.741
7	Confusionemo_Confusion	0.216	+0.40	0.110	+0.20	0.001	0.540
8	Contemplationemo_Contemplation	0.593	+0.85	0.598	+0.86	0.082	0.598
9	Contemptemo_Contempt	0.024	+0.05	0.040	+0.09	-0.000	0.464
10	Contentmentemo_Contentment	0.588	+1.14	0.710	+1.38	0.000	0.514
11	Disappointmentemo_Disappointment	-0.055	-0.08	0.035	+0.05	0.000	0.700
12	Disgustemo_Disgust	0.075	+0.14	0.054	+0.10	0.007	0.489
13	Distressemo_Distress	-0.055	-0.07	0.063	+0.08	0.000	0.821
14	Doubtemo_Doubt	0.199	+0.41	0.102	+0.21	0.006	0.466
15	Elationemo_Elation	0.111	+0.14	-0.098	-0.15	0.012	0.728
16	Embarrassmentemo_Embarrassment	-0.068	-0.26	-0.032	-0.17	0.043	0.430
17	Emotional Numbnessemo_Emotional_Numbness	0.120	+0.13	0.165	+0.18	0.004	0.917
18	Fatigue Exhaustionemo_Fatigue_Exhaustion	0.026	-0.00	0.013	-0.03	0.028	0.539
19	Fearemo_Fear	-0.099	-0.19	-0.068	-0.13	0.015	0.610
20	Helplessnessemo_Helplessness	0.035	+0.06	-0.053	-0.07	-0.004	0.696
21	Hope Enthusiasm Optimismemo_Hope_Enthusiasm_Optimism	0.404	+0.38	0.290	+0.23	0.117	0.760
22	Impatience and Irritabilityemo_Impatience_and_Irritability	0.055	-0.13	0.049	-0.14	0.149	0.705
23	Infatuationemo_Infatuation	-0.046	-0.06	0.011	+0.05	-0.015	0.533
24	Interestemo_Interest	1.815	+0.25	1.781	+0.21	1.589	0.907
25	Intoxication Altered States of Consciousnessemo_Intoxication_Altered_States_of_Consciousness	0.044	+0.12	-0.039	-0.03	-0.025	0.559
26	Jealousy and Envyemo_Jealousy_and_Envy	0.076	+0.04	0.049	-0.02	0.059	0.442
27	Longingemo_Longing	-0.034	-0.19	-0.019	-0.17	0.087	0.632
28	Malevolence Maliceemo_Malevolence_Malice	0.051	-0.01	0.021	-0.06	0.055	0.534
29	Painemo_Pain	0.028	+0.05	-0.022	-0.03	-0.002	0.579
30	Pleasure Ecstasyemo_Pleasure_Ecstasy	-0.020	-0.06	-0.077	-0.15	0.017	0.614
31	Prideemo_Pride	0.082	+0.16	0.045	+0.08	0.002	0.509
32	Reliefemo_Relief	0.040	+0.01	0.010	-0.03	0.033	0.681
33	Sadnessemo_Sadness	-0.049	-0.06	-0.010	-0.01	0.000	0.759
34	Sexual Lustemo_Sexual_Lust	0.024	-0.01	-0.045	-0.15	0.030	0.494
35	Shameemo_Shame	0.002	-0.02	0.020	+0.01	0.013	0.510
36	Sournessemo_Sourness	0.110	+0.26	-0.003	+0.01	-0.005	0.439
37	Teasingemo_Teasing	0.128	+0.24	-0.083	-0.15	0.000	0.545
38	Thankfulness Gratitudeemo_Thankfulness_Gratitude	0.079	+0.05	0.093	+0.07	0.041	0.697
39	Triumphemo_Triumph	-0.001	+0.01	-0.016	-0.02	-0.007	0.521
VoiceNet dimensions Fifty-seven VoiceNet voice, delivery, style, and recording dimensions. Codes are expanded in the target column.
40	Perceived voice age (AGEV)vn_AGEV_reg	3.873	+0.72	4.266	+1.04	2.984	1.238
41	Arousal (AROU)vn_AROU_reg	1.889	-0.41	1.777	-0.51	2.359	1.147
42	Arousal shift (ARSH)vn_ARSH_reg	2.054	-0.61	1.893	-0.79	2.580	0.867
43	Vocal attack (ATCK)vn_ATCK_reg	1.826	-0.26	1.784	-0.29	2.162	1.295
44	Background noise (BKGN)vn_BKGN_reg	3.787	+1.42	3.893	+1.56	2.703	0.761
45	Brightness (BRGT)vn_BRGT_reg	1.585	-0.50	1.677	-0.39	1.991	0.813
46	Speech chunking (CHNK)vn_CHNK_reg	1.397	-0.36	1.259	-0.47	1.847	1.239
47	Articulation clarity (CLRT)vn_CLRT_reg	3.951	+2.05	3.621	+1.70	2.018	0.945
48	Cognitive load (COGL)vn_COGL_reg	2.730	+0.60	2.319	+0.21	2.094	1.061
49	Dynamic arc (DARC)vn_DARC_reg	1.724	+0.08	1.269	-0.25	1.615	1.380
50	Disfluency (DFLU)vn_DFLU_reg	0.840	-1.39	0.711	-1.50	2.488	1.184
51	Emphasis (EMPH)vn_EMPH_reg	2.315	-0.19	2.475	-0.09	2.607	1.524
52	Esthetics (ESTH)vn_ESTH_reg	2.681	+0.36	2.854	+0.58	2.402	0.782
53	Content appropriateness (EXPL)vn_EXPL_reg	0.076	-0.03	0.325	+0.74	0.086	0.322
54	Focus (FOCS)vn_FOCS_reg	1.140	-1.09	1.413	-0.84	2.344	1.102
55	Fullness (FULL)vn_FULL_reg	1.946	+0.19	1.793	+0.02	1.778	0.889
56	Perceived gender (GEND)vn_GEND_reg	0.559	-2.20	0.982	-1.93	4.055	1.588
57	Harmonicity (HARM)vn_HARM_reg	2.469	-0.01	2.431	-0.06	2.480	0.836
58	Metallic character (METL)vn_METL_reg	2.073	+0.47	2.122	+0.52	1.621	0.958
59	Pitch range (RANG)vn_RANG_reg	2.380	-0.60	2.728	-0.21	2.914	0.897
60	Recording quality (RCQL)vn_RCQL_reg	4.067	+1.48	4.039	+1.45	2.754	0.888
61	Vocal register (REGS)vn_REGS_reg	4.170	+2.34	4.141	+2.32	1.198	1.268
62	Respiration (RESP)vn_RESP_reg	2.308	-0.35	2.491	-0.18	2.680	1.056
63	Roughness (ROUG)vn_ROUG_reg	1.875	-0.18	2.057	+0.03	2.033	0.887
64	Chest resonance (R_CHST)vn_R_CHST_reg	2.305	+0.20	2.331	+0.23	2.135	0.844
65	Head resonance (R_HEAD)vn_R_HEAD_reg	2.312	+0.20	2.372	+0.27	2.148	0.822
66	Mask resonance (R_MASK)vn_R_MASK_reg	2.403	+0.49	2.229	+0.32	1.908	1.005
67	Mixed resonance (R_MIXD)vn_R_MIXD_reg	2.658	+1.45	2.919	+1.76	1.436	0.841
68	Nasal resonance (R_NASL)vn_R_NASL_reg	3.040	+0.24	3.205	+0.40	2.791	1.047
69	Oral resonance (R_ORAL)vn_R_ORAL_reg	2.304	+0.16	2.086	-0.13	2.184	0.741
70	Throat resonance (R_THRT)vn_R_THRT_reg	2.386	+0.39	2.095	+0.03	2.070	0.803
71	Smoothness (SMTH)vn_SMTH_reg	3.122	+0.90	3.435	+1.18	2.143	1.093
72	Stance (STNC)vn_STNC_reg	2.710	+0.07	2.496	-0.12	2.633	1.137
73	Speech structure (STRU)vn_STRU_reg	3.662	+1.59	3.770	+1.70	2.137	0.958
74	ASMR style (S_ASMR)vn_S_ASMR_reg	3.213	+1.31	3.332	+1.39	1.370	1.411
75	Authoritative style (S_AUTH)vn_S_AUTH_reg	3.030	+1.86	2.892	+1.73	1.088	1.043
76	Cartoonish style (S_CART)vn_S_CART_reg	2.031	+0.34	1.798	+0.17	1.560	1.401
77	Casual style (S_CASU)vn_S_CASU_reg	1.488	-1.80	1.617	-1.70	3.793	1.278
78	Conversational style (S_CONV)vn_S_CONV_reg	1.809	-0.60	2.021	-0.43	2.594	1.318
79	Dramatic style (S_DRAM)vn_S_DRAM_reg	1.871	-0.74	1.604	-0.97	2.721	1.148
80	Formal style (S_FORM)vn_S_FORM_reg	4.168	+2.91	3.727	+2.48	1.195	1.021
81	Monologue style (S_MONO)vn_S_MONO_reg	3.988	+0.91	4.247	+1.11	2.824	1.284
82	Narrator style (S_NARR)vn_S_NARR_reg	3.213	+1.32	3.347	+1.41	1.307	1.446
83	Newsreader style (S_NEWS)vn_S_NEWS_reg	2.967	+4.50	2.743	+4.11	0.408	0.568
84	Playful style (S_PLAY)vn_S_PLAY_reg	2.244	-0.08	1.893	-0.35	2.352	1.315
85	Ranting or angry style (S_RANT)vn_S_RANT_reg	-0.101	-1.02	-0.161	-1.07	1.213	1.289
86	Storytelling style (S_STRY)vn_S_STRY_reg	2.076	-0.30	2.285	-0.14	2.480	1.366
87	Teacher or didactic style (S_TECH)vn_S_TECH_reg	4.544	+3.18	4.468	+3.12	0.646	1.227
88	Whispered talking style (S_WHIS)vn_S_WHIS_reg	4.127	+1.56	4.627	+1.87	1.597	1.618
89	Tempo (TEMP)vn_TEMP_reg	2.408	+0.24	2.471	+0.30	2.117	1.190
90	Tension (TENS)vn_TENS_reg	1.597	+0.05	1.139	-0.49	1.559	0.852
91	Valence (VALN)vn_VALN_reg	2.936	+0.54	2.623	+0.26	2.328	1.118
92	Valence shift (VALS)vn_VALS_reg	2.618	+0.09	2.547	+0.03	2.518	1.079
93	Velocity flux (VFLX)vn_VFLX_reg	2.159	-0.08	2.077	-0.15	2.256	1.208
94	Volatility (VOLT)vn_VOLT_reg	0.744	-2.08	0.812	-2.00	2.586	0.886
95	Vulnerability (VULN)vn_VULN_reg	2.148	-0.51	2.191	-0.47	2.648	0.984
96	Warmth (WARM)vn_WARM_reg	2.975	+0.44	3.340	+0.84	2.578	0.909
Genuineness, blend, and legacy quality Genuineness and vocal-burst blend are predicted. R_quality has Ladder training labels but no valid P3 test labels.
97	Genuineness (0–6)genuineness_0_6	0.541	-1.10	0.579	-1.08	2.332	1.621
98	Vocal-burst blend (0–10)blend_0_10	2.440	-1.55	2.610	-1.49	6.676	2.738
99	Legacy R_quality (no P3 test labels)R_quality	0.355	-2.19	0.376	-2.13	1.095	0.338
Empathic Insight Plus extra scores Nineteen additional clip-level teacher scores, including background noise and content enjoyment.
100	Ageeiv_extra:Age	3.308	+0.20	3.336	+0.29	3.250	0.293
101	Arousaleiv_extra:Arousal	1.017	-0.62	1.016	-0.63	1.289	0.435
102	Authenticityeiv_extra:Authenticity	2.744	+0.51	2.798	+0.86	2.667	0.153
103	Background Noiseeiv_extra:Background_Noise	0.518	-1.09	0.451	-1.35	0.808	0.264
104	Confident vs. Hesitanteiv_extra:Confident_vs._Hesitant	0.961	-0.26	1.031	-0.03	1.040	0.303
105	Gendereiv_extra:Gender	1.333	+1.96	1.177	+1.80	-0.621	0.999
106	High-Pitched vs. Low-Pitchedeiv_extra:High-Pitched_vs._Low-Pitched	1.762	-0.26	1.690	-0.55	1.827	0.250
107	Monotone vs. Expressiveeiv_extra:Monotone_vs._Expressive	1.662	-0.42	1.687	-0.37	1.859	0.470
108	Recording Qualityeiv_extra:Recording_Quality	2.497	+1.06	2.525	+1.15	2.144	0.332
109	Serious vs. Humorouseiv_extra:Serious_vs._Humorous	0.701	-0.67	0.795	-0.40	0.929	0.340
110	Soft vs. Harsheiv_extra:Soft_vs._Harsh	0.565	+0.89	0.620	+1.06	0.281	0.320
111	Submissive vs. Dominanteiv_extra:Submissive_vs._Dominant	0.332	-0.13	0.139	-0.73	0.376	0.324
112	Valenceeiv_extra:Valence	-0.021	-0.07	0.069	+0.17	0.005	0.380
113	Vulnerable vs. Emotionally Detachedeiv_extra:Vulnerable_vs._Emotionally_Detached	1.820	+0.24	1.763	+0.11	1.715	0.437
114	Warm vs. Coldeiv_extra:Warm_vs._Cold	0.063	+0.04	0.116	+0.22	0.051	0.300
115	score background qualityeiv_extra:score_background_quality	3.832	+0.77	3.919	+0.89	3.301	0.693
116	score content enjoymenteiv_extra:score_content_enjoyment	4.590	+0.27	4.601	+0.31	4.507	0.303
117	score overall qualityeiv_extra:score_overall_quality	3.123	+0.93	3.195	+1.07	2.652	0.507
118	score speech qualityeiv_extra:score_speech_quality	1.881	+0.50	1.853	+0.31	1.808	0.146
Meta AudioBox Aesthetics Four AudioBox aesthetic teacher outputs. Expansions follow the official Meta model card.
119	Content enjoyment (CE)audiobox:CE	5.725	+0.91	5.633	+0.82	4.799	1.018
120	Content usefulness (CU)audiobox:CU	6.386	+0.74	6.514	+0.86	5.649	1.001
121	Production complexity (PC)audiobox:PC	1.776	-0.34	1.442	-0.55	2.331	1.617
122	Production quality (PQ)audiobox:PQ	7.637	+0.68	7.497	+0.52	7.044	0.879
Microsoft DNSMOS Seven DNSMOS teacher outputs: raw and calibrated SIG/BAK/OVRL estimates plus P.808 MOS.
123	Speech signal quality, rawdnsmos:SIG_raw	4.074	+0.26	4.008	+0.16	3.900	0.669
124	Background quality, rawdnsmos:BAK_raw	4.500	+1.15	4.500	+1.15	3.211	1.124
125	Overall quality, rawdnsmos:OVRL_raw	3.884	+0.98	3.834	+0.92	3.085	0.812
126	Speech signal quality, calibrateddnsmos:SIG	3.585	+0.19	3.552	+0.13	3.488	0.501
127	Background quality, calibrateddnsmos:BAK	4.220	+0.90	4.228	+0.90	3.389	0.928
128	Overall quality, calibrateddnsmos:OVRL	3.364	+0.86	3.330	+0.81	2.840	0.606
129	P.808 MOS estimatednsmos:P808_MOS	3.942	+1.05	4.051	+1.27	3.421	0.496
Vocal-burst count The regression target is log(1 + count). A separate table also reports count error after inverse transformation.
130	Vocal-burst count, log(1 + count)burst_count_log1p	0.025	+0.04	0.005	+0.01	0.000	0.647
VoiceCLAP attributes Sixty-one individual VoiceCLAP attribute teacher scores. The raw 768D VoiceCLAP embedding is stored in sidecars but is not a model output.
131	Affectionvoiceclap_attribute:Affection	0.520	-0.77	0.749	-0.36	0.947	0.554
132	Agevoiceclap_attribute:Age	3.230	+0.00	3.370	+0.26	3.229	0.547
133	Amusementvoiceclap_attribute:Amusement	-0.118	-0.89	0.038	-0.62	0.392	0.572
134	Angervoiceclap_attribute:Anger	0.371	-1.23	0.395	-1.18	0.992	0.506
135	Arousalvoiceclap_attribute:Arousal	0.516	-1.45	0.647	-1.24	1.420	0.622
136	Astonishment Surprisevoiceclap_attribute:Astonishment_Surprise	0.226	-0.59	0.165	-0.72	0.509	0.479
137	Authenticityvoiceclap_attribute:Authenticity	2.842	+0.43	2.864	+0.56	2.770	0.167
138	Awevoiceclap_attribute:Awe	0.511	-0.11	0.529	-0.04	0.539	0.259
139	Background Noisevoiceclap_attribute:Background_Noise	0.247	-1.22	0.297	-1.02	0.567	0.264
140	Bitternessvoiceclap_attribute:Bitterness	0.299	-1.24	0.325	-1.14	0.592	0.236
141	Concentrationvoiceclap_attribute:Concentration	1.716	+0.94	1.556	+0.64	1.214	0.531
142	Confident vs. Hesitantvoiceclap_attribute:Confident_vs._Hesitant	0.912	-0.34	0.808	-0.56	1.069	0.468
143	Confusionvoiceclap_attribute:Confusion	0.629	-0.04	0.605	-0.12	0.643	0.334
144	Contemplationvoiceclap_attribute:Contemplation	0.944	+0.40	0.706	-0.18	0.780	0.406
145	Contemptvoiceclap_attribute:Contempt	0.077	-1.86	0.303	-1.20	0.709	0.339
146	Contentmentvoiceclap_attribute:Contentment	0.625	+0.12	0.610	+0.07	0.588	0.307
147	Disappointmentvoiceclap_attribute:Disappointment	0.388	-1.28	0.468	-1.00	0.760	0.291
148	Disgustvoiceclap_attribute:Disgust	0.179	-2.15	0.144	-2.32	0.625	0.207
149	Distressvoiceclap_attribute:Distress	0.415	-1.46	0.773	-0.44	0.927	0.350
150	Doubtvoiceclap_attribute:Doubt	0.359	-0.93	0.329	-1.09	0.535	0.188
151	Elationvoiceclap_attribute:Elation	0.282	-0.65	0.399	-0.35	0.539	0.397
152	Embarrassmentvoiceclap_attribute:Embarrassment	-0.001	-0.98	0.118	-0.60	0.307	0.314
153	Emotional Numbnessvoiceclap_attribute:Emotional_Numbness	0.802	+0.52	0.855	+0.72	0.664	0.266
154	Fatigue Exhaustionvoiceclap_attribute:Fatigue_Exhaustion	0.236	-0.87	0.252	-0.80	0.462	0.261
155	Fearvoiceclap_attribute:Fear	0.229	-1.83	0.268	-1.65	0.618	0.212
156	Gendervoiceclap_attribute:Gender	1.489	+1.63	1.380	+1.52	-0.151	1.005
157	Helplessnessvoiceclap_attribute:Helplessness	0.547	-0.41	0.623	-0.13	0.658	0.268
158	High-Pitched vs. Low-Pitchedvoiceclap_attribute:High-Pitched_vs._Low-Pitched	1.634	-0.55	1.702	-0.37	1.840	0.375
159	Hope Enthusiasm Optimismvoiceclap_attribute:Hope_Enthusiasm_Optimism	0.383	-0.81	0.415	-0.73	0.705	0.396
160	Impatience and Irritabilityvoiceclap_attribute:Impatience_and_Irritability	0.210	-1.56	0.379	-1.24	1.052	0.541
161	Infatuationvoiceclap_attribute:Infatuation	0.266	-1.03	0.378	-0.69	0.608	0.332
162	Interestvoiceclap_attribute:Interest	1.607	+0.02	1.596	-0.01	1.598	0.440
163	Intoxication Altered States of Consciousnessvoiceclap_attribute:Intoxication_Altered_States_of_Consciousness	0.006	-1.07	0.097	-0.88	0.502	0.463
164	Jealousy & Envyvoiceclap_attribute:Jealousy_&_Envy	0.533	+0.04	0.558	+0.14	0.523	0.245
165	Longingvoiceclap_attribute:Longing	0.364	-0.79	0.432	-0.48	0.538	0.220
166	Malevolence Malicevoiceclap_attribute:Malevolence_Malice	0.281	-1.60	0.422	-1.19	0.833	0.346
167	Monotone vs. Expressivevoiceclap_attribute:Monotone_vs._Expressive	1.472	-0.51	1.569	-0.35	1.775	0.594
168	Painvoiceclap_attribute:Pain	0.128	-1.16	0.062	-1.46	0.381	0.218
169	Pleasure Ecstasyvoiceclap_attribute:Pleasure_Ecstasy	0.182	-1.07	0.335	-0.56	0.503	0.301
170	Pridevoiceclap_attribute:Pride	0.641	-0.40	0.625	-0.44	0.780	0.349
171	Recording Qualityvoiceclap_attribute:Recording_Quality	2.771	+1.40	2.743	+1.31	2.313	0.328
172	Reliefvoiceclap_attribute:Relief	0.527	-1.20	0.735	-0.70	1.025	0.415
173	Sadnessvoiceclap_attribute:Sadness	0.553	-0.63	0.619	-0.42	0.752	0.313
174	Serious vs. Humorousvoiceclap_attribute:Serious_vs._Humorous	0.385	-0.74	0.603	-0.35	0.803	0.568
175	Sexual Lustvoiceclap_attribute:Sexual_Lust	0.235	-0.95	0.255	-0.91	0.635	0.419
176	Shamevoiceclap_attribute:Shame	0.308	-0.77	0.516	-0.04	0.526	0.283
177	Soft vs. Harshvoiceclap_attribute:Soft_vs._Harsh	0.613	+1.26	0.458	+0.83	0.160	0.360
178	Sournessvoiceclap_attribute:Sourness	0.328	-1.30	0.513	-0.66	0.706	0.291
179	Submissive vs. Dominantvoiceclap_attribute:Submissive_vs._Dominant	0.213	-1.14	0.366	-0.72	0.623	0.359
180	Teasingvoiceclap_attribute:Teasing	-0.062	-1.59	0.116	-1.12	0.540	0.379
181	Thankfulness Gratitudevoiceclap_attribute:Thankfulness_Gratitude	0.544	-1.59	0.751	-1.20	1.384	0.529
182	Triumphvoiceclap_attribute:Triumph	0.199	-1.44	0.314	-1.12	0.716	0.359
183	Valencevoiceclap_attribute:Valence	0.365	+0.59	0.283	+0.46	-0.007	0.635
184	Vulnerable vs. Emotionally Detachedvoiceclap_attribute:Vulnerable_vs._Emotionally_Detached	2.028	+0.70	2.098	+0.83	1.638	0.556
185	Warm vs. Coldvoiceclap_attribute:Warm_vs._Cold	0.105	+0.43	-0.119	-0.13	-0.066	0.400
186	durationvoiceclap_attribute:duration	14.085	+0.50	13.590	+0.42	10.914	6.354
187	score background qualityvoiceclap_attribute:score_background_quality	3.791	+1.10	3.834	+1.18	3.245	0.498
188	score content enjoymentvoiceclap_attribute:score_content_enjoyment	4.894	+1.62	4.883	+1.55	4.656	0.147
189	score overall qualityvoiceclap_attribute:score_overall_quality	3.093	+1.11	3.122	+1.18	2.635	0.412
190	score speech qualityvoiceclap_attribute:score_speech_quality	1.953	+0.90	1.967	+1.10	1.891	0.069
191	talking speedvoiceclap_attribute:talking_speed	8.206	-0.22	9.328	+0.08	9.028	3.756

All Orange embedding components

The cosine above is the meaningful vector-level comparison; component values have no standalone semantic label.

Timbre — all 128 vector components

Dimension	Tiny	Base	Orange teacher
0	-0.0125	-0.0097	-0.0867
1	0.1098	0.0916	0.0659
2	0.0818	0.0987	0.1168
3	0.0519	-0.0046	0.0193
4	-0.0914	-0.0529	-0.0818
5	-0.1597	-0.0955	-0.1102
6	-0.0355	-0.0532	-0.0789
7	0.1735	0.2465	0.2028
8	0.0027	0.0005	-0.0523
9	-0.0247	-0.0282	0.0234
10	-0.0766	-0.0494	-0.0373
11	-0.1604	-0.1200	-0.1019
12	-0.0802	-0.0353	-0.0876
13	-0.0979	-0.0858	-0.0089
14	-0.1111	-0.1065	-0.0372
15	0.0832	0.1020	0.0548
16	-0.0077	-0.0053	0.0999
17	-0.0700	-0.0816	-0.0906
18	-0.0565	-0.0600	-0.0803
19	-0.0109	-0.0329	-0.0094
20	0.0256	0.0461	-0.0028
21	0.0901	0.1510	0.0782
22	0.0266	0.0897	0.0712
23	-0.1177	-0.0152	0.0340
24	0.1565	0.0642	0.1159
25	-0.0145	-0.0302	0.0129
26	-0.0789	-0.0949	-0.0817
27	0.0150	0.0298	-0.0131
28	-0.0815	-0.0845	-0.0959
29	-0.0141	0.0429	-0.0727
30	-0.0357	-0.0363	-0.0938
31	-0.0316	-0.0578	-0.0804
32	-0.0270	0.0590	0.0790
33	-0.0631	-0.0571	-0.0960
34	-0.0733	-0.0781	-0.0781
35	-0.0069	0.0411	-0.0704
36	-0.1190	-0.0803	-0.0936
37	-0.0500	-0.0357	0.0085
38	0.1019	0.0574	0.1093
39	-0.0697	-0.0526	-0.0878
40	-0.0260	0.0439	0.0130
41	0.1308	0.0302	0.0243
42	-0.0832	-0.0803	-0.0878
43	0.1413	0.0878	0.1409
44	-0.0641	-0.0250	-0.0833
45	0.0271	0.0587	0.1183
46	0.0235	0.0548	0.0089
47	0.0920	0.0607	0.1460
48	-0.0726	-0.0858	-0.0850
49	-0.0641	-0.0674	-0.0880
50	-0.0638	-0.0282	-0.0333
51	0.1788	0.1910	0.2258
52	-0.0186	-0.0119	-0.0103
53	0.0233	0.0038	-0.0076
54	-0.0657	-0.0613	-0.0235
55	0.0503	-0.0548	0.0125
56	-0.0799	-0.0852	-0.0826
57	-0.0799	-0.0813	0.0292
58	0.0726	0.1026	0.0955
59	0.1045	0.1316	0.0927
60	0.0215	0.0810	0.0912
61	0.2472	0.3407	0.2036
62	0.0933	0.1220	0.0729
63	-0.0648	-0.1136	-0.0827
64	-0.0220	0.0305	-0.0137
65	-0.0648	-0.0790	-0.0710
66	-0.0227	-0.0832	-0.0544
67	-0.1288	-0.0839	-0.0840
68	-0.0717	-0.0936	-0.0920
69	0.1538	0.1742	0.2546
70	0.0177	-0.0252	-0.0734
71	0.0152	0.0331	0.0292
72	-0.0197	-0.0196	0.0481
73	0.0127	-0.0248	-0.0580
74	0.1354	0.0719	0.0865
75	-0.0467	-0.0658	-0.1058
76	0.0490	0.0159	0.1481
77	-0.0710	-0.0839	-0.0795
78	-0.0779	-0.0749	-0.0775
79	0.1210	0.1149	0.1617
80	-0.0720	-0.0755	-0.0789
81	0.2919	0.2594	0.2072
82	-0.0519	-0.0419	-0.0833
83	0.0122	0.0419	-0.0103
84	-0.0365	-0.0363	-0.0895
85	0.0421	0.0845	-0.0411
86	0.0037	0.0237	0.0325
87	-0.1032	-0.1291	-0.1005
88	-0.0394	-0.0248	-0.0383
89	-0.1012	-0.0574	-0.0800
90	-0.0030	0.0167	0.0035
91	-0.0575	-0.0497	-0.0800
92	-0.0782	-0.0255	-0.0606
93	0.0139	-0.0112	0.0333
94	0.0237	-0.0318	-0.0489
95	-0.1177	-0.1181	-0.0492
96	-0.1196	-0.1342	-0.0887
97	0.0172	-0.0344	0.0319
98	-0.0293	-0.0610	-0.0485
99	0.1440	0.1245	0.1498
100	0.1492	0.0910	0.0138
101	-0.0769	-0.0261	-0.0842
102	0.0270	0.0839	0.0153
103	-0.0437	-0.0826	-0.0707
104	-0.0427	-0.0175	-0.0851
105	-0.0062	0.0136	0.0866
106	0.0641	-0.0110	0.0188
107	-0.0763	-0.0681	-0.0811
108	-0.0887	-0.0845	-0.0945
109	0.1045	-0.0221	0.0540
110	-0.1749	-0.1226	-0.0679
111	0.0386	0.0034	0.1698
112	-0.0999	-0.1258	-0.0858
113	-0.0316	-0.0350	0.0229
114	0.1341	0.1845	0.1251
115	0.1124	0.1420	0.1006
116	0.1413	0.1039	0.1245
117	0.0838	0.0500	0.0426
118	-0.0815	-0.0661	-0.0848
119	-0.0031	0.0190	-0.0612
120	0.0634	0.1503	0.0625
121	0.1597	0.1284	0.1697
122	-0.0999	-0.1039	-0.0895
123	0.0516	0.0098	0.0455
124	0.0394	0.0003	-0.0252
125	-0.1058	-0.1374	-0.0868
126	0.0294	0.0131	0.0556
127	-0.1131	-0.1007	-0.0547

Identity — all 250 vector components

Dimension	Tiny	Base	Orange teacher
0	0.1502	0.0973	0.1238
1	-0.0154	-0.0511	-0.0102
2	-0.0779	-0.0419	-0.0559
3	0.0507	0.0265	0.0541
4	0.0223	0.0007	-0.0414
5	0.0066	-0.0020	-0.0475
6	0.0320	0.0043	-0.0139
7	0.0250	0.0698	0.0335
8	0.0261	-0.0233	-0.0512
9	0.0805	0.0803	0.0709
10	0.0284	-0.0161	0.0608
11	0.0034	-0.0424	-0.0615
12	0.0830	0.0381	0.0808
13	0.1926	0.1382	0.1431
14	-0.0315	-0.0531	-0.0649
15	0.1052	0.0260	0.0215
16	0.0491	0.0664	0.0252
17	-0.0231	-0.0565	-0.0243
18	0.1217	0.1457	0.1069
19	-0.1736	-0.1416	-0.0721
20	-0.0792	-0.0698	-0.0455
21	-0.0353	-0.0400	-0.0422
22	-0.0033	-0.0117	-0.0310
23	-0.0982	-0.1021	-0.0440
24	-0.0291	-0.0272	-0.0388
25	-0.0200	-0.0073	-0.0126
26	-0.0334	0.0311	-0.0032
27	-0.0453	-0.0575	-0.0370
28	-0.0312	0.0019	0.0266
29	0.0402	-0.0032	-0.0048
30	-0.0596	-0.0813	-0.0396
31	0.1812	0.1572	0.2399
32	-0.0261	-0.0245	-0.0043
33	0.1559	0.1334	0.0756
34	0.0989	0.1171	0.1420
35	-0.0244	-0.0225	-0.0586
36	0.0244	0.0259	-0.0203
37	0.0277	-0.0177	0.0262
38	0.0147	-0.0108	0.0712
39	-0.0874	-0.0892	-0.0384
40	-0.0520	-0.0257	-0.0281
41	-0.0355	-0.0619	-0.0522
42	0.0383	-0.0163	-0.0219
43	0.0627	0.1123	0.0936
44	-0.0058	-0.0277	-0.0547
45	-0.0105	-0.0087	0.0088
46	0.0185	0.0265	-0.0134
47	-0.0114	-0.0390	-0.0001
48	-0.0261	-0.0568	-0.0485
49	-0.0634	-0.0820	-0.0809
50	-0.0230	-0.0300	-0.0321
51	0.0074	-0.0221	0.0737
52	0.0608	0.0558	0.0735
53	-0.0371	-0.0476	-0.0440
54	0.1210	0.1572	0.1562
55	-0.0053	-0.0131	0.0048
56	0.0401	0.0055	0.0475
57	0.1280	0.1504	0.1825
58	0.0000	-0.0260	-0.0118
59	0.0982	0.0619	0.0817
60	0.0049	0.0076	-0.0345
61	0.0139	-0.0180	-0.0422
62	-0.0298	-0.0281	-0.0399
63	-0.0040	0.0094	-0.0494
64	-0.0322	-0.1103	-0.0506
65	-0.0187	0.0362	-0.0497
66	0.0624	-0.0103	-0.0020
67	0.0253	0.0076	0.0778
68	0.0304	0.0111	0.0142
69	0.0627	0.0120	-0.0075
70	-0.0523	-0.0456	-0.0659
71	-0.0776	-0.0694	-0.0476
72	0.0268	0.0100	0.1437
73	-0.0184	0.0946	0.0485
74	-0.1096	-0.1014	-0.0491
75	0.0127	0.0434	0.0947
76	-0.0520	0.0040	0.0541
77	-0.0352	-0.0109	-0.0320
78	-0.0415	-0.0417	-0.0663
79	-0.0162	-0.0572	-0.0486
80	-0.0497	-0.0919	-0.0483
81	-0.0602	-0.0718	-0.0544
82	0.0735	0.0305	-0.0172
83	-0.0050	-0.0257	-0.0290
84	0.0291	0.0212	0.0388
85	-0.0356	-0.0708	-0.0486
86	-0.0817	-0.0572	-0.0433
87	-0.0394	-0.0199	-0.0198
88	0.1990	0.2777	0.2881
89	-0.0409	-0.0414	-0.0439
90	0.0881	0.1130	0.0353
91	0.1058	0.1947	0.1643
92	-0.0166	-0.0134	-0.0077
93	0.0602	0.0728	0.1024
94	0.0057	-0.0541	-0.0109
95	-0.0168	-0.0514	-0.0507
96	-0.0024	-0.0334	-0.0434
97	-0.0196	-0.0732	-0.0163
98	0.1166	0.0858	0.0749
99	0.0181	0.0140	0.0028
100	0.0957	0.0397	0.0317
101	-0.0887	-0.0677	-0.0459
102	0.0982	0.0698	0.0994
103	0.0208	-0.0068	0.0343
104	-0.0012	-0.0776	-0.0527
105	-0.0779	-0.1028	-0.0632
106	-0.0387	-0.0701	-0.0374
107	-0.0339	-0.0121	-0.0435
108	0.0180	0.0272	0.0253
109	-0.0111	-0.0081	-0.0280
110	-0.0586	-0.0824	-0.0578
111	0.0053	0.0084	-0.0400
112	0.0776	0.0284	0.0806
113	-0.0539	-0.0204	-0.0828
114	0.0599	0.0104	0.0474
115	0.0501	0.0834	0.1147
116	0.0101	-0.0402	-0.0365
117	0.0280	0.0446	0.0662
118	-0.0779	-0.0422	-0.0634
119	0.0779	0.1191	0.0633
120	0.0109	0.0328	0.0438
121	-0.0843	-0.0800	-0.0522
122	-0.0643	-0.0589	-0.0458
123	0.0106	-0.0262	-0.0501
124	0.0135	-0.0076	0.0155
125	0.0719	0.1048	0.0798
126	-0.0173	-0.0207	-0.0110
127	-0.0249	-0.0691	-0.0499
128	-0.0093	-0.0045	-0.0148
129	0.0995	0.0330	0.0814
130	-0.0688	-0.0619	-0.0481
131	-0.0463	-0.0009	-0.0425
132	0.0194	0.0463	0.0374
133	-0.0211	-0.0371	-0.0480
134	0.0691	0.0376	-0.0116
135	0.0198	-0.0238	-0.0167
136	-0.0246	-0.0606	-0.0520
137	0.0239	-0.0035	-0.0451
138	-0.0602	-0.0538	-0.0428
139	0.0177	0.0415	0.0485
140	0.0323	-0.0613	-0.0257
141	0.0060	0.0228	-0.0233
142	0.0000	-0.0193	-0.0207
143	-0.0138	-0.0892	-0.0727
144	0.0288	0.0240	0.0036
145	-0.0970	-0.1205	-0.0617
146	-0.0428	-0.0830	0.0187
147	-0.0548	-0.0551	-0.0431
148	-0.0624	-0.0165	-0.0535
149	-0.0200	-0.0294	-0.0132
150	-0.0398	-0.0294	-0.0478
151	-0.0817	-0.0790	-0.0553
152	-0.0299	-0.0514	-0.0538
153	0.0387	-0.0134	0.0079
154	-0.0183	0.0279	-0.0046
155	0.0963	0.0885	0.0446
156	0.0390	0.0728	0.0212
157	0.1134	0.0919	0.1351
158	-0.0722	-0.0335	-0.0605
159	-0.0849	-0.0391	-0.0568
160	0.0372	0.0487	0.0330
161	0.0976	0.0337	0.0192
162	-0.0352	-0.0939	-0.0563
163	-0.0326	-0.0237	-0.0457
164	-0.0596	-0.0483	-0.0426
165	0.0719	0.1089	0.1147
166	-0.0577	-0.1144	-0.0565
167	-0.0135	0.0080	-0.0615
168	-0.0231	-0.0088	0.0059
169	0.0735	0.0230	0.0725
170	0.0041	-0.0153	0.0118
171	-0.0225	0.0104	0.0105
172	-0.1369	-0.0980	-0.0562
173	-0.0339	-0.0378	-0.0569
174	-0.0054	-0.0470	-0.0446
175	0.0301	0.0555	0.0332
176	-0.0608	-0.0345	-0.0413
177	-0.0173	-0.0262	-0.0147
178	0.1052	0.0562	0.0521
179	-0.0688	-0.0667	-0.0598
180	0.0005	-0.0174	-0.0507
181	0.1033	0.0800	0.1383
182	-0.0554	-0.0243	-0.0419
183	0.0380	0.0291	0.0617
184	-0.0006	-0.0470	-0.0446
185	0.0874	0.0541	0.0441
186	-0.0577	-0.0953	-0.0585
187	0.1229	0.0820	0.0831
188	0.0115	-0.0218	-0.0312
189	0.0385	0.0521	0.0729
190	-0.1103	-0.0960	-0.0842
191	-0.0371	-0.0140	-0.0284
192	-0.0551	-0.0048	0.0237
193	-0.0230	-0.0623	-0.0511
194	0.0309	-0.0057	0.0353
195	-0.0450	-0.0397	-0.0355
196	-0.0261	-0.0289	-0.0472
197	-0.0132	-0.0335	-0.0679
198	-0.0716	-0.0565	-0.0469
199	-0.0672	-0.0688	-0.0533
200	0.0147	-0.0179	0.0165
201	0.0764	0.0305	-0.0118
202	0.0253	0.0154	-0.0129
203	0.0358	0.0449	-0.0156
204	0.0957	0.0575	0.0670
205	0.0379	-0.0393	0.0062
206	0.0504	-0.0040	0.0029
207	0.0111	0.0303	-0.0027
208	-0.0485	-0.0541	-0.0503
209	0.0325	0.0113	0.0432
210	-0.0336	-0.0254	-0.0277
211	0.0217	0.0466	0.0964
212	-0.1058	-0.0878	-0.0710
213	0.0120	0.0442	-0.0070
214	-0.0325	-0.0088	-0.0201
215	-0.0539	-0.0259	-0.0408
216	0.0792	0.0766	0.0346
217	0.1800	0.0980	0.1160
218	0.1115	0.0705	0.1049
219	-0.0127	-0.0664	-0.0457
220	-0.1147	-0.0953	-0.0536
221	0.0507	0.0762	0.1191
222	0.0665	-0.0140	-0.0122
223	0.1267	0.1116	0.1215
224	-0.0425	-0.0473	-0.0443
225	-0.0577	-0.0335	-0.0404
226	0.0982	0.0511	0.0640
227	0.0491	0.0912	0.0807
228	-0.0586	-0.0800	-0.0786
229	0.0361	0.0279	0.0399
230	-0.0055	-0.0031	0.0151
231	-0.0513	-0.0616	-0.0546
232	0.0925	0.1287	0.1215
233	-0.0204	0.0190	-0.0267
234	0.0063	-0.0378	-0.0412
235	0.0913	0.0357	0.0777
236	-0.0453	-0.0504	-0.0417
237	0.0287	0.0371	0.0263
238	-0.0001	-0.0168	-0.0201
239	-0.0672	-0.1041	-0.0502
240	-0.0713	-0.0885	-0.0495
241	0.0415	-0.0311	0.0626
242	-0.0862	-0.0871	-0.0715
243	-0.0073	0.0015	0.0343
244	-0.0260	-0.0218	-0.0516
245	0.1521	0.1076	0.1654
246	-0.0085	-0.0191	-0.0393
247	-0.0202	-0.0504	-0.0409
248	-0.0459	-0.0677	-0.0289
249	-0.0007	-0.0207	0.0006

Source: Emolia / Emilia source archive · SHA-256 0ac4c02fa170fc9e…

p01Speech + burstsP3 curated burst test

Amusement + 5 known burst(s)

Synthetic speech with inserted bursts · P3 synthetic speech/burst mixture · 5.0 s

Tiny Base · values are model estimates, not ground truth

Strongest emotions relative to training

Intoxication Altered States of Consciousness

z +4.71 / +4.19raw 2.61 / 2.32

Embarrassment

z +3.97 / +4.03raw 1.75 / 1.77

Amusement

z +3.57 / +3.57raw 3.16 / 3.16

Teasing

z +2.44 / +2.68raw 1.33 / 1.46

Pleasure Ecstasy

z +1.83 / +2.13raw 1.14 / 1.32

Elation

z +1.96 / +1.95raw 1.44 / 1.43

Confusion

z +1.46 / +1.68raw 0.79 / 0.91

The center of each bar is the S9 teacher median. Positive z is to the right; negative z is to the left. Ranking uses z, not raw teacher units.

Strongest VoiceNet dimensions relative to training

Volatility (VOLT)

z +2.55 / +2.44raw 4.84 / 4.75

Content appropriateness (EXPL)

z +2.46 / +2.35raw 0.88 / 0.84

Playful style (S_PLAY)

z +1.91 / +2.01raw 4.86 / 4.99

Casual style (S_CASU)

z +1.96 / +1.81raw 6.29 / 6.10

Roughness (ROUG)

z +1.70 / +1.52raw 3.55 / 3.38

Disfluency (DFLU)

z +1.69 / +1.48raw 4.49 / 4.25

Dynamic arc (DARC)

z +1.50 / +1.62raw 3.69 / 3.85

All 57 VoiceNet predictions, including raw units, are in the full table below. These seven are ranked by z; the top values may differ from the strongest raw dimensions.

Voice, speed and quality scores in context

Genuineness (0–6)z +1.30 / +1.38raw 4.44 / 4.57

Vocal-burst blend (0–10)z -2.22 / -2.21raw 0.59 / 0.63

Content enjoyment (CE)z -0.69 / -0.76raw 4.09 / 4.03

Production quality (PQ)z -1.24 / -1.80raw 5.95 / 5.46

Speech signal quality, calibratedz -1.83 / -2.42raw 2.57 / 2.28

Background quality, calibratedz -1.44 / -1.29raw 2.05 / 2.19

Overall quality, calibratedz -1.68 / -1.70raw 1.82 / 1.81

P.808 MOS estimatez -1.25 / -1.27raw 2.80 / 2.79

score content enjoymentz -1.73 / -1.98raw 3.98 / 3.91

score overall qualityz -1.50 / -1.48raw 1.89 / 1.90

Background Noisez +0.81 / +0.33raw 1.02 / 0.89

Tempo (TEMP)z +0.57 / +0.62raw 2.80 / 2.85

Arousal (AROU)z +0.76 / +0.79raw 3.23 / 3.26

Valence (VALN)z +0.15 / +0.32raw 2.50 / 2.68

Recording quality (RCQL)z -0.74 / -0.96raw 2.09 / 1.90

Background noise (BKGN)z -0.71 / -0.81raw 2.16 / 2.09

talking speedz -0.59 / -0.08raw 6.83 / 8.74

Characters per second (CPS): 4.64 raw · z -1.17

P3 metadata teacher estimate; not a Whisper output. Reference: 86,334 P3 training teacher values, median 9.03, SD 3.76. Cross-language character counts depend on writing system; compare with care.

Orange speaker embedding reconstruction

Cosine against Orange on this same clip (higher means closer to that teacher vector):

Embedding	Tiny	Base
Timbre · 128D	0.440	0.377
Identity · 250D	0.449	0.368

Vocal-burst regions

Known

Tiny

Base

0 s5.0 s

Purple marks known inserted burst intervals; other vocal sounds may be unlabeled.

Tiny: 1 regions, count-head estimate 3.10; Base: 1 regions, count-head estimate 2.72.

Exact predicted start and end times

Model	Region	Start (s)	End (s)	Duration (s)
Tiny	1	0.18	4.62	4.44
Base	1	0.18	4.62	4.44

Known inserted intervals: 4.03–4.36 s, 0.17–0.72 s, 3.18–3.83 s, 0.26–4.18 s, 4.12–4.60 s

All 192 score slots · raw and z values

#	Target	Tiny raw	Tiny z	Base raw	Base z	Train median	Train SD
Emotion scores Forty clip-level Empathic Insight emotion teacher outputs. Each row evaluates one named emotion score.
0	Affectionemo_Affection	0.061	+0.09	0.184	+0.31	0.007	0.570
1	Amusementemo_Amusement	3.162	+3.57	3.162	+3.57	-0.001	0.885
2	Angeremo_Anger	0.000	-0.01	-0.086	-0.15	0.004	0.613
3	Astonishment Surpriseemo_Astonishment_Surprise	0.217	+0.37	0.167	+0.28	0.005	0.572
4	Aweemo_Awe	-0.029	-0.07	-0.059	-0.14	0.000	0.427
5	Bitternessemo_Bitterness	-0.065	-0.19	-0.021	-0.08	0.013	0.415
6	Concentrationemo_Concentration	-0.066	-0.94	0.011	-0.84	0.634	0.741
7	Confusionemo_Confusion	0.789	+1.46	0.909	+1.68	0.001	0.540
8	Contemplationemo_Contemplation	0.032	-0.08	0.018	-0.11	0.082	0.598
9	Contemptemo_Contempt	-0.075	-0.16	0.010	+0.02	-0.000	0.464
10	Contentmentemo_Contentment	0.528	+1.03	0.651	+1.27	0.000	0.514
11	Disappointmentemo_Disappointment	-0.028	-0.04	-0.014	-0.02	0.000	0.700
12	Disgustemo_Disgust	0.039	+0.06	-0.017	-0.05	0.007	0.489
13	Distressemo_Distress	0.053	+0.07	0.009	+0.01	0.000	0.821
14	Doubtemo_Doubt	0.290	+0.61	0.274	+0.58	0.006	0.466
15	Elationemo_Elation	1.440	+1.96	1.434	+1.95	0.012	0.728
16	Embarrassmentemo_Embarrassment	1.747	+3.97	1.774	+4.03	0.043	0.430
17	Emotional Numbnessemo_Emotional_Numbness	0.075	+0.08	0.045	+0.04	0.004	0.917
18	Fatigue Exhaustionemo_Fatigue_Exhaustion	0.301	+0.51	0.225	+0.37	0.028	0.539
19	Fearemo_Fear	-0.030	-0.07	-0.001	-0.03	0.015	0.610
20	Helplessnessemo_Helplessness	-0.031	-0.04	0.033	+0.05	-0.004	0.696
21	Hope Enthusiasm Optimismemo_Hope_Enthusiasm_Optimism	0.543	+0.56	0.525	+0.54	0.117	0.760
22	Impatience and Irritabilityemo_Impatience_and_Irritability	0.156	+0.01	0.143	-0.01	0.149	0.705
23	Infatuationemo_Infatuation	0.026	+0.08	0.193	+0.39	-0.015	0.533
24	Interestemo_Interest	0.871	-0.79	0.939	-0.72	1.589	0.907
25	Intoxication Altered States of Consciousnessemo_Intoxication_Altered_States_of_Consciousness	2.606	+4.71	2.319	+4.19	-0.025	0.559
26	Jealousy and Envyemo_Jealousy_and_Envy	-0.020	-0.18	0.014	-0.10	0.059	0.442
27	Longingemo_Longing	-0.079	-0.26	0.058	-0.05	0.087	0.632
28	Malevolence Maliceemo_Malevolence_Malice	0.074	+0.04	0.050	-0.01	0.055	0.534
29	Painemo_Pain	0.142	+0.25	0.101	+0.18	-0.002	0.579
30	Pleasure Ecstasyemo_Pleasure_Ecstasy	1.144	+1.83	1.325	+2.13	0.017	0.614
31	Prideemo_Pride	-0.033	-0.07	-0.029	-0.06	0.002	0.509
32	Reliefemo_Relief	-0.012	-0.07	0.010	-0.03	0.033	0.681
33	Sadnessemo_Sadness	-0.007	-0.01	-0.028	-0.04	0.000	0.759
34	Sexual Lustemo_Sexual_Lust	0.685	+1.33	0.756	+1.47	0.030	0.494
35	Shameemo_Shame	0.068	+0.11	0.087	+0.15	0.013	0.510
36	Sournessemo_Sourness	-0.013	-0.02	-0.015	-0.02	-0.005	0.439
37	Teasingemo_Teasing	1.329	+2.44	1.460	+2.68	0.000	0.545
38	Thankfulness Gratitudeemo_Thankfulness_Gratitude	0.037	-0.01	0.030	-0.02	0.041	0.697
39	Triumphemo_Triumph	-0.043	-0.07	-0.038	-0.06	-0.007	0.521
VoiceNet dimensions Fifty-seven VoiceNet voice, delivery, style, and recording dimensions. Codes are expanded in the target column.
40	Perceived voice age (AGEV)vn_AGEV_reg	2.093	-0.72	1.643	-1.08	2.984	1.238
41	Arousal (AROU)vn_AROU_reg	3.229	+0.76	3.264	+0.79	2.359	1.147
42	Arousal shift (ARSH)vn_ARSH_reg	2.180	-0.46	2.013	-0.65	2.580	0.867
43	Vocal attack (ATCK)vn_ATCK_reg	2.504	+0.26	2.741	+0.45	2.162	1.295
44	Background noise (BKGN)vn_BKGN_reg	2.164	-0.71	2.090	-0.81	2.703	0.761
45	Brightness (BRGT)vn_BRGT_reg	1.223	-0.95	1.201	-0.97	1.991	0.813
46	Speech chunking (CHNK)vn_CHNK_reg	0.859	-0.80	0.796	-0.85	1.847	1.239
47	Articulation clarity (CLRT)vn_CLRT_reg	0.588	-1.51	0.528	-1.58	2.018	0.945
48	Cognitive load (COGL)vn_COGL_reg	0.630	-1.38	0.037	-1.94	2.094	1.061
49	Dynamic arc (DARC)vn_DARC_reg	3.688	+1.50	3.847	+1.62	1.615	1.380
50	Disfluency (DFLU)vn_DFLU_reg	4.495	+1.69	4.245	+1.48	2.488	1.184
51	Emphasis (EMPH)vn_EMPH_reg	0.877	-1.14	0.472	-1.40	2.607	1.524
52	Esthetics (ESTH)vn_ESTH_reg	1.479	-1.18	1.431	-1.24	2.402	0.782
53	Content appropriateness (EXPL)vn_EXPL_reg	0.879	+2.46	0.843	+2.35	0.086	0.322
54	Focus (FOCS)vn_FOCS_reg	0.958	-1.26	0.663	-1.53	2.344	1.102
55	Fullness (FULL)vn_FULL_reg	1.861	+0.09	1.554	-0.25	1.778	0.889
56	Perceived gender (GEND)vn_GEND_reg	4.590	+0.34	4.572	+0.33	4.055	1.588
57	Harmonicity (HARM)vn_HARM_reg	3.338	+1.03	3.345	+1.03	2.480	0.836
58	Metallic character (METL)vn_METL_reg	1.570	-0.05	1.748	+0.13	1.621	0.958
59	Pitch range (RANG)vn_RANG_reg	3.129	+0.24	3.233	+0.36	2.914	0.897
60	Recording quality (RCQL)vn_RCQL_reg	2.094	-0.74	1.897	-0.96	2.754	0.888
61	Vocal register (REGS)vn_REGS_reg	1.707	+0.40	1.788	+0.46	1.198	1.268
62	Respiration (RESP)vn_RESP_reg	4.041	+1.29	4.225	+1.46	2.680	1.056
63	Roughness (ROUG)vn_ROUG_reg	3.545	+1.70	3.380	+1.52	2.033	0.887
64	Chest resonance (R_CHST)vn_R_CHST_reg	1.603	-0.63	1.720	-0.49	2.135	0.844
65	Head resonance (R_HEAD)vn_R_HEAD_reg	2.165	+0.02	2.074	-0.09	2.148	0.822
66	Mask resonance (R_MASK)vn_R_MASK_reg	0.712	-1.19	0.644	-1.26	1.908	1.005
67	Mixed resonance (R_MIXD)vn_R_MIXD_reg	0.929	-0.60	0.657	-0.93	1.436	0.841
68	Nasal resonance (R_NASL)vn_R_NASL_reg	3.031	+0.23	2.861	+0.07	2.791	1.047
69	Oral resonance (R_ORAL)vn_R_ORAL_reg	1.981	-0.27	2.032	-0.20	2.184	0.741
70	Throat resonance (R_THRT)vn_R_THRT_reg	1.944	-0.16	1.728	-0.43	2.070	0.803
71	Smoothness (SMTH)vn_SMTH_reg	1.177	-0.88	0.817	-1.21	2.143	1.093
72	Stance (STNC)vn_STNC_reg	1.818	-0.72	1.724	-0.80	2.633	1.137
73	Speech structure (STRU)vn_STRU_reg	0.111	-2.11	0.011	-2.22	2.137	0.958
74	ASMR style (S_ASMR)vn_S_ASMR_reg	0.916	-0.32	0.585	-0.56	1.370	1.411
75	Authoritative style (S_AUTH)vn_S_AUTH_reg	-0.266	-1.30	-0.306	-1.34	1.088	1.043
76	Cartoonish style (S_CART)vn_S_CART_reg	2.894	+0.95	3.017	+1.04	1.560	1.401
77	Casual style (S_CASU)vn_S_CASU_reg	6.292	+1.96	6.103	+1.81	3.793	1.278
78	Conversational style (S_CONV)vn_S_CONV_reg	4.308	+1.30	4.145	+1.18	2.594	1.318
79	Dramatic style (S_DRAM)vn_S_DRAM_reg	3.661	+0.82	3.571	+0.74	2.721	1.148
80	Formal style (S_FORM)vn_S_FORM_reg	-0.204	-1.37	-0.117	-1.29	1.195	1.021
81	Monologue style (S_MONO)vn_S_MONO_reg	0.271	-1.99	0.062	-2.15	2.824	1.284
82	Narrator style (S_NARR)vn_S_NARR_reg	-0.330	-1.13	-0.162	-1.02	1.307	1.446
83	Newsreader style (S_NEWS)vn_S_NEWS_reg	0.031	-0.66	-0.051	-0.81	0.408	0.568
84	Playful style (S_PLAY)vn_S_PLAY_reg	4.858	+1.91	4.990	+2.01	2.352	1.315
85	Ranting or angry style (S_RANT)vn_S_RANT_reg	2.112	+0.70	2.222	+0.78	1.213	1.289
86	Storytelling style (S_STRY)vn_S_STRY_reg	1.405	-0.79	0.997	-1.09	2.480	1.366
87	Teacher or didactic style (S_TECH)vn_S_TECH_reg	0.451	-0.16	0.110	-0.44	0.646	1.227
88	Whispered talking style (S_WHIS)vn_S_WHIS_reg	1.130	-0.29	0.905	-0.43	1.597	1.618
89	Tempo (TEMP)vn_TEMP_reg	2.795	+0.57	2.851	+0.62	2.117	1.190
90	Tension (TENS)vn_TENS_reg	2.518	+1.13	2.316	+0.89	1.559	0.852
91	Valence (VALN)vn_VALN_reg	2.499	+0.15	2.680	+0.32	2.328	1.118
92	Valence shift (VALS)vn_VALS_reg	3.485	+0.90	3.304	+0.73	2.518	1.079
93	Velocity flux (VFLX)vn_VFLX_reg	3.517	+1.04	3.489	+1.02	2.256	1.208
94	Volatility (VOLT)vn_VOLT_reg	4.842	+2.55	4.747	+2.44	2.586	0.886
95	Vulnerability (VULN)vn_VULN_reg	4.172	+1.55	3.878	+1.25	2.648	0.984
96	Warmth (WARM)vn_WARM_reg	1.545	-1.14	1.538	-1.14	2.578	0.909
Genuineness, blend, and legacy quality Genuineness and vocal-burst blend are predicted. R_quality has Ladder training labels but no valid P3 test labels.
97	Genuineness (0–6)genuineness_0_6	4.445	+1.30	4.570	+1.38	2.332	1.621
98	Vocal-burst blend (0–10)blend_0_10	0.592	-2.22	0.635	-2.21	6.676	2.738
99	Legacy R_quality (no P3 test labels)R_quality	0.830	-0.78	0.851	-0.72	1.095	0.338
Empathic Insight Plus extra scores Nineteen additional clip-level teacher scores, including background noise and content enjoyment.
100	Ageeiv_extra:Age	2.635	-2.10	2.699	-1.88	3.250	0.293
101	Arousaleiv_extra:Arousal	2.237	+2.18	2.158	+2.00	1.289	0.435
102	Authenticityeiv_extra:Authenticity	2.725	+0.38	2.731	+0.42	2.667	0.153
103	Background Noiseeiv_extra:Background_Noise	1.020	+0.81	0.894	+0.33	0.808	0.264
104	Confident vs. Hesitanteiv_extra:Confident_vs._Hesitant	1.910	+2.87	1.933	+2.95	1.040	0.303
105	Gendereiv_extra:Gender	-0.196	+0.42	-0.179	+0.44	-0.621	0.999
106	High-Pitched vs. Low-Pitchedeiv_extra:High-Pitched_vs._Low-Pitched	1.499	-1.31	1.530	-1.19	1.827	0.250
107	Monotone vs. Expressiveeiv_extra:Monotone_vs._Expressive	2.469	+1.30	2.495	+1.35	1.859	0.470
108	Recording Qualityeiv_extra:Recording_Quality	1.408	-2.22	1.434	-2.14	2.144	0.332
109	Serious vs. Humorouseiv_extra:Serious_vs._Humorous	2.537	+4.72	2.441	+4.44	0.929	0.340
110	Soft vs. Harsheiv_extra:Soft_vs._Harsh	1.027	+2.33	1.067	+2.46	0.281	0.320
111	Submissive vs. Dominanteiv_extra:Submissive_vs._Dominant	-0.212	-1.81	-0.215	-1.82	0.376	0.324
112	Valenceeiv_extra:Valence	1.252	+3.28	1.508	+3.95	0.005	0.380
113	Vulnerable vs. Emotionally Detachedeiv_extra:Vulnerable_vs._Emotionally_Detached	0.921	-1.81	0.911	-1.84	1.715	0.437
114	Warm vs. Coldeiv_extra:Warm_vs._Cold	0.946	+2.98	1.002	+3.17	0.051	0.300
115	score background qualityeiv_extra:score_background_quality	2.321	-1.42	2.310	-1.43	3.301	0.693
116	score content enjoymenteiv_extra:score_content_enjoyment	3.981	-1.73	3.908	-1.98	4.507	0.303
117	score overall qualityeiv_extra:score_overall_quality	1.890	-1.50	1.902	-1.48	2.652	0.507
118	score speech qualityeiv_extra:score_speech_quality	1.766	-0.28	1.791	-0.11	1.808	0.146
Meta AudioBox Aesthetics Four AudioBox aesthetic teacher outputs. Expansions follow the official Meta model card.
119	Content enjoyment (CE)audiobox:CE	4.093	-0.69	4.025	-0.76	4.799	1.018
120	Content usefulness (CU)audiobox:CU	4.907	-0.74	4.435	-1.21	5.649	1.001
121	Production complexity (PC)audiobox:PC	3.237	+0.56	3.180	+0.53	2.331	1.617
122	Production quality (PQ)audiobox:PQ	5.955	-1.24	5.460	-1.80	7.044	0.879
Microsoft DNSMOS Seven DNSMOS teacher outputs: raw and calibrated SIG/BAK/OVRL estimates plus P.808 MOS.
123	Speech signal quality, rawdnsmos:SIG_raw	2.621	-1.91	2.239	-2.48	3.900	0.669
124	Background quality, rawdnsmos:BAK_raw	1.837	-1.22	2.004	-1.07	3.211	1.124
125	Overall quality, rawdnsmos:OVRL_raw	1.827	-1.55	1.814	-1.56	3.085	0.812
126	Speech signal quality, calibrateddnsmos:SIG	2.573	-1.83	2.275	-2.42	3.488	0.501
127	Background quality, calibrateddnsmos:BAK	2.051	-1.44	2.189	-1.29	3.389	0.928
128	Overall quality, calibrateddnsmos:OVRL	1.823	-1.68	1.809	-1.70	2.840	0.606
129	P.808 MOS estimatednsmos:P808_MOS	2.802	-1.25	2.790	-1.27	3.421	0.496
Vocal-burst count The regression target is log(1 + count). A separate table also reports count error after inverse transformation.
130	Vocal-burst count, log(1 + count)burst_count_log1p	1.411	+2.18	1.315	+2.03	0.000	0.647
VoiceCLAP attributes Sixty-one individual VoiceCLAP attribute teacher scores. The raw 768D VoiceCLAP embedding is stored in sidecars but is not a model output.
131	Affectionvoiceclap_attribute:Affection	0.747	-0.36	0.886	-0.11	0.947	0.554
132	Agevoiceclap_attribute:Age	2.766	-0.85	2.646	-1.07	3.229	0.547
133	Amusementvoiceclap_attribute:Amusement	3.347	+5.17	3.365	+5.20	0.392	0.572
134	Angervoiceclap_attribute:Anger	0.296	-1.38	0.105	-1.75	0.992	0.506
135	Arousalvoiceclap_attribute:Arousal	2.364	+1.52	2.437	+1.63	1.420	0.622
136	Astonishment Surprisevoiceclap_attribute:Astonishment_Surprise	0.928	+0.87	0.832	+0.68	0.509	0.479
137	Authenticityvoiceclap_attribute:Authenticity	2.759	-0.07	2.725	-0.27	2.770	0.167
138	Awevoiceclap_attribute:Awe	-0.089	-2.42	-0.130	-2.58	0.539	0.259
139	Background Noisevoiceclap_attribute:Background_Noise	0.784	+0.82	0.726	+0.60	0.567	0.264
140	Bitternessvoiceclap_attribute:Bitterness	0.202	-1.66	0.173	-1.78	0.592	0.236
141	Concentrationvoiceclap_attribute:Concentration	0.083	-2.13	-0.083	-2.44	1.214	0.531
142	Confident vs. Hesitantvoiceclap_attribute:Confident_vs._Hesitant	1.679	+1.30	1.731	+1.41	1.069	0.468
143	Confusionvoiceclap_attribute:Confusion	0.622	-0.07	0.651	+0.02	0.643	0.334
144	Contemplationvoiceclap_attribute:Contemplation	0.116	-1.64	0.085	-1.71	0.780	0.406
145	Contemptvoiceclap_attribute:Contempt	0.369	-1.00	0.369	-1.00	0.709	0.339
146	Contentmentvoiceclap_attribute:Contentment	0.554	-0.11	0.628	+0.13	0.588	0.307
147	Disappointmentvoiceclap_attribute:Disappointment	0.207	-1.90	0.179	-1.99	0.760	0.291
148	Disgustvoiceclap_attribute:Disgust	0.382	-1.17	0.283	-1.65	0.625	0.207
149	Distressvoiceclap_attribute:Distress	0.084	-2.41	0.073	-2.44	0.927	0.350
150	Doubtvoiceclap_attribute:Doubt	0.406	-0.68	0.402	-0.71	0.535	0.188
151	Elationvoiceclap_attribute:Elation	1.336	+2.01	1.352	+2.05	0.539	0.397
152	Embarrassmentvoiceclap_attribute:Embarrassment	1.530	+3.89	1.525	+3.88	0.307	0.314
153	Emotional Numbnessvoiceclap_attribute:Emotional_Numbness	0.009	-2.46	-0.008	-2.53	0.664	0.266
154	Fatigue Exhaustionvoiceclap_attribute:Fatigue_Exhaustion	0.428	-0.13	0.397	-0.25	0.462	0.261
155	Fearvoiceclap_attribute:Fear	0.307	-1.46	0.298	-1.51	0.618	0.212
156	Gendervoiceclap_attribute:Gender	0.001	+0.15	0.022	+0.17	-0.151	1.005
157	Helplessnessvoiceclap_attribute:Helplessness	0.301	-1.33	0.265	-1.46	0.658	0.268
158	High-Pitched vs. Low-Pitchedvoiceclap_attribute:High-Pitched_vs._Low-Pitched	1.402	-1.17	1.420	-1.12	1.840	0.375
159	Hope Enthusiasm Optimismvoiceclap_attribute:Hope_Enthusiasm_Optimism	0.761	+0.14	0.748	+0.11	0.705	0.396
160	Impatience and Irritabilityvoiceclap_attribute:Impatience_and_Irritability	0.286	-1.42	0.290	-1.41	1.052	0.541
161	Infatuationvoiceclap_attribute:Infatuation	0.407	-0.61	0.457	-0.46	0.608	0.332
162	Interestvoiceclap_attribute:Interest	1.326	-0.62	1.259	-0.77	1.598	0.440
163	Intoxication Altered States of Consciousnessvoiceclap_attribute:Intoxication_Altered_States_of_Consciousness	1.633	+2.44	1.626	+2.43	0.502	0.463
164	Jealousy & Envyvoiceclap_attribute:Jealousy_&_Envy	0.072	-1.84	0.137	-1.58	0.523	0.245
165	Longingvoiceclap_attribute:Longing	0.107	-1.96	0.220	-1.44	0.538	0.220
166	Malevolence Malicevoiceclap_attribute:Malevolence_Malice	0.600	-0.67	0.541	-0.84	0.833	0.346
167	Monotone vs. Expressivevoiceclap_attribute:Monotone_vs._Expressive	2.767	+1.67	2.925	+1.94	1.775	0.594
168	Painvoiceclap_attribute:Pain	0.167	-0.98	0.150	-1.06	0.381	0.218
169	Pleasure Ecstasyvoiceclap_attribute:Pleasure_Ecstasy	1.354	+2.83	1.335	+2.76	0.503	0.301
170	Pridevoiceclap_attribute:Pride	0.051	-2.09	-0.042	-2.35	0.780	0.349
171	Recording Qualityvoiceclap_attribute:Recording_Quality	1.779	-1.63	1.682	-1.93	2.313	0.328
172	Reliefvoiceclap_attribute:Relief	0.403	-1.50	0.478	-1.32	1.025	0.415
173	Sadnessvoiceclap_attribute:Sadness	0.335	-1.33	0.325	-1.36	0.752	0.313
174	Serious vs. Humorousvoiceclap_attribute:Serious_vs._Humorous	3.290	+4.38	3.504	+4.75	0.803	0.568
175	Sexual Lustvoiceclap_attribute:Sexual_Lust	0.745	+0.26	0.678	+0.10	0.635	0.419
176	Shamevoiceclap_attribute:Shame	0.322	-0.72	0.344	-0.65	0.526	0.283
177	Soft vs. Harshvoiceclap_attribute:Soft_vs._Harsh	0.897	+2.05	1.066	+2.52	0.160	0.360
178	Sournessvoiceclap_attribute:Sourness	0.213	-1.70	0.203	-1.73	0.706	0.291
179	Submissive vs. Dominantvoiceclap_attribute:Submissive_vs._Dominant	0.268	-0.99	0.275	-0.97	0.623	0.359
180	Teasingvoiceclap_attribute:Teasing	1.586	+2.76	1.604	+2.81	0.540	0.379
181	Thankfulness Gratitudevoiceclap_attribute:Thankfulness_Gratitude	0.354	-1.95	0.411	-1.84	1.384	0.529
182	Triumphvoiceclap_attribute:Triumph	0.157	-1.56	0.168	-1.53	0.716	0.359
183	Valencevoiceclap_attribute:Valence	2.133	+3.37	2.302	+3.64	-0.007	0.635
184	Vulnerable vs. Emotionally Detachedvoiceclap_attribute:Vulnerable_vs._Emotionally_Detached	1.084	-1.00	0.841	-1.43	1.638	0.556
185	Warm vs. Coldvoiceclap_attribute:Warm_vs._Cold	1.141	+3.02	1.229	+3.24	-0.066	0.400
186	durationvoiceclap_attribute:duration	5.648	-0.83	4.757	-0.97	10.914	6.354
187	score background qualityvoiceclap_attribute:score_background_quality	2.619	-1.26	2.646	-1.20	3.245	0.498
188	score content enjoymentvoiceclap_attribute:score_content_enjoyment	4.572	-0.57	4.507	-1.01	4.656	0.147
189	score overall qualityvoiceclap_attribute:score_overall_quality	2.104	-1.29	2.088	-1.33	2.635	0.412
190	score speech qualityvoiceclap_attribute:score_speech_quality	1.937	+0.67	1.959	+0.98	1.891	0.069
191	talking speedvoiceclap_attribute:talking_speed	6.829	-0.59	8.741	-0.08	9.028	3.756

All Orange embedding components

The cosine above is the meaningful vector-level comparison; component values have no standalone semantic label.

Timbre — all 128 vector components

Dimension	Tiny	Base	Orange teacher
0	0.0009	0.0484	-0.0696
1	-0.0053	-0.1062	-0.0690
2	0.0748	0.0316	-0.0135
3	-0.0072	0.0291	-0.0367
4	-0.0252	-0.0106	-0.0657
5	0.0267	0.0307	0.0492
6	-0.1183	-0.0704	-0.0634
7	-0.0254	-0.0549	-0.0131
8	-0.0492	-0.0715	-0.0423
9	-0.0733	-0.0664	-0.0095
10	0.0351	0.0841	-0.0650
11	-0.0931	-0.0524	-0.0817
12	-0.0437	-0.0571	0.0515
13	-0.0767	-0.0639	-0.0154
14	0.0801	0.0029	-0.0474
15	0.0485	-0.0383	0.1118
16	-0.0652	-0.0650	0.0479
17	0.0305	0.0487	-0.0079
18	-0.0649	-0.0794	-0.0645
19	0.1854	0.1430	0.2097
20	-0.0527	-0.0433	-0.0635
21	-0.0060	-0.0747	-0.0313
22	0.1465	0.1148	0.0865
23	0.0973	0.1863	0.0331
24	-0.0397	-0.0235	0.0181
25	-0.0549	-0.0466	0.0157
26	-0.1084	-0.0968	-0.0656
27	-0.1068	-0.0939	0.1078
28	0.0113	0.0113	0.1198
29	0.0862	0.0719	0.0958
30	-0.0893	-0.1163	-0.0753
31	0.0706	-0.0283	-0.0645
32	0.0479	0.0899	-0.0587
33	-0.1106	-0.1437	-0.0770
34	-0.0172	0.0502	-0.0309
35	-0.0580	-0.0567	0.0195
36	-0.0018	-0.0298	0.0481
37	-0.0828	-0.1372	-0.0828
38	-0.0641	-0.1069	0.1194
39	-0.0125	0.0181	0.0890
40	0.0098	-0.0084	-0.0564
41	-0.0286	-0.1098	-0.0244
42	0.0977	0.0495	-0.0224
43	-0.0908	-0.1278	0.0823
44	-0.0843	-0.1148	-0.0671
45	0.2152	0.2427	0.2278
46	-0.0900	-0.1127	-0.0659
47	0.0702	0.1278	0.2023
48	-0.0137	-0.0578	-0.0682
49	0.2030	0.2340	-0.0171
50	-0.0022	-0.0339	-0.0715
51	0.0414	-0.0165	-0.0400
52	0.0155	-0.0235	-0.0316
53	-0.0408	-0.0585	0.0479
54	0.1122	-0.0211	-0.0591
55	-0.1206	-0.1199	-0.0673
56	0.0126	-0.0469	-0.0663
57	-0.0858	-0.1286	-0.0385
58	0.0755	0.0516	0.0750
59	-0.0320	-0.1054	0.0560
60	0.1969	0.1993	-0.0154
61	0.1168	0.0498	0.1918
62	0.2686	0.2701	0.1799
63	-0.0286	-0.0477	-0.0664
64	-0.1160	-0.0509	-0.0709
65	-0.0202	-0.0312	0.0256
66	0.0736	0.0348	0.0433
67	0.0878	0.1639	-0.0674
68	-0.0855	-0.0856	-0.0739
69	0.0486	-0.0203	0.0656
70	-0.1450	-0.1062	-0.0696
71	-0.1305	-0.1387	-0.0775
72	0.0919	0.1091	0.0264
73	-0.1251	-0.1119	-0.0278
74	-0.0099	-0.0672	-0.0098
75	-0.0683	-0.0805	-0.0849
76	-0.0370	-0.0679	0.0136
77	-0.0721	-0.0432	-0.0638
78	-0.0399	-0.0312	-0.0622
79	-0.0265	-0.0276	0.1785
80	0.0179	-0.0422	-0.0633
81	-0.0138	-0.0332	0.0592
82	-0.0288	0.0093	-0.0585
83	-0.0025	-0.0127	-0.0715
84	-0.0805	-0.0334	-0.0314
85	-0.0515	-0.0545	-0.0338
86	0.0523	0.0140	0.0515
87	-0.1473	-0.1257	-0.0807
88	0.1084	0.0056	-0.0649
89	0.0319	0.0180	-0.0641
90	0.0250	0.0283	0.0132
91	-0.0950	-0.1228	-0.0643
92	0.2198	0.1878	0.0580
93	0.0725	-0.0119	0.0141
94	-0.0824	0.0100	-0.0323
95	0.0254	-0.0348	-0.0242
96	-0.0870	-0.0273	-0.0964
97	0.1221	0.1560	-0.0539
98	-0.0977	-0.0863	0.0419
99	0.0660	-0.0617	0.0988
100	-0.0206	-0.0773	-0.0475
101	-0.1435	-0.1517	-0.0235
102	-0.0265	-0.0218	-0.0466
103	0.1198	0.0809	0.0876
104	-0.0507	-0.0361	-0.0310
105	0.0034	-0.0065	0.2920
106	-0.1450	-0.0697	-0.0840
107	0.0238	-0.0585	-0.0651
108	0.0441	0.0863	-0.0758
109	-0.0633	-0.0221	-0.0685
110	0.0322	0.0444	-0.1039
111	-0.0729	-0.0877	-0.0811
112	-0.0301	0.0502	0.0282
113	-0.0752	-0.0520	0.0845
114	-0.0683	-0.0617	0.1329
115	0.0235	0.0460	0.0678
116	0.0633	-0.0149	0.2361
117	-0.1519	-0.0437	0.0269
118	-0.0931	-0.0899	-0.0681
119	-0.1229	-0.1408	0.0197
120	0.2335	0.1351	0.2057
121	0.1198	0.1379	0.3176
122	-0.0214	0.0133	-0.0718
123	-0.0263	0.0274	-0.0735
124	-0.0591	-0.0823	-0.0975
125	-0.1007	-0.1040	-0.0697
126	-0.0588	-0.0498	0.1172
127	-0.0523	-0.0560	-0.0742

Identity — all 250 vector components

Dimension	Tiny	Base	Orange teacher
0	-0.0087	-0.0057	-0.0012
1	-0.0643	-0.0705	-0.0417
2	-0.0353	-0.0435	0.0270
3	0.0672	0.0573	0.0116
4	-0.0433	-0.0712	-0.0392
5	-0.0239	-0.0431	-0.0450
6	-0.0372	-0.0223	0.0118
7	0.1073	0.0662	0.0488
8	0.0084	0.0630	-0.0162
9	0.0203	0.0594	0.0313
10	-0.0085	0.0311	0.0790
11	-0.0690	-0.0644	-0.0583
12	-0.0690	-0.0512	-0.0369
13	0.0119	0.0152	-0.0168
14	-0.0316	-0.0063	0.1003
15	-0.0465	-0.0379	-0.0508
16	0.2273	0.1961	0.0683
17	-0.1131	-0.1131	-0.0517
18	0.0059	0.0195	0.0594
19	0.0028	0.0369	0.0445
20	-0.0828	-0.0551	-0.0431
21	-0.0749	-0.0612	0.0576
22	-0.0619	-0.0523	-0.0396
23	-0.0034	0.0426	-0.0417
24	-0.0743	-0.0594	-0.0368
25	-0.0220	0.0310	0.0966
26	-0.0065	-0.0310	-0.0286
27	-0.0728	-0.0838	-0.0350
28	-0.0733	-0.0795	0.0726
29	-0.0648	-0.0702	-0.0064
30	0.0272	0.0187	-0.0374
31	0.2124	0.0966	0.2228
32	0.0571	0.1031	-0.0443
33	-0.0007	-0.0462	0.0012
34	0.0738	0.0290	-0.0432
35	-0.0656	-0.0798	-0.0215
36	-0.0629	-0.0612	-0.0455
37	-0.0414	-0.0734	-0.0298
38	0.0425	-0.0163	0.0136
39	-0.0443	-0.0648	-0.0009
40	-0.0961	-0.0995	-0.0499
41	-0.0219	-0.0285	-0.0495
42	-0.0315	-0.0376	-0.0428
43	0.0158	0.0002	-0.0509
44	-0.0446	-0.0211	-0.0518
45	-0.0435	-0.0551	-0.0062
46	-0.0770	-0.0766	-0.0633
47	0.0648	0.1024	-0.0564
48	-0.0489	-0.0156	-0.0180
49	-0.0882	-0.0741	-0.0570
50	0.0924	0.0906	0.0494
51	0.0124	0.0530	-0.0382
52	-0.0797	-0.0898	-0.0405
53	-0.0470	-0.0687	-0.0417
54	0.0624	0.0508	0.1302
55	0.0475	0.0338	0.0362
56	-0.0343	-0.0327	0.0213
57	-0.0358	-0.0428	-0.0078
58	-0.0204	-0.0501	-0.0413
59	-0.0409	-0.0727	-0.0213
60	0.0042	0.0089	0.1555
61	0.0332	0.1238	-0.0400
62	-0.0102	0.0009	-0.0378
63	-0.0014	0.0140	-0.0468
64	-0.0966	-0.0938	-0.0479
65	-0.0183	-0.0129	-0.0526
66	0.0238	0.0215	0.0487
67	0.0325	0.0016	-0.0453
68	-0.0523	-0.0216	-0.0464
69	0.0656	-0.0148	0.1156
70	-0.0844	-0.0931	0.0664
71	-0.0876	-0.0759	-0.0451
72	-0.0181	-0.0199	-0.0477
73	0.0107	-0.0311	0.0157
74	-0.0568	-0.0734	-0.0184
75	-0.0528	-0.0626	0.0016
76	0.0011	-0.0399	-0.0106
77	-0.0109	-0.0194	-0.0512
78	0.0369	0.0288	-0.0117
79	-0.0754	-0.0523	-0.0461
80	0.0491	0.0608	-0.0457
81	-0.0765	-0.0487	-0.0516
82	0.0093	-0.0205	0.0627
83	0.0099	-0.0020	-0.0382
84	-0.0323	-0.0046	0.0326
85	-0.0196	-0.0354	0.0702
86	-0.0940	-0.0659	-0.0410
87	-0.0137	-0.0630	-0.0039
88	0.1859	0.1568	0.1382
89	-0.0129	-0.0424	0.1008
90	-0.0116	-0.0109	-0.0456
91	0.1126	0.1024	0.0351
92	0.0465	0.0265	0.0776
93	0.0020	0.0085	-0.0522
94	-0.1083	-0.1052	-0.0048
95	0.0068	-0.0209	-0.0480
96	-0.0526	-0.0175	-0.0411
97	0.0320	0.0458	-0.0259
98	0.0616	0.0109	0.0123
99	-0.0012	-0.0143	-0.0576
100	0.1540	0.1253	0.1256
101	0.0085	-0.0004	-0.0435
102	0.1136	0.1095	-0.0514
103	0.0465	0.0336	0.0609
104	-0.0696	-0.0780	-0.0599
105	-0.1041	-0.0988	-0.0598
106	-0.0388	-0.0189	-0.0354
107	-0.0264	-0.0202	-0.0412
108	-0.0443	-0.0494	-0.0342
109	-0.0802	-0.0909	-0.0442
110	-0.0451	-0.0898	-0.0547
111	-0.0640	-0.1009	-0.0379
112	-0.0966	-0.0755	-0.0080
113	-0.0008	-0.0203	-0.0784
114	-0.0560	-0.0795	-0.0010
115	0.1402	0.0709	0.1644
116	-0.0068	0.0179	-0.0825
117	0.0435	0.0160	0.0240
118	0.0177	-0.0038	-0.0174
119	0.0414	0.0859	0.0567
120	-0.0475	-0.0498	0.1506
121	-0.0754	-0.0719	-0.0195
122	-0.0222	-0.0401	0.0236
123	0.0536	0.0702	0.1274
124	-0.0539	-0.0421	-0.0459
125	-0.0446	-0.0442	-0.0447
126	0.0316	-0.0109	-0.0884
127	-0.0690	-0.0326	-0.0473
128	-0.0754	-0.0630	0.1912
129	-0.0042	-0.0105	0.0903
130	-0.0552	-0.0616	-0.0462
131	-0.0422	-0.0379	-0.0403
132	-0.0494	-0.0103	-0.0487
133	-0.0366	-0.0462	0.1251
134	0.0114	0.0112	-0.0517
135	0.0361	0.0311	-0.0463
136	-0.1009	-0.0848	-0.0493
137	-0.0775	-0.0838	-0.0427
138	-0.0797	-0.0684	-0.0406
139	-0.0523	-0.0655	0.1073
140	0.0264	-0.0131	0.0309
141	-0.0441	-0.0841	-0.0455
142	-0.0555	-0.0444	-0.0197
143	-0.0759	-0.0644	-0.0861
144	-0.0645	-0.0787	-0.0479
145	-0.0993	-0.0759	0.0152
146	0.0168	-0.0062	-0.0551
147	0.0304	0.0185	0.0511
148	-0.0945	-0.1024	0.0678
149	-0.0094	-0.0306	0.1002
150	-0.0018	-0.0225	0.0114
151	-0.0632	-0.0576	-0.0524
152	-0.0104	0.0231	-0.0510
153	-0.0531	-0.0798	-0.0362
154	0.0443	0.0634	0.1158
155	-0.0850	-0.1045	-0.0600
156	-0.0195	-0.0501	0.1265
157	0.0173	-0.0408	0.0367
158	-0.0220	0.0059	0.0311
159	0.0353	0.0841	-0.0427
160	-0.0328	-0.0455	-0.0437
161	-0.0706	-0.0395	0.1062
162	-0.0871	-0.0626	-0.0534
163	-0.1004	-0.1131	-0.0512
164	-0.0579	-0.0413	-0.0404
165	0.0961	0.0662	0.0934
166	-0.0119	-0.0208	-0.0535
167	-0.0621	-0.0533	-0.0583
168	0.0414	0.0220	0.0643
169	0.0190	0.0141	-0.0525
170	-0.0701	-0.0422	-0.0430
171	0.0512	0.0392	-0.0405
172	0.0089	0.0071	-0.0533
173	-0.0690	-0.0440	0.0109
174	-0.0366	-0.0591	0.0132
175	-0.0082	-0.0150	-0.0180
176	-0.0412	-0.0365	-0.0391
177	-0.0550	-0.0616	-0.0223
178	0.1094	0.0766	0.0960
179	-0.0552	-0.0651	-0.0505
180	-0.0309	-0.0834	-0.0526
181	0.0791	0.1002	0.1079
182	-0.0227	0.0064	-0.0039
183	0.1259	0.1360	0.0806
184	-0.0770	-0.0469	-0.0467
185	-0.0050	-0.0252	-0.0550
186	-0.0621	-0.0583	-0.0554
187	0.0269	0.0180	-0.0523
188	-0.0234	0.0069	-0.0432
189	0.0076	0.0358	-0.0237
190	0.0039	-0.0177	-0.0622
191	-0.0267	-0.0437	0.1111
192	-0.1237	-0.1417	-0.0557
193	0.1110	0.0791	0.1255
194	-0.0462	-0.0469	0.0864
195	0.0680	0.0490	0.0599
196	-0.0860	-0.0601	-0.0420
197	0.0982	0.0916	0.1381
198	-0.0834	-0.0684	-0.0444
199	0.0544	0.1102	-0.0392
200	-0.0149	-0.0433	-0.0531
201	0.0420	0.0042	-0.0433
202	-0.0544	-0.0626	-0.0095
203	-0.0406	-0.0056	-0.0573
204	-0.0441	-0.0755	0.0175
205	0.0935	0.0673	0.0902
206	0.0369	-0.0016	0.0247
207	0.0770	0.0128	0.1342
208	-0.0433	-0.0508	0.0714
209	-0.0781	-0.0630	-0.0208
210	0.0749	0.0870	-0.0056
211	0.0000	0.0258	0.0703
212	0.0021	0.0112	-0.0394
213	0.0277	-0.0566	-0.0602
214	0.0096	-0.0151	0.0742
215	-0.0028	0.0153	-0.0386
216	-0.0336	-0.1067	-0.0550
217	-0.0092	-0.0390	0.0312
218	0.0483	0.0587	0.1064
219	-0.0696	-0.0526	-0.0316
220	-0.0374	-0.0245	-0.0508
221	0.0238	0.0159	0.0037
222	0.0828	0.1790	0.0370
223	0.1221	0.1195	0.1217
224	-0.1046	-0.1167	-0.0420
225	-0.0380	-0.0383	-0.0383
226	0.0786	0.0787	0.0517
227	0.0020	0.0555	0.1240
228	-0.0358	-0.0191	-0.0686
229	-0.0297	-0.0231	-0.0504
230	-0.0765	-0.0770	0.0790
231	-0.0728	-0.0752	0.0759
232	0.0244	0.0153	0.0778
233	0.0635	0.0659	-0.0939
234	-0.0605	-0.0419	-0.0390
235	0.1986	0.1775	0.1089
236	-0.0672	-0.0515	-0.0395
237	-0.0275	0.0118	-0.0469
238	-0.0786	-0.0884	-0.0504
239	0.0110	0.0121	-0.0475
240	0.0356	0.0181	0.0487
241	0.0390	0.0196	0.0596
242	-0.0685	-0.0773	0.0046
243	-0.0866	-0.0880	-0.0591
244	-0.0034	-0.0360	-0.0489
245	0.0223	-0.0211	0.0323
246	0.1025	0.1711	-0.0372
247	0.0251	0.0680	0.1266
248	-0.0759	-0.0612	-0.0526
249	-0.0157	-0.0160	-0.0638

Source: P3 source-disjoint test split · p3_02000795 · SHA-256 7102cb4fbccb5806…

p02Speech + burstsP3 curated burst test

Anger + 2 known burst(s)

Synthetic speech with inserted bursts · P3 synthetic speech/burst mixture · 12.0 s

Tiny Base · values are model estimates, not ground truth

Strongest emotions relative to training

Triumph

z +3.74 / +4.63raw 1.94 / 2.40

Malevolence Malice

z +3.87 / +4.56raw 2.12 / 2.49

Pride

z +3.02 / +3.74raw 1.54 / 1.90

Contempt

z +2.56 / +3.14raw 1.19 / 1.46

Anger

z +2.19 / +2.96raw 1.34 / 1.82

Jealousy and Envy

z +1.47 / +2.60raw 0.71 / 1.21

Bitterness

z +2.53 / +2.50raw 1.07 / 1.05

The center of each bar is the S9 teacher median. Positive z is to the right; negative z is to the left. Ranking uses z, not raw teacher units.

Strongest VoiceNet dimensions relative to training

Tension (TENS)

z +2.23 / +2.78raw 3.45 / 3.92

Roughness (ROUG)

z +1.90 / +2.47raw 3.72 / 4.22

Dramatic style (S_DRAM)

z +1.93 / +2.23raw 4.94 / 5.28

Focus (FOCS)

z +1.86 / +2.11raw 4.39 / 4.67

Metallic character (METL)

z +1.66 / +2.08raw 3.21 / 3.61

Content appropriateness (EXPL)

z +1.66 / +2.05raw 0.62 / 0.75

Cartoonish style (S_CART)

z +1.57 / +1.77raw 3.77 / 4.04

All 57 VoiceNet predictions, including raw units, are in the full table below. These seven are ranked by z; the top values may differ from the strongest raw dimensions.

Voice, speed and quality scores in context

Genuineness (0–6)z +0.10 / +0.04raw 2.49 / 2.40

Vocal-burst blend (0–10)z -0.35 / -0.39raw 5.73 / 5.61

Content enjoyment (CE)z -0.41 / -0.49raw 4.38 / 4.30

Production quality (PQ)z -1.40 / -1.62raw 5.81 / 5.62

Speech signal quality, calibratedz -3.94 / -4.30raw 1.52 / 1.34

Background quality, calibratedz -2.27 / -2.49raw 1.28 / 1.08

Overall quality, calibratedz -2.70 / -2.86raw 1.20 / 1.11

P.808 MOS estimatez -1.03 / -1.16raw 2.91 / 2.84

score content enjoymentz -0.08 / +0.21raw 4.48 / 4.57

score overall qualityz -2.39 / -2.31raw 1.44 / 1.48

Background Noisez +0.35 / +0.45raw 0.90 / 0.93

Tempo (TEMP)z +0.71 / +1.05raw 2.96 / 3.37

Arousal (AROU)z +0.68 / +0.91raw 3.15 / 3.40

Valence (VALN)z +0.53 / +0.07raw 2.92 / 2.41

Recording quality (RCQL)z -1.54 / -1.64raw 1.39 / 1.30

Background noise (BKGN)z -0.87 / -0.85raw 2.04 / 2.06

talking speedz -0.30 / +0.18raw 7.88 / 9.71

Characters per second (CPS): 9.27 raw · z +0.06

P3 metadata teacher estimate; not a Whisper output. Reference: 86,334 P3 training teacher values, median 9.03, SD 3.76. Cross-language character counts depend on writing system; compare with care.

Orange speaker embedding reconstruction

Cosine against Orange on this same clip (higher means closer to that teacher vector):

Embedding	Tiny	Base
Timbre · 128D	0.800	0.826
Identity · 250D	0.732	0.750

Vocal-burst regions

Known

Tiny

Base

0 s12.0 s

Purple marks known inserted burst intervals; other vocal sounds may be unlabeled.

Tiny: 3 regions, count-head estimate 1.78; Base: 2 regions, count-head estimate 1.43.

Exact predicted start and end times

Model	Region	Start (s)	End (s)	Duration (s)
Tiny	1	5.40	5.76	0.36
Tiny	2	6.02	6.36	0.34
Tiny	3	11.16	11.22	0.06
Base	1	5.44	5.76	0.32
Base	2	6.02	6.34	0.32

Known inserted intervals: 5.44–5.72 s, 6.03–6.35 s

All 192 score slots · raw and z values

#	Target	Tiny raw	Tiny z	Base raw	Base z	Train median	Train SD
Emotion scores Forty clip-level Empathic Insight emotion teacher outputs. Each row evaluates one named emotion score.
0	Affectionemo_Affection	0.218	+0.37	-0.035	-0.07	0.007	0.570
1	Amusementemo_Amusement	0.368	+0.42	0.402	+0.45	-0.001	0.885
2	Angeremo_Anger	1.344	+2.19	1.820	+2.96	0.004	0.613
3	Astonishment Surpriseemo_Astonishment_Surprise	0.320	+0.55	0.222	+0.38	0.005	0.572
4	Aweemo_Awe	0.164	+0.38	0.112	+0.26	0.000	0.427
5	Bitternessemo_Bitterness	1.065	+2.53	1.052	+2.50	0.013	0.415
6	Concentrationemo_Concentration	1.333	+0.94	1.264	+0.85	0.634	0.741
7	Confusionemo_Confusion	0.073	+0.13	-0.051	-0.10	0.001	0.540
8	Contemplationemo_Contemplation	0.466	+0.64	0.168	+0.14	0.082	0.598
9	Contemptemo_Contempt	1.189	+2.56	1.456	+3.14	-0.000	0.464
10	Contentmentemo_Contentment	0.266	+0.52	-0.037	-0.07	0.000	0.514
11	Disappointmentemo_Disappointment	0.593	+0.85	0.309	+0.44	0.000	0.700
12	Disgustemo_Disgust	1.073	+2.18	1.046	+2.12	0.007	0.489
13	Distressemo_Distress	0.560	+0.68	0.501	+0.61	0.000	0.821
14	Doubtemo_Doubt	0.137	+0.28	0.025	+0.04	0.006	0.466
15	Elationemo_Elation	0.646	+0.87	0.859	+1.16	0.012	0.728
16	Embarrassmentemo_Embarrassment	-0.015	-0.14	-0.025	-0.16	0.043	0.430
17	Emotional Numbnessemo_Emotional_Numbness	0.165	+0.18	0.437	+0.47	0.004	0.917
18	Fatigue Exhaustionemo_Fatigue_Exhaustion	-0.034	-0.12	-0.013	-0.08	0.028	0.539
19	Fearemo_Fear	0.287	+0.45	0.322	+0.50	0.015	0.610
20	Helplessnessemo_Helplessness	0.103	+0.15	-0.009	-0.01	-0.004	0.696
21	Hope Enthusiasm Optimismemo_Hope_Enthusiasm_Optimism	0.870	+0.99	1.046	+1.22	0.117	0.760
22	Impatience and Irritabilityemo_Impatience_and_Irritability	0.785	+0.90	1.209	+1.50	0.149	0.705
23	Infatuationemo_Infatuation	0.396	+0.77	0.261	+0.52	-0.015	0.533
24	Interestemo_Interest	2.535	+1.04	2.435	+0.93	1.589	0.907
25	Intoxication Altered States of Consciousnessemo_Intoxication_Altered_States_of_Consciousness	0.234	+0.46	0.301	+0.58	-0.025	0.559
26	Jealousy and Envyemo_Jealousy_and_Envy	0.709	+1.47	1.211	+2.60	0.059	0.442
27	Longingemo_Longing	0.823	+1.16	0.378	+0.46	0.087	0.632
28	Malevolence Maliceemo_Malevolence_Malice	2.121	+3.87	2.489	+4.56	0.055	0.534
29	Painemo_Pain	0.054	+0.10	0.020	+0.04	-0.002	0.579
30	Pleasure Ecstasyemo_Pleasure_Ecstasy	0.590	+0.93	0.710	+1.13	0.017	0.614
31	Prideemo_Pride	1.536	+3.02	1.902	+3.74	0.002	0.509
32	Reliefemo_Relief	0.040	+0.01	0.005	-0.04	0.033	0.681
33	Sadnessemo_Sadness	0.382	+0.50	0.174	+0.23	0.000	0.759
34	Sexual Lustemo_Sexual_Lust	0.799	+1.56	1.161	+2.29	0.030	0.494
35	Shameemo_Shame	0.050	+0.07	0.016	+0.01	0.013	0.510
36	Sournessemo_Sourness	0.799	+1.83	0.891	+2.04	-0.005	0.439
37	Teasingemo_Teasing	0.415	+0.76	0.507	+0.93	0.000	0.545
38	Thankfulness Gratitudeemo_Thankfulness_Gratitude	0.214	+0.25	0.061	+0.03	0.041	0.697
39	Triumphemo_Triumph	1.942	+3.74	2.404	+4.63	-0.007	0.521
VoiceNet dimensions Fifty-seven VoiceNet voice, delivery, style, and recording dimensions. Codes are expanded in the target column.
40	Perceived voice age (AGEV)vn_AGEV_reg	2.754	-0.19	2.748	-0.19	2.984	1.238
41	Arousal (AROU)vn_AROU_reg	3.145	+0.68	3.405	+0.91	2.359	1.147
42	Arousal shift (ARSH)vn_ARSH_reg	3.505	+1.07	3.214	+0.73	2.580	0.867
43	Vocal attack (ATCK)vn_ATCK_reg	2.715	+0.43	3.322	+0.90	2.162	1.295
44	Background noise (BKGN)vn_BKGN_reg	2.040	-0.87	2.058	-0.85	2.703	0.761
45	Brightness (BRGT)vn_BRGT_reg	0.824	-1.44	0.925	-1.31	1.991	0.813
46	Speech chunking (CHNK)vn_CHNK_reg	2.225	+0.31	2.211	+0.29	1.847	1.239
47	Articulation clarity (CLRT)vn_CLRT_reg	0.873	-1.21	0.828	-1.26	2.018	0.945
48	Cognitive load (COGL)vn_COGL_reg	1.210	-0.83	1.177	-0.86	2.094	1.061
49	Dynamic arc (DARC)vn_DARC_reg	3.039	+1.03	3.581	+1.42	1.615	1.380
50	Disfluency (DFLU)vn_DFLU_reg	1.844	-0.54	2.104	-0.32	2.488	1.184
51	Emphasis (EMPH)vn_EMPH_reg	3.424	+0.54	4.056	+0.95	2.607	1.524
52	Esthetics (ESTH)vn_ESTH_reg	1.811	-0.76	1.701	-0.90	2.402	0.782
53	Content appropriateness (EXPL)vn_EXPL_reg	0.623	+1.66	0.746	+2.05	0.086	0.322
54	Focus (FOCS)vn_FOCS_reg	4.392	+1.86	4.669	+2.11	2.344	1.102
55	Fullness (FULL)vn_FULL_reg	0.128	-1.86	0.329	-1.63	1.778	0.889
56	Perceived gender (GEND)vn_GEND_reg	4.584	+0.33	5.051	+0.63	4.055	1.588
57	Harmonicity (HARM)vn_HARM_reg	1.437	-1.25	1.262	-1.46	2.480	0.836
58	Metallic character (METL)vn_METL_reg	3.210	+1.66	3.614	+2.08	1.621	0.958
59	Pitch range (RANG)vn_RANG_reg	3.780	+0.96	3.943	+1.15	2.914	0.897
60	Recording quality (RCQL)vn_RCQL_reg	1.387	-1.54	1.296	-1.64	2.754	0.888
61	Vocal register (REGS)vn_REGS_reg	1.064	-0.11	0.824	-0.30	1.198	1.268
62	Respiration (RESP)vn_RESP_reg	3.511	+0.79	3.858	+1.12	2.680	1.056
63	Roughness (ROUG)vn_ROUG_reg	3.717	+1.90	4.220	+2.47	2.033	0.887
64	Chest resonance (R_CHST)vn_R_CHST_reg	2.224	+0.11	2.120	-0.02	2.135	0.844
65	Head resonance (R_HEAD)vn_R_HEAD_reg	1.761	-0.47	1.526	-0.76	2.148	0.822
66	Mask resonance (R_MASK)vn_R_MASK_reg	1.359	-0.55	1.397	-0.51	1.908	1.005
67	Mixed resonance (R_MIXD)vn_R_MIXD_reg	1.069	-0.44	0.860	-0.68	1.436	0.841
68	Nasal resonance (R_NASL)vn_R_NASL_reg	2.753	-0.04	2.747	-0.04	2.791	1.047
69	Oral resonance (R_ORAL)vn_R_ORAL_reg	1.536	-0.87	1.684	-0.67	2.184	0.741
70	Throat resonance (R_THRT)vn_R_THRT_reg	2.071	+0.00	2.200	+0.16	2.070	0.803
71	Smoothness (SMTH)vn_SMTH_reg	1.693	-0.41	1.552	-0.54	2.143	1.093
72	Stance (STNC)vn_STNC_reg	3.988	+1.19	4.024	+1.22	2.633	1.137
73	Speech structure (STRU)vn_STRU_reg	1.674	-0.48	1.463	-0.70	2.137	0.958
74	ASMR style (S_ASMR)vn_S_ASMR_reg	1.207	-0.12	0.978	-0.28	1.370	1.411
75	Authoritative style (S_AUTH)vn_S_AUTH_reg	2.591	+1.44	2.526	+1.38	1.088	1.043
76	Cartoonish style (S_CART)vn_S_CART_reg	3.765	+1.57	4.043	+1.77	1.560	1.401
77	Casual style (S_CASU)vn_S_CASU_reg	4.326	+0.42	4.508	+0.56	3.793	1.278
78	Conversational style (S_CONV)vn_S_CONV_reg	-0.363	-2.24	-0.057	-2.01	2.594	1.318
79	Dramatic style (S_DRAM)vn_S_DRAM_reg	4.942	+1.93	5.280	+2.23	2.721	1.148
80	Formal style (S_FORM)vn_S_FORM_reg	0.261	-0.92	0.001	-1.17	1.195	1.021
81	Monologue style (S_MONO)vn_S_MONO_reg	1.498	-1.03	1.304	-1.18	2.824	1.284
82	Narrator style (S_NARR)vn_S_NARR_reg	0.270	-0.72	0.471	-0.58	1.307	1.446
83	Newsreader style (S_NEWS)vn_S_NEWS_reg	0.238	-0.30	0.299	-0.19	0.408	0.568
84	Playful style (S_PLAY)vn_S_PLAY_reg	2.906	+0.42	2.888	+0.41	2.352	1.315
85	Ranting or angry style (S_RANT)vn_S_RANT_reg	2.591	+1.07	3.039	+1.42	1.213	1.289
86	Storytelling style (S_STRY)vn_S_STRY_reg	4.247	+1.29	4.302	+1.33	2.480	1.366
87	Teacher or didactic style (S_TECH)vn_S_TECH_reg	-0.908	-1.27	-1.194	-1.50	0.646	1.227
88	Whispered talking style (S_WHIS)vn_S_WHIS_reg	2.672	+0.67	2.254	+0.41	1.597	1.618
89	Tempo (TEMP)vn_TEMP_reg	2.964	+0.71	3.372	+1.05	2.117	1.190
90	Tension (TENS)vn_TENS_reg	3.454	+2.23	3.922	+2.78	1.559	0.852
91	Valence (VALN)vn_VALN_reg	2.919	+0.53	2.407	+0.07	2.328	1.118
92	Valence shift (VALS)vn_VALS_reg	2.602	+0.08	2.549	+0.03	2.518	1.079
93	Velocity flux (VFLX)vn_VFLX_reg	2.546	+0.24	3.032	+0.64	2.256	1.208
94	Volatility (VOLT)vn_VOLT_reg	3.885	+1.47	4.089	+1.70	2.586	0.886
95	Vulnerability (VULN)vn_VULN_reg	0.651	-2.03	0.434	-2.25	2.648	0.984
96	Warmth (WARM)vn_WARM_reg	1.439	-1.25	1.305	-1.40	2.578	0.909
Genuineness, blend, and legacy quality Genuineness and vocal-burst blend are predicted. R_quality has Ladder training labels but no valid P3 test labels.
97	Genuineness (0–6)genuineness_0_6	2.494	+0.10	2.395	+0.04	2.332	1.621
98	Vocal-burst blend (0–10)blend_0_10	5.726	-0.35	5.614	-0.39	6.676	2.738
99	Legacy R_quality (no P3 test labels)R_quality	1.009	-0.25	0.989	-0.31	1.095	0.338
Empathic Insight Plus extra scores Nineteen additional clip-level teacher scores, including background noise and content enjoyment.
100	Ageeiv_extra:Age	3.254	+0.01	3.122	-0.44	3.250	0.293
101	Arousaleiv_extra:Arousal	2.703	+3.25	2.901	+3.70	1.289	0.435
102	Authenticityeiv_extra:Authenticity	2.718	+0.33	2.604	-0.41	2.667	0.153
103	Background Noiseeiv_extra:Background_Noise	0.901	+0.35	0.928	+0.45	0.808	0.264
104	Confident vs. Hesitanteiv_extra:Confident_vs._Hesitant	1.095	+0.18	1.015	-0.08	1.040	0.303
105	Gendereiv_extra:Gender	-0.391	+0.23	-0.732	-0.11	-0.621	0.999
106	High-Pitched vs. Low-Pitchedeiv_extra:High-Pitched_vs._Low-Pitched	2.042	+0.86	2.024	+0.79	1.827	0.250
107	Monotone vs. Expressiveeiv_extra:Monotone_vs._Expressive	3.039	+2.51	3.017	+2.46	1.859	0.470
108	Recording Qualityeiv_extra:Recording_Quality	2.231	+0.26	2.225	+0.24	2.144	0.332
109	Serious vs. Humorouseiv_extra:Serious_vs._Humorous	0.970	+0.12	0.974	+0.13	0.929	0.340
110	Soft vs. Harsheiv_extra:Soft_vs._Harsh	0.109	-0.54	-0.108	-1.22	0.281	0.320
111	Submissive vs. Dominanteiv_extra:Submissive_vs._Dominant	1.267	+2.75	1.490	+3.44	0.376	0.324
112	Valenceeiv_extra:Valence	-0.101	-0.28	-0.273	-0.73	0.005	0.380
113	Vulnerable vs. Emotionally Detachedeiv_extra:Vulnerable_vs._Emotionally_Detached	1.459	-0.58	1.526	-0.43	1.715	0.437
114	Warm vs. Coldeiv_extra:Warm_vs._Cold	-0.308	-1.20	-0.369	-1.40	0.051	0.300
115	score background qualityeiv_extra:score_background_quality	1.795	-2.17	1.806	-2.16	3.301	0.693
116	score content enjoymenteiv_extra:score_content_enjoyment	4.483	-0.08	4.570	+0.21	4.507	0.303
117	score overall qualityeiv_extra:score_overall_quality	1.442	-2.39	1.482	-2.31	2.652	0.507
118	score speech qualityeiv_extra:score_speech_quality	1.569	-1.64	1.562	-1.69	1.808	0.146
Meta AudioBox Aesthetics Four AudioBox aesthetic teacher outputs. Expansions follow the official Meta model card.
119	Content enjoyment (CE)audiobox:CE	4.380	-0.41	4.297	-0.49	4.799	1.018
120	Content usefulness (CU)audiobox:CU	4.177	-1.47	4.286	-1.36	5.649	1.001
121	Production complexity (PC)audiobox:PC	4.786	+1.52	4.111	+1.10	2.331	1.617
122	Production quality (PQ)audiobox:PQ	5.810	-1.40	5.618	-1.62	7.044	0.879
Microsoft DNSMOS Seven DNSMOS teacher outputs: raw and calibrated SIG/BAK/OVRL estimates plus P.808 MOS.
123	Speech signal quality, rawdnsmos:SIG_raw	1.361	-3.79	1.152	-4.11	3.900	0.669
124	Background quality, rawdnsmos:BAK_raw	1.160	-1.82	0.984	-1.98	3.211	1.124
125	Overall quality, rawdnsmos:OVRL_raw	1.096	-2.45	1.007	-2.56	3.085	0.812
126	Speech signal quality, calibrateddnsmos:SIG	1.516	-3.94	1.336	-4.30	3.488	0.501
127	Background quality, calibrateddnsmos:BAK	1.282	-2.27	1.079	-2.49	3.389	0.928
128	Overall quality, calibrateddnsmos:OVRL	1.202	-2.70	1.108	-2.86	2.840	0.606
129	P.808 MOS estimatednsmos:P808_MOS	2.908	-1.03	2.844	-1.16	3.421	0.496
Vocal-burst count The regression target is log(1 + count). A separate table also reports count error after inverse transformation.
130	Vocal-burst count, log(1 + count)burst_count_log1p	1.021	+1.58	0.889	+1.37	0.000	0.647
VoiceCLAP attributes Sixty-one individual VoiceCLAP attribute teacher scores. The raw 768D VoiceCLAP embedding is stored in sidecars but is not a model output.
131	Affectionvoiceclap_attribute:Affection	0.891	-0.10	0.997	+0.09	0.947	0.554
132	Agevoiceclap_attribute:Age	2.910	-0.58	2.802	-0.78	3.229	0.547
133	Amusementvoiceclap_attribute:Amusement	0.969	+1.01	1.050	+1.15	0.392	0.572
134	Angervoiceclap_attribute:Anger	1.798	+1.59	2.095	+2.18	0.992	0.506
135	Arousalvoiceclap_attribute:Arousal	2.992	+2.53	2.992	+2.53	1.420	0.622
136	Astonishment Surprisevoiceclap_attribute:Astonishment_Surprise	0.833	+0.68	1.096	+1.23	0.509	0.479
137	Authenticityvoiceclap_attribute:Authenticity	2.694	-0.46	2.701	-0.41	2.770	0.167
138	Awevoiceclap_attribute:Awe	0.740	+0.77	0.795	+0.99	0.539	0.259
139	Background Noisevoiceclap_attribute:Background_Noise	0.868	+1.14	0.932	+1.38	0.567	0.264
140	Bitternessvoiceclap_attribute:Bitterness	0.782	+0.80	0.883	+1.23	0.592	0.236
141	Concentrationvoiceclap_attribute:Concentration	0.944	-0.51	0.787	-0.80	1.214	0.531
142	Confident vs. Hesitantvoiceclap_attribute:Confident_vs._Hesitant	1.098	+0.06	1.196	+0.27	1.069	0.468
143	Confusionvoiceclap_attribute:Confusion	0.702	+0.18	0.735	+0.27	0.643	0.334
144	Contemplationvoiceclap_attribute:Contemplation	0.450	-0.81	0.514	-0.66	0.780	0.406
145	Contemptvoiceclap_attribute:Contempt	1.290	+1.72	1.269	+1.65	0.709	0.339
146	Contentmentvoiceclap_attribute:Contentment	0.512	-0.25	0.458	-0.42	0.588	0.307
147	Disappointmentvoiceclap_attribute:Disappointment	0.944	+0.63	1.024	+0.91	0.760	0.291
148	Disgustvoiceclap_attribute:Disgust	0.908	+1.37	1.043	+2.02	0.625	0.207
149	Distressvoiceclap_attribute:Distress	1.077	+0.43	1.192	+0.76	0.927	0.350
150	Doubtvoiceclap_attribute:Doubt	0.359	-0.93	0.334	-1.07	0.535	0.188
151	Elationvoiceclap_attribute:Elation	1.576	+2.61	1.639	+2.77	0.539	0.397
152	Embarrassmentvoiceclap_attribute:Embarrassment	0.365	+0.18	0.344	+0.12	0.307	0.314
153	Emotional Numbnessvoiceclap_attribute:Emotional_Numbness	0.424	-0.90	0.489	-0.66	0.664	0.266
154	Fatigue Exhaustionvoiceclap_attribute:Fatigue_Exhaustion	0.262	-0.77	0.405	-0.22	0.462	0.261
155	Fearvoiceclap_attribute:Fear	0.670	+0.24	0.738	+0.57	0.618	0.212
156	Gendervoiceclap_attribute:Gender	-0.294	-0.14	-0.433	-0.28	-0.151	1.005
157	Helplessnessvoiceclap_attribute:Helplessness	0.374	-1.06	0.444	-0.80	0.658	0.268
158	High-Pitched vs. Low-Pitchedvoiceclap_attribute:High-Pitched_vs._Low-Pitched	2.111	+0.72	2.085	+0.65	1.840	0.375
159	Hope Enthusiasm Optimismvoiceclap_attribute:Hope_Enthusiasm_Optimism	2.208	+3.80	2.127	+3.59	0.705	0.396
160	Impatience and Irritabilityvoiceclap_attribute:Impatience_and_Irritability	2.200	+2.12	2.577	+2.82	1.052	0.541
161	Infatuationvoiceclap_attribute:Infatuation	0.877	+0.81	0.843	+0.71	0.608	0.332
162	Interestvoiceclap_attribute:Interest	2.117	+1.18	2.012	+0.94	1.598	0.440
163	Intoxication Altered States of Consciousnessvoiceclap_attribute:Intoxication_Altered_States_of_Consciousness	1.083	+1.25	1.340	+1.81	0.502	0.463
164	Jealousy & Envyvoiceclap_attribute:Jealousy_&_Envy	0.859	+1.38	0.848	+1.33	0.523	0.245
165	Longingvoiceclap_attribute:Longing	0.526	-0.05	0.562	+0.11	0.538	0.220
166	Malevolence Malicevoiceclap_attribute:Malevolence_Malice	1.663	+2.40	1.663	+2.40	0.833	0.346
167	Monotone vs. Expressivevoiceclap_attribute:Monotone_vs._Expressive	3.224	+2.44	3.261	+2.50	1.775	0.594
168	Painvoiceclap_attribute:Pain	0.395	+0.06	0.455	+0.34	0.381	0.218
169	Pleasure Ecstasyvoiceclap_attribute:Pleasure_Ecstasy	1.029	+1.75	1.022	+1.72	0.503	0.301
170	Pridevoiceclap_attribute:Pride	1.314	+1.53	1.412	+1.81	0.780	0.349
171	Recording Qualityvoiceclap_attribute:Recording_Quality	2.279	-0.10	2.142	-0.52	2.313	0.328
172	Reliefvoiceclap_attribute:Relief	0.507	-1.25	0.527	-1.20	1.025	0.415
173	Sadnessvoiceclap_attribute:Sadness	0.462	-0.93	0.495	-0.82	0.752	0.313
174	Serious vs. Humorousvoiceclap_attribute:Serious_vs._Humorous	1.059	+0.45	1.320	+0.91	0.803	0.568
175	Sexual Lustvoiceclap_attribute:Sexual_Lust	1.211	+1.37	1.247	+1.46	0.635	0.419
176	Shamevoiceclap_attribute:Shame	0.412	-0.40	0.398	-0.46	0.526	0.283
177	Soft vs. Harshvoiceclap_attribute:Soft_vs._Harsh	-0.507	-1.85	-0.611	-2.14	0.160	0.360
178	Sournessvoiceclap_attribute:Sourness	0.951	+0.85	0.960	+0.88	0.706	0.291
179	Submissive vs. Dominantvoiceclap_attribute:Submissive_vs._Dominant	1.579	+2.67	1.736	+3.10	0.623	0.359
180	Teasingvoiceclap_attribute:Teasing	1.029	+1.29	1.079	+1.42	0.540	0.379
181	Thankfulness Gratitudevoiceclap_attribute:Thankfulness_Gratitude	1.917	+1.01	1.799	+0.78	1.384	0.529
182	Triumphvoiceclap_attribute:Triumph	1.662	+2.63	1.785	+2.98	0.716	0.359
183	Valencevoiceclap_attribute:Valence	0.010	+0.03	-0.256	-0.39	-0.007	0.635
184	Vulnerable vs. Emotionally Detachedvoiceclap_attribute:Vulnerable_vs._Emotionally_Detached	1.318	-0.58	1.403	-0.42	1.638	0.556
185	Warm vs. Coldvoiceclap_attribute:Warm_vs._Cold	-0.260	-0.48	-0.370	-0.76	-0.066	0.400
186	durationvoiceclap_attribute:duration	11.657	+0.12	11.147	+0.04	10.914	6.354
187	score background qualityvoiceclap_attribute:score_background_quality	2.475	-1.54	2.510	-1.47	3.245	0.498
188	score content enjoymentvoiceclap_attribute:score_content_enjoyment	4.716	+0.41	4.742	+0.58	4.656	0.147
189	score overall qualityvoiceclap_attribute:score_overall_quality	2.037	-1.45	2.056	-1.40	2.635	0.412
190	score speech qualityvoiceclap_attribute:score_speech_quality	1.827	-0.93	1.840	-0.73	1.891	0.069
191	talking speedvoiceclap_attribute:talking_speed	7.884	-0.30	9.714	+0.18	9.028	3.756

All Orange embedding components

The cosine above is the meaningful vector-level comparison; component values have no standalone semantic label.

Timbre — all 128 vector components

Dimension	Tiny	Base	Orange teacher
0	0.0013	0.0433	-0.0739
1	-0.0136	-0.0879	-0.0739
2	0.0526	0.0449	0.1046
3	-0.0581	-0.0490	-0.0124
4	0.0256	0.0371	-0.0196
5	-0.1324	-0.1011	-0.0941
6	0.0842	0.1156	-0.0039
7	-0.0820	-0.0383	0.0127
8	-0.0142	-0.0172	-0.0557
9	-0.0147	0.0015	-0.0498
10	0.2309	0.2877	0.2683
11	0.0185	0.0757	0.0417
12	0.0045	0.0204	0.0180
13	-0.0621	-0.0399	-0.0181
14	0.1882	0.1200	0.1236
15	-0.1353	-0.1193	-0.0666
16	-0.1574	-0.1382	-0.0920
17	-0.0868	-0.0911	-0.0773
18	-0.0276	0.0345	0.0870
19	-0.0838	-0.1074	-0.0703
20	-0.0879	-0.0678	-0.0744
21	-0.0739	-0.0738	-0.0684
22	0.0234	0.0261	0.0812
23	0.0246	0.0637	0.0675
24	-0.0375	-0.0587	-0.0311
25	-0.0893	-0.1005	-0.0652
26	-0.0298	0.0028	0.0211
27	-0.1176	-0.0911	-0.0693
28	-0.0022	0.0336	0.0931
29	-0.0194	-0.0559	-0.0059
30	-0.0012	0.0294	-0.0800
31	-0.0860	-0.0437	-0.0686
32	0.1743	0.1972	0.0774
33	-0.0599	-0.0437	0.0387
34	0.0248	-0.0051	0.0834
35	-0.0338	0.0064	-0.0659
36	-0.0174	-0.0540	-0.0423
37	-0.1154	-0.0619	-0.0444
38	0.0776	0.0502	0.0151
39	-0.0805	-0.0458	-0.0637
40	-0.1500	-0.0873	-0.0717
41	-0.0131	0.0037	0.0079
42	-0.0301	-0.0272	-0.0750
43	-0.0978	-0.0961	-0.0716
44	-0.1088	-0.0678	-0.0714
45	-0.0041	-0.0217	0.0051
46	-0.0012	0.0192	-0.0701
47	-0.0563	-0.0729	-0.0115
48	-0.1088	-0.0779	-0.0587
49	-0.0636	-0.0769	-0.0751
50	-0.0452	-0.0253	-0.0760
51	0.1654	0.1620	0.1561
52	-0.0296	-0.0515	0.0080
53	-0.0923	-0.0930	-0.0757
54	-0.0581	-0.0659	-0.0356
55	-0.0489	-0.0462	-0.0130
56	0.0119	0.0543	-0.0488
57	-0.0555	-0.0854	-0.0283
58	-0.0732	-0.0449	-0.0430
59	-0.1037	-0.0779	-0.0745
60	-0.0439	-0.0364	0.0175
61	-0.0151	-0.0388	-0.0684
62	0.0281	-0.0101	-0.0028
63	-0.0923	-0.0663	-0.0706
64	0.0901	0.1080	0.0431
65	-0.0309	-0.0421	-0.0550
66	0.0212	-0.0675	-0.1028
67	0.1596	0.1319	0.0508
68	0.0244	0.0389	-0.0019
69	0.1794	0.1646	0.1873
70	-0.0160	-0.0305	0.0731
71	0.1051	0.1696	0.1891
72	0.2529	0.2387	0.2201
73	-0.0128	-0.0108	0.0094
74	-0.0511	-0.0625	-0.0804
75	0.0669	0.0294	0.0139
76	0.1118	0.0904	0.1998
77	0.0311	0.0631	0.1659
78	0.0581	0.0898	0.0537
79	0.0588	0.0757	0.1925
80	0.1037	0.1275	0.0715
81	0.2000	0.2161	0.1992
82	0.0511	0.0835	0.1165
83	0.0056	0.0669	0.0662
84	-0.1228	-0.0904	-0.0921
85	0.0125	0.0146	0.0434
86	0.0257	0.0088	0.1166
87	-0.0008	-0.0319	0.0468
88	-0.0614	-0.0421	-0.0690
89	-0.0382	0.0067	-0.0120
90	0.1037	0.0917	0.1327
91	0.0265	0.0418	0.0115
92	0.0161	-0.0110	-0.0211
93	-0.1000	-0.1168	-0.0726
94	0.0403	0.0177	0.0035
95	0.0511	0.0115	-0.0099
96	-0.0313	-0.0297	0.0579
97	-0.0030	0.0287	0.0735
98	-0.0540	-0.0751	-0.0751
99	0.2368	0.1872	0.1240
100	0.0654	0.0443	0.0477
101	0.2029	0.2462	0.1376
102	-0.0956	-0.0754	-0.0795
103	0.0551	0.0258	0.0178
104	-0.0311	-0.0128	-0.0727
105	-0.0252	-0.0062	-0.0199
106	-0.0225	0.0008	0.1113
107	0.0496	0.0644	0.0766
108	0.0447	0.0198	0.0457
109	-0.0162	-0.0069	0.0014
110	0.0798	0.0898	0.0048
111	0.1059	0.1087	0.2241
112	-0.0178	-0.0170	0.1010
113	-0.0684	-0.0754	-0.1046
114	0.2794	0.3203	0.2737
115	0.1551	0.1275	0.1503
116	-0.0563	-0.0688	-0.0637
117	-0.0292	0.0038	0.0119
118	-0.0691	-0.0581	-0.0723
119	-0.1007	-0.0816	-0.0718
120	-0.0309	-0.0366	-0.0764
121	-0.0300	-0.0757	-0.0476
122	-0.0592	-0.0394	-0.0764
123	-0.0629	-0.0606	-0.0394
124	0.0489	0.0023	-0.0269
125	-0.1015	-0.0936	-0.0741
126	0.0052	-0.0037	0.0838
127	-0.0351	-0.0729	-0.0208

Identity — all 250 vector components

Dimension	Tiny	Base	Orange teacher
0	0.0913	0.1021	0.0930
1	-0.0703	-0.0704	-0.0417
2	0.0121	0.0464	-0.0412
3	-0.0136	-0.0513	-0.0284
4	-0.0389	-0.0196	-0.0392
5	-0.0178	0.0087	0.0295
6	0.0982	0.1339	0.0870
7	-0.0298	-0.0149	-0.0100
8	-0.0247	0.0053	-0.0765
9	0.0445	0.0927	0.1493
10	-0.0342	-0.0486	-0.0453
11	0.0288	0.0436	-0.0018
12	-0.0578	-0.0441	0.0245
13	0.1546	0.1576	0.1284
14	-0.0907	-0.0917	-0.0616
15	0.1000	0.0942	0.1400
16	-0.1250	-0.1031	-0.0698
17	-0.0058	-0.0332	-0.0518
18	0.0480	0.0530	0.1569
19	-0.0453	-0.0283	-0.0684
20	0.0371	-0.0254	-0.0432
21	-0.0488	-0.0439	-0.0400
22	-0.0101	-0.0431	-0.0180
23	-0.0907	-0.0709	-0.0417
24	-0.0123	-0.0362	-0.0368
25	-0.0607	-0.0759	-0.0793
26	0.1256	0.1487	0.0190
27	-0.0327	-0.0231	-0.0351
28	0.0301	-0.0003	0.0504
29	-0.0584	-0.0459	-0.0415
30	-0.0102	-0.0347	-0.0375
31	0.0381	0.0228	0.1704
32	0.0814	0.0947	0.0432
33	0.0849	0.1408	0.0859
34	-0.1041	-0.0957	-0.0515
35	0.1093	0.0932	-0.0001
36	-0.0407	-0.0419	0.0437
37	-0.0082	-0.0244	-0.0298
38	-0.0181	-0.0059	-0.0166
39	-0.1041	-0.1190	-0.0643
40	-0.0692	-0.0617	-0.0500
41	-0.0631	-0.0419	-0.0495
42	-0.0410	-0.0305	0.0147
43	0.0404	0.0089	-0.0485
44	0.0209	-0.0053	-0.0519
45	0.0312	0.0109	0.0035
46	-0.0217	-0.0525	-0.0634
47	0.1000	0.0947	0.0350
48	-0.0058	-0.0496	-0.0461
49	-0.0421	-0.0402	-0.0050
50	0.1128	0.0967	0.0976
51	-0.0311	-0.0178	-0.0340
52	-0.0424	-0.0389	-0.0425
53	-0.0509	-0.0306	-0.0417
54	-0.0439	-0.0446	-0.0231
55	0.0773	0.0783	0.0323
56	-0.0512	-0.0615	-0.0593
57	-0.0095	0.0085	0.0220
58	-0.0266	-0.0112	-0.0117
59	0.1145	0.0897	0.0952
60	-0.0692	-0.0813	-0.0452
61	0.1331	0.1497	-0.0401
62	-0.0936	-0.0644	-0.0379
63	-0.0113	0.0088	-0.0469
64	-0.0616	-0.0607	-0.0480
65	-0.0355	-0.0322	-0.0526
66	0.1023	0.0877	0.1108
67	0.0404	-0.0023	-0.0032
68	0.0033	-0.0134	0.0090
69	-0.0837	-0.1096	-0.0797
70	-0.0375	-0.0491	-0.0343
71	-0.0253	-0.0315	-0.0452
72	-0.0677	-0.0421	0.0764
73	-0.0872	-0.1006	-0.0770
74	-0.0831	-0.0674	-0.0465
75	0.1372	0.1081	0.1122
76	0.0977	0.0952	0.1376
77	-0.0228	0.0175	0.0354
78	0.0244	0.0141	0.0371
79	-0.0427	-0.0224	-0.0461
80	-0.0663	-0.0421	-0.0458
81	-0.0477	-0.0605	-0.0516
82	0.1256	0.1309	0.1698
83	-0.0622	-0.0568	-0.0383
84	0.0208	0.0407	0.0513
85	-0.0187	-0.0488	-0.0461
86	-0.0273	-0.0411	-0.0411
87	-0.0075	-0.0191	-0.0367
88	0.0208	0.0057	0.0286
89	-0.0202	-0.0580	-0.0417
90	0.0256	0.0394	-0.0457
91	-0.0427	-0.0335	-0.0412
92	-0.0049	-0.0107	0.0531
93	-0.0613	-0.0627	-0.0523
94	-0.0453	-0.0858	-0.0746
95	0.0605	0.1378	0.0181
96	-0.0738	-0.0573	-0.0412
97	0.0500	0.0350	0.0999
98	0.0762	0.0456	0.0580
99	-0.0773	-0.0654	-0.0576
100	0.0538	0.0622	0.1366
101	-0.0459	-0.0407	-0.0435
102	-0.0625	-0.0345	-0.0366
103	-0.1017	-0.0987	-0.0761
104	-0.0488	-0.0102	-0.0600
105	0.0407	0.0426	-0.0599
106	-0.0671	-0.0664	-0.0355
107	-0.0353	-0.0217	-0.0413
108	-0.0488	-0.0513	-0.0343
109	0.0017	-0.0058	-0.0443
110	-0.0416	-0.0066	-0.0205
111	0.1232	0.0907	0.0460
112	0.0104	0.0402	0.0428
113	-0.0315	-0.0739	-0.0786
114	-0.0767	-0.0654	-0.0642
115	-0.0240	-0.0649	-0.0326
116	0.0628	0.0907	0.0450
117	-0.1232	-0.1190	-0.0751
118	-0.0860	-0.0714	-0.0601
119	0.0427	0.0523	0.0248
120	0.0163	0.0228	-0.0247
121	0.0378	0.0436	0.0730
122	-0.0924	-0.0863	-0.0435
123	0.0279	-0.0094	-0.0476
124	-0.0085	-0.0274	-0.0214
125	-0.0558	-0.0449	-0.0448
126	0.1046	0.1348	0.1593
127	-0.0324	-0.0330	-0.0474
128	-0.0602	-0.0763	-0.0574
129	-0.0219	-0.0439	0.0078
130	-0.0549	-0.0061	-0.0323
131	-0.0416	-0.0399	-0.0403
132	-0.0238	-0.0219	-0.0189
133	-0.0401	-0.0456	-0.0455
134	0.0889	0.0818	0.0174
135	0.0045	0.0148	0.0587
136	-0.0211	-0.0568	-0.0353
137	-0.0791	-0.0632	-0.0428
138	-0.0517	-0.0555	-0.0406
139	-0.0503	-0.0783	-0.0471
140	-0.0031	0.0399	-0.0288
141	-0.0639	-0.0449	-0.0456
142	-0.0555	-0.0530	-0.0398
143	-0.0195	-0.0030	-0.0862
144	0.0013	0.0429	-0.0480
145	-0.0097	0.0059	0.0047
146	0.1308	0.1120	0.1117
147	0.0750	0.1001	0.0393
148	0.0895	0.0394	0.0912
149	-0.0622	-0.0622	-0.0593
150	-0.0497	-0.0468	-0.0453
151	0.0605	0.0555	-0.0525
152	0.0124	-0.0008	0.0778
153	0.1442	0.0917	0.0193
154	0.0715	0.0587	0.0124
155	-0.0055	-0.0617	-0.0601
156	-0.0246	-0.0754	-0.0461
157	0.0820	0.0597	0.0365
158	-0.0314	-0.0320	0.0384
159	-0.1104	-0.0763	-0.0539
160	0.0558	0.0560	0.1549
161	-0.1110	-0.1497	-0.1008
162	0.0709	0.1185	0.0405
163	-0.0503	-0.0617	-0.0513
164	-0.0436	-0.0538	-0.0404
165	-0.0913	-0.0739	-0.0232
166	-0.0199	-0.0092	-0.0536
167	-0.1093	-0.1165	-0.0584
168	0.0482	0.0115	0.0266
169	0.0034	0.0337	0.0211
170	0.0273	0.0327	0.1466
171	-0.0121	-0.0138	-0.0405
172	0.0744	0.0788	0.0352
173	0.0291	0.0213	-0.0354
174	-0.0182	-0.0233	-0.0371
175	-0.0497	-0.0873	-0.0667
176	-0.0674	-0.0719	-0.0392
177	-0.0041	-0.0019	0.0563
178	-0.0514	-0.0513	-0.0409
179	0.0363	0.0219	-0.0113
180	-0.0392	-0.0449	-0.0527
181	-0.0040	0.0191	-0.0179
182	-0.0401	-0.0516	-0.0398
183	-0.0430	-0.0325	-0.0469
184	-0.0301	-0.0320	-0.0468
185	-0.0994	-0.0749	-0.0551
186	0.0407	-0.0185	0.0472
187	-0.0526	-0.0813	-0.0524
188	0.0465	0.0640	0.0405
189	-0.0283	-0.0327	-0.0730
190	0.1052	0.1051	0.0811
191	-0.0102	-0.0006	0.0265
192	0.0387	0.0232	0.0409
193	0.0564	0.0478	0.1102
194	-0.0526	-0.0439	0.0435
195	-0.0590	-0.0602	-0.0437
196	0.0346	0.0014	0.0188
197	-0.0520	-0.0436	-0.0369
198	-0.0523	-0.0523	-0.0445
199	-0.0471	-0.0387	-0.0506
200	-0.0167	-0.0186	-0.0090
201	-0.0497	-0.0273	-0.0434
202	-0.1006	-0.1398	-0.0958
203	-0.0163	-0.0350	-0.0574
204	0.1442	0.1408	0.1459
205	0.0610	0.0416	0.1215
206	-0.0375	-0.0237	0.0526
207	0.0076	0.0404	0.0043
208	-0.0671	-0.0724	-0.0478
209	-0.0066	0.0090	0.0319
210	0.0564	0.0300	0.0637
211	-0.0276	-0.0073	-0.0354
212	0.0360	0.0364	-0.0008
213	0.1639	0.1205	0.0663
214	0.0488	0.0258	0.0256
215	-0.0014	-0.0006	-0.0387
216	0.1163	0.1081	0.0686
217	0.0050	0.0434	0.0211
218	0.1436	0.1239	0.0928
219	-0.0837	-0.0295	-0.0553
220	-0.0288	-0.0024	-0.0137
221	0.0291	0.0175	-0.0399
222	-0.0584	-0.0374	-0.0540
223	-0.0410	-0.0550	-0.0369
224	0.0866	0.0793	0.2059
225	0.0026	-0.0285	-0.0383
226	0.0750	0.0468	0.0052
227	-0.0605	-0.0714	-0.0608
228	0.0500	0.0190	-0.0005
229	0.0114	0.0097	0.0132
230	-0.0028	0.0115	-0.0469
231	0.0349	0.0749	0.0408
232	-0.0185	-0.0374	-0.0299
233	0.0741	0.0622	0.0567
234	-0.0421	-0.0352	-0.0391
235	-0.0082	-0.0065	0.0339
236	-0.0465	-0.0543	-0.0395
237	0.0186	0.0086	-0.0092
238	-0.0439	-0.0496	-0.0505
239	0.0005	-0.0058	-0.0259
240	-0.0225	-0.0399	-0.0469
241	0.0442	0.0429	0.0869
242	-0.0953	-0.1041	-0.0678
243	0.0663	0.1190	0.2343
244	-0.0027	-0.0085	-0.0490
245	-0.0228	-0.0332	0.0566
246	-0.0674	-0.0397	-0.0373
247	0.1942	0.1368	0.1653
248	-0.0025	-0.0273	0.0230
249	0.0680	0.0320	0.0079

Source: P3 source-disjoint test split · p3_02007119 · SHA-256 ed8104e92c44a469…

p03Speech + burstsP3 curated burst test

Astonishment Surprise + 3 known burst(s)

Synthetic speech with inserted bursts · P3 synthetic speech/burst mixture · 8.0 s

Tiny Base · values are model estimates, not ground truth

Strongest emotions relative to training

Astonishment Surprise

z +2.85 / +3.16raw 1.63 / 1.81

Disgust

z +2.22 / +1.76raw 1.10 / 0.87

Teasing

z +1.95 / +1.86raw 1.06 / 1.01

Relief

z +0.70 / +1.47raw 0.51 / 1.03

Anger

z +0.96 / +1.41raw 0.59 / 0.87

Malevolence Malice

z +1.08 / +1.14raw 0.63 / 0.66

Contempt

z +1.07 / +0.87raw 0.49 / 0.40

The center of each bar is the S9 teacher median. Positive z is to the right; negative z is to the left. Ranking uses z, not raw teacher units.

Strongest VoiceNet dimensions relative to training

Chest resonance (R_CHST)

z +2.24 / +2.27raw 4.02 / 4.05

Warmth (WARM)

z +2.18 / +1.99raw 4.56 / 4.39

Narrator style (S_NARR)

z +1.57 / +2.15raw 3.57 / 4.41

Roughness (ROUG)

z +1.39 / +1.85raw 3.26 / 3.68

Content appropriateness (EXPL)

z +1.84 / +1.23raw 0.68 / 0.48

Volatility (VOLT)

z +0.97 / +1.73raw 3.44 / 4.12

Storytelling style (S_STRY)

z +1.25 / +1.61raw 4.19 / 4.68

All 57 VoiceNet predictions, including raw units, are in the full table below. These seven are ranked by z; the top values may differ from the strongest raw dimensions.

Voice, speed and quality scores in context

Genuineness (0–6)z -0.48 / -0.32raw 1.56 / 1.81

Vocal-burst blend (0–10)z -2.11 / -2.55raw 0.89 / -0.30

Content enjoyment (CE)z +0.58 / +0.54raw 5.39 / 5.35

Production quality (PQ)z +1.14 / +1.01raw 8.04 / 7.93

Speech signal quality, calibratedz +0.11 / -0.06raw 3.54 / 3.46

Background quality, calibratedz +0.56 / +0.40raw 3.91 / 3.76

Overall quality, calibratedz +0.59 / +0.35raw 3.20 / 3.05

P.808 MOS estimatez +0.22 / +0.29raw 3.53 / 3.56

score content enjoymentz +0.47 / +0.45raw 4.65 / 4.64

score overall qualityz +0.62 / +0.65raw 2.97 / 2.98

Background Noisez -0.49 / -0.32raw 0.68 / 0.72

Tempo (TEMP)z -0.19 / -0.19raw 1.89 / 1.89

Arousal (AROU)z -0.39 / -0.02raw 1.91 / 2.33

Valence (VALN)z -0.34 / -0.35raw 1.95 / 1.93

Recording quality (RCQL)z +0.34 / +0.69raw 3.06 / 3.37

Background noise (BKGN)z +0.50 / +1.29raw 3.09 / 3.69

talking speedz +0.30 / +0.37raw 10.14 / 10.42

Characters per second (CPS): 9.16 raw · z +0.03

P3 metadata teacher estimate; not a Whisper output. Reference: 86,334 P3 training teacher values, median 9.03, SD 3.76. Cross-language character counts depend on writing system; compare with care.

Orange speaker embedding reconstruction

Cosine against Orange on this same clip (higher means closer to that teacher vector):

Embedding	Tiny	Base
Timbre · 128D	0.875	0.887
Identity · 250D	0.812	0.819

Vocal-burst regions

Known

Tiny

Base

0 s8.0 s

Purple marks known inserted burst intervals; other vocal sounds may be unlabeled.

Tiny: 3 regions, count-head estimate 4.02; Base: 3 regions, count-head estimate 4.36.

Exact predicted start and end times

Model	Region	Start (s)	End (s)	Duration (s)
Tiny	1	0.02	0.50	0.48
Tiny	2	5.76	6.34	0.58
Tiny	3	6.78	7.72	0.94
Base	1	0.02	0.50	0.48
Base	2	5.74	6.34	0.60
Base	3	6.78	7.70	0.92

Known inserted intervals: 5.76–6.33 s, 6.79–7.70 s, 0.02–0.47 s

All 192 score slots · raw and z values

#	Target	Tiny raw	Tiny z	Base raw	Base z	Train median	Train SD
Emotion scores Forty clip-level Empathic Insight emotion teacher outputs. Each row evaluates one named emotion score.
0	Affectionemo_Affection	0.163	+0.27	0.156	+0.26	0.007	0.570
1	Amusementemo_Amusement	0.939	+1.06	0.922	+1.04	-0.001	0.885
2	Angeremo_Anger	0.591	+0.96	0.871	+1.41	0.004	0.613
3	Astonishment Surpriseemo_Astonishment_Surprise	1.632	+2.85	1.814	+3.16	0.005	0.572
4	Aweemo_Awe	0.090	+0.21	0.070	+0.16	0.000	0.427
5	Bitternessemo_Bitterness	0.069	+0.14	0.011	-0.00	0.013	0.415
6	Concentrationemo_Concentration	0.237	-0.54	0.217	-0.56	0.634	0.741
7	Confusionemo_Confusion	0.218	+0.40	0.272	+0.50	0.001	0.540
8	Contemplationemo_Contemplation	0.020	-0.10	0.027	-0.09	0.082	0.598
9	Contemptemo_Contempt	0.494	+1.07	0.404	+0.87	-0.000	0.464
10	Contentmentemo_Contentment	-0.012	-0.02	0.012	+0.02	0.000	0.514
11	Disappointmentemo_Disappointment	0.142	+0.20	0.090	+0.13	0.000	0.700
12	Disgustemo_Disgust	1.096	+2.22	0.870	+1.76	0.007	0.489
13	Distressemo_Distress	0.173	+0.21	0.216	+0.26	0.000	0.821
14	Doubtemo_Doubt	0.257	+0.54	0.181	+0.38	0.006	0.466
15	Elationemo_Elation	0.484	+0.65	0.689	+0.93	0.012	0.728
16	Embarrassmentemo_Embarrassment	0.186	+0.33	0.241	+0.46	0.043	0.430
17	Emotional Numbnessemo_Emotional_Numbness	-0.013	-0.02	-0.056	-0.07	0.004	0.917
18	Fatigue Exhaustionemo_Fatigue_Exhaustion	0.035	+0.01	0.050	+0.04	0.028	0.539
19	Fearemo_Fear	0.376	+0.59	0.350	+0.55	0.015	0.610
20	Helplessnessemo_Helplessness	0.002	+0.01	0.011	+0.02	-0.004	0.696
21	Hope Enthusiasm Optimismemo_Hope_Enthusiasm_Optimism	0.314	+0.26	0.336	+0.29	0.117	0.760
22	Impatience and Irritabilityemo_Impatience_and_Irritability	0.631	+0.68	0.765	+0.87	0.149	0.705
23	Infatuationemo_Infatuation	0.260	+0.52	0.105	+0.22	-0.015	0.533
24	Interestemo_Interest	1.697	+0.12	1.606	+0.02	1.589	0.907
25	Intoxication Altered States of Consciousnessemo_Intoxication_Altered_States_of_Consciousness	0.032	+0.10	0.019	+0.08	-0.025	0.559
26	Jealousy and Envyemo_Jealousy_and_Envy	0.130	+0.16	0.106	+0.11	0.059	0.442
27	Longingemo_Longing	0.126	+0.06	-0.042	-0.20	0.087	0.632
28	Malevolence Maliceemo_Malevolence_Malice	0.634	+1.08	0.665	+1.14	0.055	0.534
29	Painemo_Pain	0.136	+0.24	0.104	+0.18	-0.002	0.579
30	Pleasure Ecstasyemo_Pleasure_Ecstasy	0.484	+0.76	0.564	+0.89	0.017	0.614
31	Prideemo_Pride	0.066	+0.13	0.108	+0.21	0.002	0.509
32	Reliefemo_Relief	0.513	+0.70	1.032	+1.47	0.033	0.681
33	Sadnessemo_Sadness	-0.040	-0.05	0.035	+0.05	0.000	0.759
34	Sexual Lustemo_Sexual_Lust	0.328	+0.60	0.221	+0.39	0.030	0.494
35	Shameemo_Shame	0.073	+0.12	0.059	+0.09	0.013	0.510
36	Sournessemo_Sourness	0.368	+0.85	0.218	+0.51	-0.005	0.439
37	Teasingemo_Teasing	1.064	+1.95	1.014	+1.86	0.000	0.545
38	Thankfulness Gratitudeemo_Thankfulness_Gratitude	0.166	+0.18	0.365	+0.47	0.041	0.697
39	Triumphemo_Triumph	0.249	+0.49	0.509	+0.99	-0.007	0.521
VoiceNet dimensions Fifty-seven VoiceNet voice, delivery, style, and recording dimensions. Codes are expanded in the target column.
40	Perceived voice age (AGEV)vn_AGEV_reg	3.048	+0.05	3.186	+0.16	2.984	1.238
41	Arousal (AROU)vn_AROU_reg	1.911	-0.39	2.331	-0.02	2.359	1.147
42	Arousal shift (ARSH)vn_ARSH_reg	2.800	+0.25	3.710	+1.30	2.580	0.867
43	Vocal attack (ATCK)vn_ATCK_reg	1.396	-0.59	1.427	-0.57	2.162	1.295
44	Background noise (BKGN)vn_BKGN_reg	3.086	+0.50	3.686	+1.29	2.703	0.761
45	Brightness (BRGT)vn_BRGT_reg	2.007	+0.02	2.225	+0.29	1.991	0.813
46	Speech chunking (CHNK)vn_CHNK_reg	2.391	+0.44	2.159	+0.25	1.847	1.239
47	Articulation clarity (CLRT)vn_CLRT_reg	1.754	-0.28	1.941	-0.08	2.018	0.945
48	Cognitive load (COGL)vn_COGL_reg	1.350	-0.70	1.153	-0.89	2.094	1.061
49	Dynamic arc (DARC)vn_DARC_reg	1.743	+0.09	2.868	+0.91	1.615	1.380
50	Disfluency (DFLU)vn_DFLU_reg	2.063	-0.36	2.261	-0.19	2.488	1.184
51	Emphasis (EMPH)vn_EMPH_reg	3.835	+0.81	4.584	+1.30	2.607	1.524
52	Esthetics (ESTH)vn_ESTH_reg	2.736	+0.43	2.799	+0.51	2.402	0.782
53	Content appropriateness (EXPL)vn_EXPL_reg	0.679	+1.84	0.482	+1.23	0.086	0.322
54	Focus (FOCS)vn_FOCS_reg	3.321	+0.89	3.845	+1.36	2.344	1.102
55	Fullness (FULL)vn_FULL_reg	2.225	+0.50	2.503	+0.82	1.778	0.889
56	Perceived gender (GEND)vn_GEND_reg	6.034	+1.25	6.059	+1.26	4.055	1.588
57	Harmonicity (HARM)vn_HARM_reg	1.773	-0.85	1.624	-1.02	2.480	0.836
58	Metallic character (METL)vn_METL_reg	1.233	-0.40	1.549	-0.07	1.621	0.958
59	Pitch range (RANG)vn_RANG_reg	3.294	+0.42	3.602	+0.77	2.914	0.897
60	Recording quality (RCQL)vn_RCQL_reg	3.057	+0.34	3.370	+0.69	2.754	0.888
61	Vocal register (REGS)vn_REGS_reg	0.294	-0.71	0.137	-0.84	1.198	1.268
62	Respiration (RESP)vn_RESP_reg	3.321	+0.61	3.444	+0.72	2.680	1.056
63	Roughness (ROUG)vn_ROUG_reg	3.263	+1.39	3.676	+1.85	2.033	0.887
64	Chest resonance (R_CHST)vn_R_CHST_reg	4.025	+2.24	4.051	+2.27	2.135	0.844
65	Head resonance (R_HEAD)vn_R_HEAD_reg	1.622	-0.64	1.780	-0.45	2.148	0.822
66	Mask resonance (R_MASK)vn_R_MASK_reg	1.217	-0.69	1.243	-0.66	1.908	1.005
67	Mixed resonance (R_MIXD)vn_R_MIXD_reg	2.409	+1.16	2.579	+1.36	1.436	0.841
68	Nasal resonance (R_NASL)vn_R_NASL_reg	2.423	-0.35	2.453	-0.32	2.791	1.047
69	Oral resonance (R_ORAL)vn_R_ORAL_reg	2.045	-0.19	2.076	-0.15	2.184	0.741
70	Throat resonance (R_THRT)vn_R_THRT_reg	2.087	+0.02	2.016	-0.07	2.070	0.803
71	Smoothness (SMTH)vn_SMTH_reg	2.822	+0.62	2.744	+0.55	2.143	1.093
72	Stance (STNC)vn_STNC_reg	3.508	+0.77	3.748	+0.98	2.633	1.137
73	Speech structure (STRU)vn_STRU_reg	1.706	-0.45	1.665	-0.49	2.137	0.958
74	ASMR style (S_ASMR)vn_S_ASMR_reg	0.911	-0.33	0.943	-0.30	1.370	1.411
75	Authoritative style (S_AUTH)vn_S_AUTH_reg	2.108	+0.98	2.445	+1.30	1.088	1.043
76	Cartoonish style (S_CART)vn_S_CART_reg	2.589	+0.73	3.124	+1.12	1.560	1.401
77	Casual style (S_CASU)vn_S_CASU_reg	3.292	-0.39	3.073	-0.56	3.793	1.278
78	Conversational style (S_CONV)vn_S_CONV_reg	3.920	+1.01	4.104	+1.15	2.594	1.318
79	Dramatic style (S_DRAM)vn_S_DRAM_reg	3.763	+0.91	3.972	+1.09	2.721	1.148
80	Formal style (S_FORM)vn_S_FORM_reg	0.726	-0.46	0.718	-0.47	1.195	1.021
81	Monologue style (S_MONO)vn_S_MONO_reg	2.907	+0.06	3.034	+0.16	2.824	1.284
82	Narrator style (S_NARR)vn_S_NARR_reg	3.572	+1.57	4.413	+2.15	1.307	1.446
83	Newsreader style (S_NEWS)vn_S_NEWS_reg	0.293	-0.20	0.239	-0.30	0.408	0.568
84	Playful style (S_PLAY)vn_S_PLAY_reg	3.132	+0.59	3.650	+0.99	2.352	1.315
85	Ranting or angry style (S_RANT)vn_S_RANT_reg	2.571	+1.05	2.346	+0.88	1.213	1.289
86	Storytelling style (S_STRY)vn_S_STRY_reg	4.193	+1.25	4.683	+1.61	2.480	1.366
87	Teacher or didactic style (S_TECH)vn_S_TECH_reg	0.669	+0.02	0.988	+0.28	0.646	1.227
88	Whispered talking style (S_WHIS)vn_S_WHIS_reg	2.413	+0.50	2.541	+0.58	1.597	1.618
89	Tempo (TEMP)vn_TEMP_reg	1.891	-0.19	1.892	-0.19	2.117	1.190
90	Tension (TENS)vn_TENS_reg	2.472	+1.07	2.882	+1.55	1.559	0.852
91	Valence (VALN)vn_VALN_reg	1.948	-0.34	1.935	-0.35	2.328	1.118
92	Valence shift (VALS)vn_VALS_reg	2.476	-0.04	2.619	+0.09	2.518	1.079
93	Velocity flux (VFLX)vn_VFLX_reg	1.175	-0.89	2.194	-0.05	2.256	1.208
94	Volatility (VOLT)vn_VOLT_reg	3.444	+0.97	4.123	+1.73	2.586	0.886
95	Vulnerability (VULN)vn_VULN_reg	2.040	-0.62	2.668	+0.02	2.648	0.984
96	Warmth (WARM)vn_WARM_reg	4.556	+2.18	4.387	+1.99	2.578	0.909
Genuineness, blend, and legacy quality Genuineness and vocal-burst blend are predicted. R_quality has Ladder training labels but no valid P3 test labels.
97	Genuineness (0–6)genuineness_0_6	1.558	-0.48	1.815	-0.32	2.332	1.621
98	Vocal-burst blend (0–10)blend_0_10	0.890	-2.11	-0.300	-2.55	6.676	2.738
99	Legacy R_quality (no P3 test labels)R_quality	0.386	-2.10	0.298	-2.36	1.095	0.338
Empathic Insight Plus extra scores Nineteen additional clip-level teacher scores, including background noise and content enjoyment.
100	Ageeiv_extra:Age	3.255	+0.01	3.224	-0.09	3.250	0.293
101	Arousaleiv_extra:Arousal	2.192	+2.08	2.261	+2.23	1.289	0.435
102	Authenticityeiv_extra:Authenticity	2.847	+1.18	2.909	+1.59	2.667	0.153
103	Background Noiseeiv_extra:Background_Noise	0.679	-0.49	0.723	-0.32	0.808	0.264
104	Confident vs. Hesitanteiv_extra:Confident_vs._Hesitant	1.075	+0.12	1.085	+0.15	1.040	0.303
105	Gendereiv_extra:Gender	-0.678	-0.06	-0.709	-0.09	-0.621	0.999
106	High-Pitched vs. Low-Pitchedeiv_extra:High-Pitched_vs._Low-Pitched	1.589	-0.95	1.532	-1.18	1.827	0.250
107	Monotone vs. Expressiveeiv_extra:Monotone_vs._Expressive	2.104	+0.52	2.062	+0.43	1.859	0.470
108	Recording Qualityeiv_extra:Recording_Quality	2.143	-0.00	2.227	+0.25	2.144	0.332
109	Serious vs. Humorouseiv_extra:Serious_vs._Humorous	1.483	+1.62	1.509	+1.70	0.929	0.340
110	Soft vs. Harsheiv_extra:Soft_vs._Harsh	0.096	-0.58	0.202	-0.25	0.281	0.320
111	Submissive vs. Dominanteiv_extra:Submissive_vs._Dominant	0.916	+1.67	0.871	+1.53	0.376	0.324
112	Valenceeiv_extra:Valence	0.148	+0.38	0.234	+0.60	0.005	0.380
113	Vulnerable vs. Emotionally Detachedeiv_extra:Vulnerable_vs._Emotionally_Detached	1.371	-0.79	1.293	-0.97	1.715	0.437
114	Warm vs. Coldeiv_extra:Warm_vs._Cold	0.162	+0.37	0.079	+0.09	0.051	0.300
115	score background qualityeiv_extra:score_background_quality	3.572	+0.39	3.659	+0.52	3.301	0.693
116	score content enjoymenteiv_extra:score_content_enjoyment	4.649	+0.47	4.644	+0.45	4.507	0.303
117	score overall qualityeiv_extra:score_overall_quality	2.967	+0.62	2.981	+0.65	2.652	0.507
118	score speech qualityeiv_extra:score_speech_quality	1.789	-0.13	1.797	-0.07	1.808	0.146
Meta AudioBox Aesthetics Four AudioBox aesthetic teacher outputs. Expansions follow the official Meta model card.
119	Content enjoyment (CE)audiobox:CE	5.391	+0.58	5.347	+0.54	4.799	1.018
120	Content usefulness (CU)audiobox:CU	6.643	+0.99	6.698	+1.05	5.649	1.001
121	Production complexity (PC)audiobox:PC	2.404	+0.05	2.571	+0.15	2.331	1.617
122	Production quality (PQ)audiobox:PQ	8.043	+1.14	7.933	+1.01	7.044	0.879
Microsoft DNSMOS Seven DNSMOS teacher outputs: raw and calibrated SIG/BAK/OVRL estimates plus P.808 MOS.
123	Speech signal quality, rawdnsmos:SIG_raw	4.011	+0.17	3.849	-0.08	3.900	0.669
124	Background quality, rawdnsmos:BAK_raw	3.982	+0.69	3.815	+0.54	3.211	1.124
125	Overall quality, rawdnsmos:OVRL_raw	3.627	+0.67	3.427	+0.42	3.085	0.812
126	Speech signal quality, calibrateddnsmos:SIG	3.545	+0.11	3.456	-0.06	3.488	0.501
127	Background quality, calibrateddnsmos:BAK	3.908	+0.56	3.760	+0.40	3.389	0.928
128	Overall quality, calibrateddnsmos:OVRL	3.200	+0.59	3.053	+0.35	2.840	0.606
129	P.808 MOS estimatednsmos:P808_MOS	3.530	+0.22	3.563	+0.29	3.421	0.496
Vocal-burst count The regression target is log(1 + count). A separate table also reports count error after inverse transformation.
130	Vocal-burst count, log(1 + count)burst_count_log1p	1.614	+2.49	1.680	+2.60	0.000	0.647
VoiceCLAP attributes Sixty-one individual VoiceCLAP attribute teacher scores. The raw 768D VoiceCLAP embedding is stored in sidecars but is not a model output.
131	Affectionvoiceclap_attribute:Affection	0.686	-0.47	0.708	-0.43	0.947	0.554
132	Agevoiceclap_attribute:Age	3.113	-0.21	3.004	-0.41	3.229	0.547
133	Amusementvoiceclap_attribute:Amusement	0.955	+0.98	1.097	+1.23	0.392	0.572
134	Angervoiceclap_attribute:Anger	1.620	+1.24	1.766	+1.53	0.992	0.506
135	Arousalvoiceclap_attribute:Arousal	2.282	+1.38	2.622	+1.93	1.420	0.622
136	Astonishment Surprisevoiceclap_attribute:Astonishment_Surprise	1.541	+2.15	2.140	+3.40	0.509	0.479
137	Authenticityvoiceclap_attribute:Authenticity	2.914	+0.86	3.021	+1.50	2.770	0.167
138	Awevoiceclap_attribute:Awe	0.541	+0.01	0.765	+0.87	0.539	0.259
139	Background Noisevoiceclap_attribute:Background_Noise	0.511	-0.21	0.554	-0.05	0.567	0.264
140	Bitternessvoiceclap_attribute:Bitterness	0.555	-0.16	0.620	+0.12	0.592	0.236
141	Concentrationvoiceclap_attribute:Concentration	0.369	-1.59	0.207	-1.90	1.214	0.531
142	Confident vs. Hesitantvoiceclap_attribute:Confident_vs._Hesitant	0.705	-0.78	0.668	-0.86	1.069	0.468
143	Confusionvoiceclap_attribute:Confusion	0.721	+0.23	0.795	+0.45	0.643	0.334
144	Contemplationvoiceclap_attribute:Contemplation	0.271	-1.25	0.069	-1.75	0.780	0.406
145	Contemptvoiceclap_attribute:Contempt	1.107	+1.18	1.136	+1.26	0.709	0.339
146	Contentmentvoiceclap_attribute:Contentment	0.387	-0.66	0.346	-0.79	0.588	0.307
147	Disappointmentvoiceclap_attribute:Disappointment	0.952	+0.66	0.900	+0.48	0.760	0.291
148	Disgustvoiceclap_attribute:Disgust	1.078	+2.19	1.185	+2.71	0.625	0.207
149	Distressvoiceclap_attribute:Distress	1.145	+0.62	1.457	+1.52	0.927	0.350
150	Doubtvoiceclap_attribute:Doubt	0.529	-0.03	0.520	-0.08	0.535	0.188
151	Elationvoiceclap_attribute:Elation	0.766	+0.57	0.857	+0.80	0.539	0.397
152	Embarrassmentvoiceclap_attribute:Embarrassment	0.380	+0.23	0.428	+0.38	0.307	0.314
153	Emotional Numbnessvoiceclap_attribute:Emotional_Numbness	0.476	-0.71	0.331	-1.25	0.664	0.266
154	Fatigue Exhaustionvoiceclap_attribute:Fatigue_Exhaustion	0.479	+0.07	0.294	-0.64	0.462	0.261
155	Fearvoiceclap_attribute:Fear	0.905	+1.35	1.036	+1.97	0.618	0.212
156	Gendervoiceclap_attribute:Gender	-0.353	-0.20	-0.140	+0.01	-0.151	1.005
157	Helplessnessvoiceclap_attribute:Helplessness	0.932	+1.02	1.072	+1.54	0.658	0.268
158	High-Pitched vs. Low-Pitchedvoiceclap_attribute:High-Pitched_vs._Low-Pitched	1.379	-1.23	1.329	-1.36	1.840	0.375
159	Hope Enthusiasm Optimismvoiceclap_attribute:Hope_Enthusiasm_Optimism	0.654	-0.13	0.689	-0.04	0.705	0.396
160	Impatience and Irritabilityvoiceclap_attribute:Impatience_and_Irritability	1.525	+0.87	1.654	+1.11	1.052	0.541
161	Infatuationvoiceclap_attribute:Infatuation	0.785	+0.53	0.965	+1.08	0.608	0.332
162	Interestvoiceclap_attribute:Interest	1.377	-0.50	1.448	-0.34	1.598	0.440
163	Intoxication Altered States of Consciousnessvoiceclap_attribute:Intoxication_Altered_States_of_Consciousness	0.845	+0.74	0.735	+0.50	0.502	0.463
164	Jealousy & Envyvoiceclap_attribute:Jealousy_&_Envy	0.955	+1.77	1.000	+1.95	0.523	0.245
165	Longingvoiceclap_attribute:Longing	0.470	-0.31	0.414	-0.56	0.538	0.220
166	Malevolence Malicevoiceclap_attribute:Malevolence_Malice	1.281	+1.30	1.398	+1.63	0.833	0.346
167	Monotone vs. Expressivevoiceclap_attribute:Monotone_vs._Expressive	1.966	+0.32	1.960	+0.31	1.775	0.594
168	Painvoiceclap_attribute:Pain	0.441	+0.27	0.644	+1.20	0.381	0.218
169	Pleasure Ecstasyvoiceclap_attribute:Pleasure_Ecstasy	0.728	+0.75	0.797	+0.98	0.503	0.301
170	Pridevoiceclap_attribute:Pride	0.925	+0.41	0.892	+0.32	0.780	0.349
171	Recording Qualityvoiceclap_attribute:Recording_Quality	2.343	+0.09	2.363	+0.15	2.313	0.328
172	Reliefvoiceclap_attribute:Relief	1.755	+1.76	1.723	+1.68	1.025	0.415
173	Sadnessvoiceclap_attribute:Sadness	0.681	-0.23	0.728	-0.07	0.752	0.313
174	Serious vs. Humorousvoiceclap_attribute:Serious_vs._Humorous	1.327	+0.92	1.452	+1.14	0.803	0.568
175	Sexual Lustvoiceclap_attribute:Sexual_Lust	1.017	+0.91	1.195	+1.34	0.635	0.419
176	Shamevoiceclap_attribute:Shame	0.665	+0.49	0.630	+0.37	0.526	0.283
177	Soft vs. Harshvoiceclap_attribute:Soft_vs._Harsh	-0.220	-1.05	-0.265	-1.18	0.160	0.360
178	Sournessvoiceclap_attribute:Sourness	0.814	+0.37	0.845	+0.48	0.706	0.291
179	Submissive vs. Dominantvoiceclap_attribute:Submissive_vs._Dominant	1.046	+1.18	1.072	+1.25	0.623	0.359
180	Teasingvoiceclap_attribute:Teasing	1.148	+1.60	1.171	+1.66	0.540	0.379
181	Thankfulness Gratitudevoiceclap_attribute:Thankfulness_Gratitude	1.537	+0.29	1.700	+0.60	1.384	0.529
182	Triumphvoiceclap_attribute:Triumph	1.244	+1.47	1.348	+1.76	0.716	0.359
183	Valencevoiceclap_attribute:Valence	0.159	+0.26	-0.083	-0.12	-0.007	0.635
184	Vulnerable vs. Emotionally Detachedvoiceclap_attribute:Vulnerable_vs._Emotionally_Detached	1.160	-0.86	1.045	-1.07	1.638	0.556
185	Warm vs. Coldvoiceclap_attribute:Warm_vs._Cold	-0.253	-0.47	-0.277	-0.53	-0.066	0.400
186	durationvoiceclap_attribute:duration	7.479	-0.54	7.726	-0.50	10.914	6.354
187	score background qualityvoiceclap_attribute:score_background_quality	3.429	+0.37	3.467	+0.45	3.245	0.498
188	score content enjoymentvoiceclap_attribute:score_content_enjoyment	4.777	+0.82	4.834	+1.21	4.656	0.147
189	score overall qualityvoiceclap_attribute:score_overall_quality	2.831	+0.47	2.824	+0.46	2.635	0.412
190	score speech qualityvoiceclap_attribute:score_speech_quality	1.887	-0.05	1.882	-0.13	1.891	0.069
191	talking speedvoiceclap_attribute:talking_speed	10.145	+0.30	10.416	+0.37	9.028	3.756

All Orange embedding components

The cosine above is the meaningful vector-level comparison; component values have no standalone semantic label.

Timbre — all 128 vector components

Dimension	Tiny	Base	Orange teacher
0	0.1852	0.1312	0.1396
1	-0.0014	-0.0448	-0.0804
2	0.0180	-0.0122	0.0170
3	-0.0297	-0.0499	-0.0839
4	0.2315	0.2074	0.1769
5	0.0841	0.0722	0.0928
6	-0.0615	-0.0488	-0.0175
7	0.0286	0.0154	-0.0589
8	0.0139	0.0313	0.0388
9	-0.0161	0.0167	-0.0036
10	0.1852	0.1715	0.2001
11	-0.0877	-0.0626	-0.0967
12	-0.0100	0.0052	0.0208
13	-0.0685	-0.0906	-0.0816
14	-0.0352	-0.0027	-0.0232
15	-0.0292	-0.0884	-0.0741
16	-0.1163	-0.1610	-0.1024
17	-0.0048	0.0103	-0.0267
18	0.0188	0.0453	0.0892
19	0.0306	0.0385	0.0414
20	-0.0563	-0.0363	-0.0828
21	0.1571	0.2030	0.1462
22	-0.0764	-0.0809	-0.0778
23	-0.0390	-0.0630	-0.0978
24	-0.0327	-0.0418	-0.0668
25	-0.0926	-0.0748	-0.0726
26	-0.0551	-0.0363	0.0296
27	-0.0908	-0.0783	-0.0771
28	-0.0816	-0.0962	-0.0622
29	0.1200	0.1120	0.1599
30	0.0676	0.0678	0.0888
31	0.1011	0.1295	0.1538
32	0.0075	-0.0113	-0.0797
33	0.1815	0.1470	0.1891
34	-0.0393	-0.0691	-0.0660
35	-0.0536	-0.0284	-0.0151
36	-0.0481	-0.0665	-0.0149
37	0.0731	0.0464	0.0363
38	-0.1029	-0.0674	-0.0826
39	-0.0761	-0.1015	-0.0834
40	0.0445	0.0348	-0.0728
41	-0.0396	-0.0252	0.0768
42	-0.0877	-0.0370	-0.0834
43	-0.0640	-0.0523	-0.0851
44	-0.0393	-0.0028	-0.0375
45	-0.0524	-0.0687	-0.0513
46	-0.0099	-0.0195	-0.0780
47	-0.0822	-0.0871	-0.0836
48	-0.0019	-0.0409	-0.0531
49	-0.1084	-0.1164	-0.0836
50	0.2156	0.2056	0.1376
51	0.0859	0.0459	0.0349
52	0.0115	0.0302	0.0109
53	-0.0938	-0.1137	-0.0844
54	-0.0478	-0.0295	-0.0634
55	-0.0187	-0.0194	-0.0150
56	0.0115	0.0346	0.0424
57	-0.0944	-0.0932	-0.0907
58	-0.1200	-0.1505	-0.0880
59	-0.0393	-0.0429	-0.0830
60	-0.0402	-0.0127	-0.0341
61	0.0145	-0.0097	-0.0358
62	-0.0609	-0.0809	-0.0773
63	-0.0643	-0.0396	-0.0786
64	0.1279	0.1277	0.1487
65	-0.0883	-0.0827	-0.0674
66	0.0369	0.0357	0.0328
67	0.1608	0.1295	0.1340
68	0.1693	0.2231	0.1655
69	-0.1011	-0.0853	-0.0758
70	0.0509	0.0442	0.0925
71	0.0171	-0.0188	-0.0396
72	-0.0673	-0.0518	-0.0485
73	-0.0387	-0.0604	-0.0102
74	-0.0282	-0.0261	-0.0377
75	0.0518	0.0095	0.0614
76	-0.0090	0.0109	0.0503
77	0.1888	0.1890	0.1826
78	-0.0047	-0.0213	0.0506
79	-0.0962	-0.0687	-0.0717
80	0.1913	0.1627	0.2051
81	-0.0128	-0.0151	0.0494
82	0.0094	0.0400	0.1610
83	-0.0091	0.0064	-0.0155
84	-0.0612	-0.0304	0.0382
85	-0.0388	-0.0674	-0.0143
86	0.0021	-0.0113	0.0013
87	-0.0215	-0.0224	-0.0229
88	0.0100	-0.0212	-0.0231
89	0.1182	0.1146	0.1146
90	-0.0597	-0.1019	-0.0897
91	0.0212	-0.0105	0.1216
92	-0.0841	-0.0831	-0.0803
93	-0.0346	-0.0304	-0.0808
94	-0.0536	-0.0385	0.0251
95	-0.1090	-0.1356	-0.0889
96	0.0064	-0.0001	-0.0209
97	-0.1529	-0.1164	-0.0884
98	-0.0968	-0.0779	-0.0836
99	0.0396	0.0435	0.0250
100	0.1023	0.0927	0.1678
101	0.0652	0.0514	0.0966
102	0.0361	0.0249	0.0268
103	-0.0487	-0.0536	-0.0491
104	-0.0822	-0.0709	-0.0809
105	-0.1450	-0.1098	-0.0798
106	-0.0512	-0.0444	-0.0441
107	0.1645	0.1925	0.1847
108	0.1133	0.1636	0.1945
109	-0.0834	-0.0805	-0.0811
110	0.1596	0.1566	0.1078
111	-0.0780	-0.0656	-0.0959
112	-0.1109	-0.1120	-0.0815
113	-0.1632	-0.1540	-0.1164
114	-0.0260	-0.0717	-0.0126
115	0.0051	-0.0120	0.0339
116	-0.0804	-0.1137	-0.0709
117	0.0078	0.0167	0.0602
118	0.0109	-0.0168	-0.0743
119	-0.0003	-0.0194	0.0060
120	0.0014	-0.0207	0.0548
121	-0.1169	-0.1172	-0.0838
122	-0.1310	-0.1207	-0.0850
123	0.2436	0.2555	0.1511
124	-0.0245	-0.0350	0.0442
125	-0.0767	-0.0853	-0.0688
126	-0.0719	-0.0612	-0.0713
127	-0.0475	-0.0166	-0.0466

Identity — all 250 vector components

Dimension	Tiny	Base	Orange teacher
0	-0.0369	-0.0756	-0.0442
1	-0.0758	-0.0885	-0.0389
2	-0.0514	-0.1035	-0.0494
3	-0.0628	-0.0756	-0.0423
4	-0.0446	-0.0296	-0.0011
5	0.0253	-0.0100	-0.0420
6	0.0688	0.0252	0.0119
7	0.1546	0.2139	0.2213
8	-0.0137	-0.0259	-0.0743
9	-0.0109	-0.0205	-0.0181
10	0.0026	-0.0266	-0.0421
11	-0.0297	-0.0310	-0.0544
12	-0.0698	-0.0606	-0.0440
13	-0.0097	-0.0407	-0.0355
14	-0.0768	-0.0681	-0.0573
15	0.0334	0.0593	0.0181
16	0.0298	0.0538	0.0646
17	-0.0251	-0.0271	-0.0482
18	-0.0002	-0.0147	-0.0409
19	-0.0256	-0.0511	-0.0422
20	-0.0178	-0.0368	-0.0025
21	-0.0633	-0.0613	-0.0373
22	-0.0598	-0.0453	-0.0417
23	0.0967	0.0967	0.1671
24	-0.0299	-0.0456	-0.0343
25	-0.0536	-0.0463	-0.0718
26	0.0788	0.0507	0.0931
27	-0.0474	-0.0373	-0.0327
28	-0.0833	-0.0732	-0.0435
29	0.0334	0.0572	0.0750
30	0.0359	0.0688	0.0915
31	-0.0491	-0.0436	-0.0505
32	-0.1277	-0.1110	-0.0414
33	0.0511	0.0528	0.0235
34	0.0982	0.0627	0.1093
35	-0.0118	0.0089	0.0462
36	0.0319	0.0363	0.0905
37	-0.0104	-0.0395	-0.0278
38	0.0025	-0.0352	-0.0558
39	-0.0601	-0.0400	-0.0599
40	-0.0531	-0.0541	-0.0465
41	-0.0372	-0.0528	-0.0461
42	0.0863	0.1158	0.1214
43	0.0708	0.0366	0.0920
44	0.0122	0.0110	0.0112
45	0.0668	0.0244	0.0386
46	-0.0853	-0.0729	-0.0591
47	-0.0982	-0.1294	-0.0526
48	-0.0479	-0.0453	-0.0429
49	-0.0303	-0.0086	-0.0251
50	0.0060	0.0003	0.0349
51	-0.0147	-0.0152	-0.0095
52	-0.0504	-0.0417	-0.0396
53	-0.0132	-0.0112	-0.0389
54	-0.0868	-0.0388	-0.0679
55	0.0266	-0.0197	-0.0381
56	-0.0668	-0.0698	-0.0553
57	-0.0099	0.0216	0.0124
58	-0.0541	-0.0402	-0.0386
59	0.0289	0.0780	0.0659
60	-0.0621	-0.0811	-0.0421
61	0.1656	0.1403	0.1627
62	-0.0213	-0.0358	-0.0353
63	-0.0688	-0.0988	-0.0436
64	0.0638	0.0559	0.0776
65	0.0100	0.0061	-0.0308
66	0.0180	0.0109	0.0804
67	0.0254	0.0269	0.0304
68	0.0868	0.0434	0.0279
69	0.2164	0.1710	0.2118
70	-0.0394	-0.0400	-0.0187
71	0.0191	0.0074	0.0349
72	-0.0107	-0.0407	-0.0445
73	-0.0793	-0.0301	0.0151
74	-0.0197	-0.0247	-0.0151
75	-0.0596	-0.0216	-0.0585
76	0.0883	0.0535	0.1129
77	0.0227	0.0715	0.0153
78	-0.0041	0.0332	-0.0233
79	0.0474	0.0521	0.0297
80	0.0888	0.0947	0.1225
81	-0.0967	-0.0773	-0.0481
82	0.0277	-0.0122	-0.0096
83	-0.0559	-0.0450	-0.0357
84	0.0347	-0.0057	0.0493
85	-0.0818	-0.0879	-0.0429
86	-0.0459	-0.0261	-0.0383
87	0.0109	-0.0041	-0.0191
88	-0.1112	-0.1035	-0.0424
89	-0.0536	-0.0220	-0.0388
90	0.0041	-0.0026	-0.0312
91	0.1486	0.1669	0.0573
92	-0.0237	-0.0156	-0.0371
93	-0.0186	-0.0221	-0.0487
94	-0.0838	-0.0685	-0.0695
95	0.0384	-0.0143	0.0224
96	-0.0823	-0.0691	-0.0384
97	-0.0564	-0.0848	-0.0505
98	0.2234	0.2071	0.2803
99	-0.0564	-0.0606	-0.0486
100	0.1092	0.1212	0.0637
101	-0.0072	-0.0257	-0.0405
102	0.0202	-0.0366	-0.0479
103	-0.0068	-0.0158	-0.0690
104	-0.0466	-0.0712	-0.0559
105	-0.1297	-0.1103	-0.0558
106	0.0312	0.0168	0.0766
107	0.0509	0.0341	0.1396
108	-0.0633	-0.0582	-0.0319
109	0.0036	0.0140	-0.0057
110	0.0406	0.0173	0.0213
111	0.0763	0.0681	0.0835
112	-0.0142	-0.0238	-0.0346
113	0.0444	0.0463	0.0601
114	0.0556	0.0463	0.0796
115	0.0218	0.0361	-0.0304
116	-0.0016	0.0158	-0.0003
117	0.0564	0.0390	0.0376
118	-0.0628	-0.0130	-0.0560
119	0.0601	0.0351	0.1198
120	-0.0556	-0.0654	-0.0214
121	0.0738	0.0725	0.0021
122	-0.0014	0.0201	-0.0228
123	-0.0593	0.0018	-0.0443
124	-0.0516	-0.0742	-0.0428
125	0.0231	-0.0346	-0.0417
126	0.0918	0.0787	0.0502
127	-0.0207	-0.0080	-0.0179
128	-0.0231	-0.0344	-0.0500
129	-0.0504	-0.0429	-0.0455
130	-0.0499	-0.0742	-0.0431
131	-0.0424	-0.0129	-0.0375
132	0.0888	0.0473	0.0565
133	0.0103	0.0191	0.1025
134	-0.0606	-0.0108	0.0217
135	0.0953	0.0232	0.0538
136	-0.0561	-0.0606	-0.0460
137	-0.0156	-0.0150	-0.0398
138	-0.0673	-0.0548	-0.0378
139	0.0668	0.0994	0.1250
140	-0.0159	-0.0434	-0.0441
141	-0.0041	-0.0255	-0.0038
142	-0.0227	-0.0456	-0.0371
143	-0.1122	-0.0967	-0.0803
144	0.0399	-0.0198	-0.0447
145	-0.0618	-0.0538	-0.0545
146	0.1356	0.1335	0.1177
147	0.0327	0.0339	0.0640
148	-0.0601	-0.0623	-0.0371
149	-0.0653	-0.0125	-0.0552
150	0.0273	0.0393	0.0771
151	0.0267	0.0722	0.0739
152	-0.0132	-0.0320	-0.0139
153	0.0591	0.0181	0.0235
154	0.0526	0.0664	0.0697
155	-0.0043	-0.0068	-0.0408
156	-0.0501	-0.0427	-0.0430
157	0.0262	0.0409	0.0013
158	-0.0798	-0.0548	-0.0534
159	-0.0207	0.0276	-0.0474
160	0.0486	0.0376	0.0473
161	-0.1177	-0.0954	-0.0939
162	0.0489	0.0084	0.0023
163	0.0032	0.0261	0.0317
164	0.0319	0.0538	0.0764
165	-0.0196	-0.0181	-0.0614
166	-0.0933	-0.0940	-0.0499
167	-0.0102	0.0179	0.0094
168	0.0858	0.0974	0.0916
169	-0.0441	-0.0296	-0.0489
170	-0.0491	-0.0518	-0.0402
171	-0.0327	-0.0235	-0.0377
172	0.0055	-0.0220	-0.0271
173	-0.0967	-0.0633	-0.0092
174	0.0758	0.0753	0.1748
175	-0.0494	-0.0470	-0.0113
176	-0.0229	0.0131	-0.0365
177	-0.0451	-0.0507	-0.0353
178	0.0217	0.0576	0.0279
179	-0.0298	-0.0606	-0.0528
180	0.1356	0.1410	0.0528
181	-0.0449	-0.0325	-0.0574
182	-0.0386	-0.0524	-0.0370
183	-0.0188	-0.0169	-0.0158
184	-0.0342	-0.0375	-0.0435
185	-0.0401	0.0250	-0.0513
186	-0.0529	-0.0298	-0.0517
187	-0.0251	0.0254	-0.0488
188	-0.0266	-0.0378	-0.0068
189	-0.0476	0.0130	-0.0045
190	0.0058	-0.0189	-0.0272
191	0.0581	0.0572	0.0598
192	-0.0499	-0.0596	-0.0429
193	0.0873	0.0410	0.0684
194	-0.0138	-0.0267	-0.0556
195	0.0481	0.0787	0.0743
196	-0.0016	-0.0267	0.0383
197	0.0188	0.0507	0.0615
198	-0.0034	-0.0176	0.1100
199	0.0833	0.1737	0.1192
200	0.0134	0.0257	-0.0220
201	0.0923	0.1287	0.0759
202	-0.0933	-0.0800	-0.0359
203	-0.0718	-0.0354	-0.0535
204	0.0743	0.0831	0.1078
205	0.0289	0.0431	0.0332
206	-0.0858	-0.0845	-0.0442
207	0.0084	0.0182	0.0690
208	-0.0858	-0.0879	-0.0445
209	0.0132	-0.0192	0.0136
210	-0.0119	-0.0358	-0.0558
211	-0.0153	-0.0189	-0.0330
212	0.0106	0.0240	-0.0627
213	0.0783	0.1131	0.1367
214	0.0773	0.1410	0.0812
215	0.0302	0.0439	0.0482
216	0.0626	0.0424	0.0665
217	0.0534	0.0310	0.0602
218	-0.0429	-0.0688	-0.0498
219	-0.0342	-0.0346	-0.0558
220	-0.0065	-0.0211	0.0676
221	-0.1172	-0.0865	-0.0372
222	-0.1262	-0.1103	-0.0503
223	0.0364	0.0139	-0.0021
224	0.0678	0.0341	0.1515
225	-0.0596	-0.0364	-0.0357
226	0.0853	0.1424	0.1075
227	-0.0206	-0.0272	0.0024
228	-0.0554	-0.0363	-0.0185
229	-0.0873	-0.0933	-0.0367
230	0.0117	-0.0272	-0.0271
231	-0.0101	0.0060	-0.0212
232	-0.0718	-0.0620	-0.0589
233	0.1247	0.0834	0.0635
234	-0.0496	-0.0514	-0.0364
235	0.1945	0.2261	0.1080
236	-0.0303	-0.0335	-0.0099
237	0.0362	0.0279	0.0092
238	-0.0733	-0.0610	-0.0470
239	0.0446	-0.0228	-0.0112
240	-0.0344	-0.0109	-0.0437
241	-0.0668	-0.0681	-0.0579
242	-0.1232	-0.1131	-0.0632
243	0.0683	0.0272	0.0181
244	0.1107	0.0746	0.0627
245	0.0228	0.0366	-0.0408
246	0.0163	0.0257	-0.0347
247	-0.0070	-0.0210	-0.0361
248	-0.0145	-0.0278	-0.0231
249	-0.0216	-0.0647	-0.0654

Source: P3 source-disjoint test split · p3_02005463 · SHA-256 d9d7139aaf95b3cd…

p04Speech + burstsP3 curated burst test

Fear + 4 known burst(s)

Synthetic speech with inserted bursts · P3 synthetic speech/burst mixture · 8.0 s

Tiny Base · values are model estimates, not ground truth

Strongest emotions relative to training

Astonishment Surprise

z +3.80 / +3.80raw 2.18 / 2.18

Disgust

z +1.29 / +2.91raw 0.64 / 1.43

Fear

z +2.20 / +2.35raw 1.35 / 1.45

Impatience and Irritability

z +2.32 / +1.84raw 1.79 / 1.44

Contempt

z +1.31 / +2.08raw 0.61 / 0.97

Anger

z +2.05 / +2.02raw 1.26 / 1.24

Teasing

z +1.25 / +1.71raw 0.68 / 0.93

The center of each bar is the S9 teacher median. Positive z is to the right; negative z is to the left. Ranking uses z, not raw teacher units.

Strongest VoiceNet dimensions relative to training

Pitch range (RANG)

z +4.10 / +4.07raw 6.59 / 6.56

Volatility (VOLT)

z +3.80 / +3.39raw 5.95 / 5.59

Dramatic style (S_DRAM)

z +3.45 / +3.27raw 6.69 / 6.47

Dynamic arc (DARC)

z +3.31 / +3.37raw 6.19 / 6.27

Roughness (ROUG)

z +2.89 / +3.01raw 4.59 / 4.70

Ranting or angry style (S_RANT)

z +2.83 / +2.27raw 4.86 / 4.15

Tension (TENS)

z +2.65 / +2.79raw 3.82 / 3.94

All 57 VoiceNet predictions, including raw units, are in the full table below. These seven are ranked by z; the top values may differ from the strongest raw dimensions.

Voice, speed and quality scores in context

Genuineness (0–6)z -0.14 / -0.32raw 2.10 / 1.81

Vocal-burst blend (0–10)z -1.84 / -1.78raw 1.63 / 1.80

Content enjoyment (CE)z -0.73 / -0.94raw 4.05 / 3.85

Production quality (PQ)z +0.31 / +0.08raw 7.31 / 7.11

Speech signal quality, calibratedz -0.23 / -0.14raw 3.37 / 3.42

Background quality, calibratedz -1.44 / -1.16raw 2.05 / 2.31

Overall quality, calibratedz -1.18 / -0.91raw 2.13 / 2.29

P.808 MOS estimatez -0.97 / -0.96raw 2.94 / 2.95

score content enjoymentz -1.02 / -0.63raw 4.20 / 4.32

score overall qualityz -0.47 / -0.44raw 2.41 / 2.43

Background Noisez +0.84 / +0.45raw 1.03 / 0.93

Tempo (TEMP)z +1.35 / +1.27raw 3.72 / 3.63

Arousal (AROU)z +2.31 / +2.51raw 5.01 / 5.24

Valence (VALN)z -0.71 / -0.08raw 1.53 / 2.23

Recording quality (RCQL)z -0.85 / -0.81raw 2.00 / 2.03

Background noise (BKGN)z -0.31 / -0.18raw 2.47 / 2.56

talking speedz +0.14 / -0.00raw 9.56 / 9.01

Characters per second (CPS): 8.57 raw · z -0.12

P3 metadata teacher estimate; not a Whisper output. Reference: 86,334 P3 training teacher values, median 9.03, SD 3.76. Cross-language character counts depend on writing system; compare with care.

Orange speaker embedding reconstruction

Cosine against Orange on this same clip (higher means closer to that teacher vector):

Embedding	Tiny	Base
Timbre · 128D	0.774	0.790
Identity · 250D	0.764	0.786

Vocal-burst regions

Known

Tiny

Base

0 s8.0 s

Purple marks known inserted burst intervals; other vocal sounds may be unlabeled.

Tiny: 3 regions, count-head estimate 3.82; Base: 5 regions, count-head estimate 3.75.

Exact predicted start and end times

Model	Region	Start (s)	End (s)	Duration (s)
Tiny	1	0.30	0.90	0.60
Tiny	2	1.00	5.66	4.66
Tiny	3	5.70	6.10	0.40
Base	1	0.30	0.90	0.60
Base	2	1.00	1.20	0.20
Base	3	1.24	1.26	0.02
Base	4	1.30	5.66	4.36
Base	5	5.70	6.10	0.40

Known inserted intervals: 0.31–5.33 s, 5.33–5.64 s, 5.70–6.10 s, 0.38–0.89 s

All 192 score slots · raw and z values

#	Target	Tiny raw	Tiny z	Base raw	Base z	Train median	Train SD
Emotion scores Forty clip-level Empathic Insight emotion teacher outputs. Each row evaluates one named emotion score.
0	Affectionemo_Affection	-0.064	-0.13	-0.020	-0.05	0.007	0.570
1	Amusementemo_Amusement	0.910	+1.03	1.057	+1.20	-0.001	0.885
2	Angeremo_Anger	1.263	+2.05	1.244	+2.02	0.004	0.613
3	Astonishment Surpriseemo_Astonishment_Surprise	2.176	+3.80	2.176	+3.80	0.005	0.572
4	Aweemo_Awe	0.027	+0.06	0.071	+0.17	0.000	0.427
5	Bitternessemo_Bitterness	0.177	+0.39	0.178	+0.40	0.013	0.415
6	Concentrationemo_Concentration	0.257	-0.51	0.240	-0.53	0.634	0.741
7	Confusionemo_Confusion	0.778	+1.44	0.743	+1.37	0.001	0.540
8	Contemplationemo_Contemplation	0.027	-0.09	0.034	-0.08	0.082	0.598
9	Contemptemo_Contempt	0.609	+1.31	0.967	+2.08	-0.000	0.464
10	Contentmentemo_Contentment	-0.094	-0.18	-0.041	-0.08	0.000	0.514
11	Disappointmentemo_Disappointment	0.473	+0.68	0.008	+0.01	0.000	0.700
12	Disgustemo_Disgust	0.636	+1.29	1.433	+2.91	0.007	0.489
13	Distressemo_Distress	1.334	+1.62	1.110	+1.35	0.000	0.821
14	Doubtemo_Doubt	0.166	+0.34	0.174	+0.36	0.006	0.466
15	Elationemo_Elation	0.250	+0.33	0.192	+0.25	0.012	0.728
16	Embarrassmentemo_Embarrassment	0.158	+0.27	0.201	+0.37	0.043	0.430
17	Emotional Numbnessemo_Emotional_Numbness	-0.203	-0.23	0.075	+0.08	0.004	0.917
18	Fatigue Exhaustionemo_Fatigue_Exhaustion	0.038	+0.02	0.042	+0.03	0.028	0.539
19	Fearemo_Fear	1.354	+2.20	1.450	+2.35	0.015	0.610
20	Helplessnessemo_Helplessness	0.731	+1.06	0.409	+0.59	-0.004	0.696
21	Hope Enthusiasm Optimismemo_Hope_Enthusiasm_Optimism	0.030	-0.12	0.089	-0.04	0.117	0.760
22	Impatience and Irritabilityemo_Impatience_and_Irritability	1.786	+2.32	1.444	+1.84	0.149	0.705
23	Infatuationemo_Infatuation	-0.011	+0.01	0.032	+0.09	-0.015	0.533
24	Interestemo_Interest	1.071	-0.57	1.234	-0.39	1.589	0.907
25	Intoxication Altered States of Consciousnessemo_Intoxication_Altered_States_of_Consciousness	0.175	+0.36	0.112	+0.24	-0.025	0.559
26	Jealousy and Envyemo_Jealousy_and_Envy	0.086	+0.06	0.019	-0.09	0.059	0.442
27	Longingemo_Longing	0.043	-0.07	0.028	-0.09	0.087	0.632
28	Malevolence Maliceemo_Malevolence_Malice	0.609	+1.04	0.877	+1.54	0.055	0.534
29	Painemo_Pain	0.697	+1.21	0.447	+0.77	-0.002	0.579
30	Pleasure Ecstasyemo_Pleasure_Ecstasy	0.249	+0.38	0.293	+0.45	0.017	0.614
31	Prideemo_Pride	-0.052	-0.11	-0.039	-0.08	0.002	0.509
32	Reliefemo_Relief	0.106	+0.11	0.144	+0.16	0.033	0.681
33	Sadnessemo_Sadness	0.374	+0.49	0.110	+0.14	0.000	0.759
34	Sexual Lustemo_Sexual_Lust	0.260	+0.47	0.415	+0.78	0.030	0.494
35	Shameemo_Shame	0.031	+0.04	0.018	+0.01	0.013	0.510
36	Sournessemo_Sourness	0.287	+0.67	0.306	+0.71	-0.005	0.439
37	Teasingemo_Teasing	0.680	+1.25	0.930	+1.71	0.000	0.545
38	Thankfulness Gratitudeemo_Thankfulness_Gratitude	0.014	-0.04	0.045	+0.01	0.041	0.697
39	Triumphemo_Triumph	0.180	+0.36	0.017	+0.05	-0.007	0.521
VoiceNet dimensions Fifty-seven VoiceNet voice, delivery, style, and recording dimensions. Codes are expanded in the target column.
40	Perceived voice age (AGEV)vn_AGEV_reg	0.929	-1.66	1.205	-1.44	2.984	1.238
41	Arousal (AROU)vn_AROU_reg	5.007	+2.31	5.235	+2.51	2.359	1.147
42	Arousal shift (ARSH)vn_ARSH_reg	3.957	+1.59	4.238	+1.91	2.580	0.867
43	Vocal attack (ATCK)vn_ATCK_reg	3.919	+1.36	4.330	+1.67	2.162	1.295
44	Background noise (BKGN)vn_BKGN_reg	2.467	-0.31	2.564	-0.18	2.703	0.761
45	Brightness (BRGT)vn_BRGT_reg	2.768	+0.96	3.129	+1.40	1.991	0.813
46	Speech chunking (CHNK)vn_CHNK_reg	2.335	+0.39	2.447	+0.48	1.847	1.239
47	Articulation clarity (CLRT)vn_CLRT_reg	1.166	-0.90	1.448	-0.60	2.018	0.945
48	Cognitive load (COGL)vn_COGL_reg	1.120	-0.92	0.868	-1.16	2.094	1.061
49	Dynamic arc (DARC)vn_DARC_reg	6.189	+3.31	6.274	+3.37	1.615	1.380
50	Disfluency (DFLU)vn_DFLU_reg	3.355	+0.73	2.718	+0.19	2.488	1.184
51	Emphasis (EMPH)vn_EMPH_reg	4.522	+1.26	4.596	+1.30	2.607	1.524
52	Esthetics (ESTH)vn_ESTH_reg	1.212	-1.52	1.467	-1.20	2.402	0.782
53	Content appropriateness (EXPL)vn_EXPL_reg	-0.001	-0.27	-0.017	-0.32	0.086	0.322
54	Focus (FOCS)vn_FOCS_reg	1.656	-0.62	1.925	-0.38	2.344	1.102
55	Fullness (FULL)vn_FULL_reg	0.860	-1.03	1.147	-0.71	1.778	0.889
56	Perceived gender (GEND)vn_GEND_reg	2.084	-1.24	2.715	-0.84	4.055	1.588
57	Harmonicity (HARM)vn_HARM_reg	2.648	+0.20	2.857	+0.45	2.480	0.836
58	Metallic character (METL)vn_METL_reg	3.704	+2.17	4.108	+2.60	1.621	0.958
59	Pitch range (RANG)vn_RANG_reg	6.590	+4.10	6.562	+4.07	2.914	0.897
60	Recording quality (RCQL)vn_RCQL_reg	1.996	-0.85	2.031	-0.81	2.754	0.888
61	Vocal register (REGS)vn_REGS_reg	3.562	+1.86	3.631	+1.92	1.198	1.268
62	Respiration (RESP)vn_RESP_reg	4.660	+1.88	4.309	+1.54	2.680	1.056
63	Roughness (ROUG)vn_ROUG_reg	4.592	+2.89	4.702	+3.01	2.033	0.887
64	Chest resonance (R_CHST)vn_R_CHST_reg	0.721	-1.67	0.987	-1.36	2.135	0.844
65	Head resonance (R_HEAD)vn_R_HEAD_reg	3.405	+1.53	3.250	+1.34	2.148	0.822
66	Mask resonance (R_MASK)vn_R_MASK_reg	2.898	+0.98	3.202	+1.29	1.908	1.005
67	Mixed resonance (R_MIXD)vn_R_MIXD_reg	0.003	-1.70	0.513	-1.10	1.436	0.841
68	Nasal resonance (R_NASL)vn_R_NASL_reg	4.219	+1.36	4.384	+1.52	2.791	1.047
69	Oral resonance (R_ORAL)vn_R_ORAL_reg	3.155	+1.31	3.254	+1.44	2.184	0.741
70	Throat resonance (R_THRT)vn_R_THRT_reg	2.230	+0.20	2.486	+0.52	2.070	0.803
71	Smoothness (SMTH)vn_SMTH_reg	1.043	-1.01	1.069	-0.98	2.143	1.093
72	Stance (STNC)vn_STNC_reg	4.335	+1.50	4.291	+1.46	2.633	1.137
73	Speech structure (STRU)vn_STRU_reg	0.997	-1.19	1.112	-1.07	2.137	0.958
74	ASMR style (S_ASMR)vn_S_ASMR_reg	0.418	-0.67	0.429	-0.67	1.370	1.411
75	Authoritative style (S_AUTH)vn_S_AUTH_reg	0.246	-0.81	0.436	-0.62	1.088	1.043
76	Cartoonish style (S_CART)vn_S_CART_reg	5.359	+2.71	5.423	+2.76	1.560	1.401
77	Casual style (S_CASU)vn_S_CASU_reg	5.256	+1.14	4.887	+0.86	3.793	1.278
78	Conversational style (S_CONV)vn_S_CONV_reg	2.475	-0.09	2.212	-0.29	2.594	1.318
79	Dramatic style (S_DRAM)vn_S_DRAM_reg	6.687	+3.45	6.473	+3.27	2.721	1.148
80	Formal style (S_FORM)vn_S_FORM_reg	0.080	-1.09	0.261	-0.92	1.195	1.021
81	Monologue style (S_MONO)vn_S_MONO_reg	1.215	-1.25	1.265	-1.21	2.824	1.284
82	Narrator style (S_NARR)vn_S_NARR_reg	0.522	-0.54	0.799	-0.35	1.307	1.446
83	Newsreader style (S_NEWS)vn_S_NEWS_reg	0.124	-0.50	0.137	-0.48	0.408	0.568
84	Playful style (S_PLAY)vn_S_PLAY_reg	3.487	+0.86	3.721	+1.04	2.352	1.315
85	Ranting or angry style (S_RANT)vn_S_RANT_reg	4.863	+2.83	4.146	+2.27	1.213	1.289
86	Storytelling style (S_STRY)vn_S_STRY_reg	4.988	+1.83	4.977	+1.83	2.480	1.366
87	Teacher or didactic style (S_TECH)vn_S_TECH_reg	0.103	-0.44	0.072	-0.47	0.646	1.227
88	Whispered talking style (S_WHIS)vn_S_WHIS_reg	0.886	-0.44	0.893	-0.44	1.597	1.618
89	Tempo (TEMP)vn_TEMP_reg	3.719	+1.35	3.635	+1.27	2.117	1.190
90	Tension (TENS)vn_TENS_reg	3.818	+2.65	3.935	+2.79	1.559	0.852
91	Valence (VALN)vn_VALN_reg	1.533	-0.71	2.234	-0.08	2.328	1.118
92	Valence shift (VALS)vn_VALS_reg	2.313	-0.19	2.423	-0.09	2.518	1.079
93	Velocity flux (VFLX)vn_VFLX_reg	5.064	+2.32	4.913	+2.20	2.256	1.208
94	Volatility (VOLT)vn_VOLT_reg	5.955	+3.80	5.588	+3.39	2.586	0.886
95	Vulnerability (VULN)vn_VULN_reg	4.466	+1.85	4.257	+1.63	2.648	0.984
96	Warmth (WARM)vn_WARM_reg	1.347	-1.35	1.467	-1.22	2.578	0.909
Genuineness, blend, and legacy quality Genuineness and vocal-burst blend are predicted. R_quality has Ladder training labels but no valid P3 test labels.
97	Genuineness (0–6)genuineness_0_6	2.097	-0.14	1.815	-0.32	2.332	1.621
98	Vocal-burst blend (0–10)blend_0_10	1.633	-1.84	1.803	-1.78	6.676	2.738
99	Legacy R_quality (no P3 test labels)R_quality	0.542	-1.64	0.513	-1.72	1.095	0.338
Empathic Insight Plus extra scores Nineteen additional clip-level teacher scores, including background noise and content enjoyment.
100	Ageeiv_extra:Age	2.761	-1.67	2.986	-0.90	3.250	0.293
101	Arousaleiv_extra:Arousal	2.894	+3.69	2.765	+3.39	1.289	0.435
102	Authenticityeiv_extra:Authenticity	2.825	+1.04	2.796	+0.84	2.667	0.153
103	Background Noiseeiv_extra:Background_Noise	1.029	+0.84	0.928	+0.45	0.808	0.264
104	Confident vs. Hesitanteiv_extra:Confident_vs._Hesitant	1.660	+2.05	1.454	+1.37	1.040	0.303
105	Gendereiv_extra:Gender	0.596	+1.22	0.616	+1.24	-0.621	0.999
106	High-Pitched vs. Low-Pitchedeiv_extra:High-Pitched_vs._Low-Pitched	1.399	-1.71	1.427	-1.60	1.827	0.250
107	Monotone vs. Expressiveeiv_extra:Monotone_vs._Expressive	2.701	+1.79	2.583	+1.54	1.859	0.470
108	Recording Qualityeiv_extra:Recording_Quality	1.522	-1.87	1.707	-1.32	2.144	0.332
109	Serious vs. Humorouseiv_extra:Serious_vs._Humorous	1.302	+1.09	1.421	+1.44	0.929	0.340
110	Soft vs. Harsheiv_extra:Soft_vs._Harsh	0.338	+0.18	0.338	+0.18	0.281	0.320
111	Submissive vs. Dominanteiv_extra:Submissive_vs._Dominant	0.394	+0.06	0.566	+0.59	0.376	0.324
112	Valenceeiv_extra:Valence	-0.355	-0.95	-0.281	-0.75	0.005	0.380
113	Vulnerable vs. Emotionally Detachedeiv_extra:Vulnerable_vs._Emotionally_Detached	0.870	-1.93	1.064	-1.49	1.715	0.437
114	Warm vs. Coldeiv_extra:Warm_vs._Cold	-0.221	-0.91	-0.200	-0.84	0.051	0.300
115	score background qualityeiv_extra:score_background_quality	2.953	-0.50	2.932	-0.53	3.301	0.693
116	score content enjoymenteiv_extra:score_content_enjoyment	4.198	-1.02	4.316	-0.63	4.507	0.303
117	score overall qualityeiv_extra:score_overall_quality	2.415	-0.47	2.427	-0.44	2.652	0.507
118	score speech qualityeiv_extra:score_speech_quality	1.801	-0.05	1.802	-0.04	1.808	0.146
Meta AudioBox Aesthetics Four AudioBox aesthetic teacher outputs. Expansions follow the official Meta model card.
119	Content enjoyment (CE)audiobox:CE	4.053	-0.73	3.846	-0.94	4.799	1.018
120	Content usefulness (CU)audiobox:CU	5.413	-0.24	5.285	-0.36	5.649	1.001
121	Production complexity (PC)audiobox:PC	2.647	+0.20	2.262	-0.04	2.331	1.617
122	Production quality (PQ)audiobox:PQ	7.313	+0.31	7.110	+0.08	7.044	0.879
Microsoft DNSMOS Seven DNSMOS teacher outputs: raw and calibrated SIG/BAK/OVRL estimates plus P.808 MOS.
123	Speech signal quality, rawdnsmos:SIG_raw	3.707	-0.29	3.785	-0.17	3.900	0.669
124	Background quality, rawdnsmos:BAK_raw	1.634	-1.40	1.977	-1.10	3.211	1.124
125	Overall quality, rawdnsmos:OVRL_raw	2.112	-1.20	2.351	-0.90	3.085	0.812
126	Speech signal quality, calibrateddnsmos:SIG	3.373	-0.23	3.416	-0.14	3.488	0.501
127	Background quality, calibrateddnsmos:BAK	2.051	-1.44	2.312	-1.16	3.389	0.928
128	Overall quality, calibrateddnsmos:OVRL	2.127	-1.18	2.288	-0.91	2.840	0.606
129	P.808 MOS estimatednsmos:P808_MOS	2.941	-0.97	2.945	-0.96	3.421	0.496
Vocal-burst count The regression target is log(1 + count). A separate table also reports count error after inverse transformation.
130	Vocal-burst count, log(1 + count)burst_count_log1p	1.573	+2.43	1.558	+2.41	0.000	0.647
VoiceCLAP attributes Sixty-one individual VoiceCLAP attribute teacher scores. The raw 768D VoiceCLAP embedding is stored in sidecars but is not a model output.
131	Affectionvoiceclap_attribute:Affection	1.245	+0.54	1.242	+0.53	0.947	0.554
132	Agevoiceclap_attribute:Age	1.841	-2.54	1.960	-2.32	3.229	0.547
133	Amusementvoiceclap_attribute:Amusement	1.940	+2.71	2.029	+2.86	0.392	0.572
134	Angervoiceclap_attribute:Anger	1.390	+0.79	1.227	+0.46	0.992	0.506
135	Arousalvoiceclap_attribute:Arousal	3.060	+2.64	2.963	+2.48	1.420	0.622
136	Astonishment Surprisevoiceclap_attribute:Astonishment_Surprise	1.609	+2.29	1.467	+2.00	0.509	0.479
137	Authenticityvoiceclap_attribute:Authenticity	3.069	+1.79	3.013	+1.45	2.770	0.167
138	Awevoiceclap_attribute:Awe	0.639	+0.39	0.636	+0.38	0.539	0.259
139	Background Noisevoiceclap_attribute:Background_Noise	0.845	+1.05	0.751	+0.70	0.567	0.264
140	Bitternessvoiceclap_attribute:Bitterness	0.803	+0.89	0.766	+0.74	0.592	0.236
141	Concentrationvoiceclap_attribute:Concentration	0.149	-2.01	0.137	-2.03	1.214	0.531
142	Confident vs. Hesitantvoiceclap_attribute:Confident_vs._Hesitant	1.785	+1.53	1.654	+1.25	1.069	0.468
143	Confusionvoiceclap_attribute:Confusion	0.941	+0.89	0.939	+0.89	0.643	0.334
144	Contemplationvoiceclap_attribute:Contemplation	0.088	-1.71	0.176	-1.49	0.780	0.406
145	Contemptvoiceclap_attribute:Contempt	0.668	-0.12	0.701	-0.02	0.709	0.339
146	Contentmentvoiceclap_attribute:Contentment	0.702	+0.37	0.720	+0.43	0.588	0.307
147	Disappointmentvoiceclap_attribute:Disappointment	1.165	+1.39	1.085	+1.12	0.760	0.291
148	Disgustvoiceclap_attribute:Disgust	0.731	+0.51	0.661	+0.18	0.625	0.207
149	Distressvoiceclap_attribute:Distress	1.768	+2.41	1.585	+1.88	0.927	0.350
150	Doubtvoiceclap_attribute:Doubt	0.195	-1.81	0.203	-1.76	0.535	0.188
151	Elationvoiceclap_attribute:Elation	1.751	+3.05	1.701	+2.93	0.539	0.397
152	Embarrassmentvoiceclap_attribute:Embarrassment	0.876	+1.81	0.724	+1.33	0.307	0.314
153	Emotional Numbnessvoiceclap_attribute:Emotional_Numbness	0.165	-1.88	0.231	-1.63	0.664	0.266
154	Fatigue Exhaustionvoiceclap_attribute:Fatigue_Exhaustion	0.617	+0.59	0.500	+0.15	0.462	0.261
155	Fearvoiceclap_attribute:Fear	0.977	+1.69	0.891	+1.29	0.618	0.212
156	Gendervoiceclap_attribute:Gender	1.034	+1.18	0.862	+1.01	-0.151	1.005
157	Helplessnessvoiceclap_attribute:Helplessness	1.281	+2.32	1.017	+1.34	0.658	0.268
158	High-Pitched vs. Low-Pitchedvoiceclap_attribute:High-Pitched_vs._Low-Pitched	1.248	-1.58	1.329	-1.36	1.840	0.375
159	Hope Enthusiasm Optimismvoiceclap_attribute:Hope_Enthusiasm_Optimism	1.553	+2.14	1.500	+2.01	0.705	0.396
160	Impatience and Irritabilityvoiceclap_attribute:Impatience_and_Irritability	1.705	+1.21	1.419	+0.68	1.052	0.541
161	Infatuationvoiceclap_attribute:Infatuation	1.274	+2.01	1.155	+1.65	0.608	0.332
162	Interestvoiceclap_attribute:Interest	1.243	-0.81	1.398	-0.46	1.598	0.440
163	Intoxication Altered States of Consciousnessvoiceclap_attribute:Intoxication_Altered_States_of_Consciousness	1.023	+1.12	0.928	+0.92	0.502	0.463
164	Jealousy & Envyvoiceclap_attribute:Jealousy_&_Envy	0.908	+1.58	0.846	+1.32	0.523	0.245
165	Longingvoiceclap_attribute:Longing	0.773	+1.07	0.734	+0.89	0.538	0.220
166	Malevolence Malicevoiceclap_attribute:Malevolence_Malice	1.160	+0.95	1.106	+0.79	0.833	0.346
167	Monotone vs. Expressivevoiceclap_attribute:Monotone_vs._Expressive	3.093	+2.22	2.977	+2.02	1.775	0.594
168	Painvoiceclap_attribute:Pain	1.105	+3.32	0.894	+2.35	0.381	0.218
169	Pleasure Ecstasyvoiceclap_attribute:Pleasure_Ecstasy	1.570	+3.55	1.575	+3.56	0.503	0.301
170	Pridevoiceclap_attribute:Pride	0.802	+0.06	0.888	+0.31	0.780	0.349
171	Recording Qualityvoiceclap_attribute:Recording_Quality	1.807	-1.54	1.825	-1.49	2.313	0.328
172	Reliefvoiceclap_attribute:Relief	1.469	+1.07	1.185	+0.39	1.025	0.415
173	Sadnessvoiceclap_attribute:Sadness	1.361	+1.95	1.193	+1.41	0.752	0.313
174	Serious vs. Humorousvoiceclap_attribute:Serious_vs._Humorous	1.980	+2.07	1.989	+2.09	0.803	0.568
175	Sexual Lustvoiceclap_attribute:Sexual_Lust	1.407	+1.84	1.300	+1.58	0.635	0.419
176	Shamevoiceclap_attribute:Shame	0.449	-0.27	0.292	-0.83	0.526	0.283
177	Soft vs. Harshvoiceclap_attribute:Soft_vs._Harsh	0.401	+0.67	0.485	+0.90	0.160	0.360
178	Sournessvoiceclap_attribute:Sourness	0.682	-0.08	0.639	-0.23	0.706	0.291
179	Submissive vs. Dominantvoiceclap_attribute:Submissive_vs._Dominant	0.640	+0.05	0.557	-0.19	0.623	0.359
180	Teasingvoiceclap_attribute:Teasing	1.222	+1.80	1.391	+2.24	0.540	0.379
181	Thankfulness Gratitudevoiceclap_attribute:Thankfulness_Gratitude	1.523	+0.26	1.453	+0.13	1.384	0.529
182	Triumphvoiceclap_attribute:Triumph	1.121	+1.13	1.216	+1.39	0.716	0.359
183	Valencevoiceclap_attribute:Valence	0.053	+0.09	0.442	+0.71	-0.007	0.635
184	Vulnerable vs. Emotionally Detachedvoiceclap_attribute:Vulnerable_vs._Emotionally_Detached	0.576	-1.91	0.767	-1.57	1.638	0.556
185	Warm vs. Coldvoiceclap_attribute:Warm_vs._Cold	0.150	+0.54	0.402	+1.17	-0.066	0.400
186	durationvoiceclap_attribute:duration	5.623	-0.83	5.821	-0.80	10.914	6.354
187	score background qualityvoiceclap_attribute:score_background_quality	2.915	-0.66	2.876	-0.74	3.245	0.498
188	score content enjoymentvoiceclap_attribute:score_content_enjoyment	4.591	-0.44	4.634	-0.15	4.656	0.147
189	score overall qualityvoiceclap_attribute:score_overall_quality	2.295	-0.83	2.249	-0.94	2.635	0.412
190	score speech qualityvoiceclap_attribute:score_speech_quality	1.914	+0.34	1.912	+0.30	1.891	0.069
191	talking speedvoiceclap_attribute:talking_speed	9.563	+0.14	9.014	-0.00	9.028	3.756

All Orange embedding components

The cosine above is the meaningful vector-level comparison; component values have no standalone semantic label.

Timbre — all 128 vector components

Dimension	Tiny	Base	Orange teacher
0	0.0692	0.1154	0.1144
1	0.0818	0.0603	-0.0244
2	-0.0139	-0.0329	-0.0472
3	-0.0227	0.0232	0.1272
4	-0.1004	-0.1080	-0.0646
5	0.0073	0.0088	-0.0532
6	-0.0827	-0.0932	-0.0623
7	0.1375	0.1295	0.0903
8	0.1164	0.0632	0.0607
9	0.0028	-0.0012	0.0287
10	-0.1034	-0.1036	-0.0639
11	0.0300	0.0810	0.0527
12	-0.1181	-0.0914	-0.0691
13	0.0848	0.1036	0.1885
14	-0.0010	-0.0038	-0.0556
15	0.1291	0.1783	0.1720
16	0.0553	0.0533	-0.0057
17	0.0196	-0.0020	-0.0715
18	-0.1042	-0.0906	-0.0634
19	-0.0167	-0.0141	-0.0650
20	0.0050	-0.0314	-0.0688
21	0.0700	0.1095	-0.0155
22	-0.0443	-0.0122	-0.0646
23	0.2033	0.2456	0.0922
24	0.1034	0.1161	0.0870
25	0.1443	0.0743	0.1592
26	-0.0949	-0.1043	-0.0645
27	0.0565	0.0274	-0.0214
28	-0.1059	-0.0984	-0.0757
29	-0.0340	-0.0740	-0.0736
30	0.0759	0.0477	0.0531
31	-0.0886	-0.0939	-0.0258
32	0.0014	0.0359	-0.0097
33	0.0654	0.0610	0.0017
34	0.0184	0.0253	0.0795
35	-0.0489	-0.0108	-0.0529
36	-0.0844	-0.0729	-0.0739
37	0.0818	0.0928	-0.0590
38	0.1519	0.1524	0.2252
39	0.1257	0.1206	0.0073
40	0.0513	0.0703	0.0994
41	0.0363	0.0140	-0.0988
42	-0.0776	-0.1013	-0.0693
43	0.0142	0.0185	0.0207
44	0.1578	0.1642	0.1545
45	0.0612	0.0264	0.1210
46	-0.0974	-0.0847	-0.0648
47	-0.0426	-0.0388	0.0036
48	-0.1097	-0.1110	-0.0671
49	-0.0759	-0.0566	-0.0480
50	0.0153	0.0429	-0.0703
51	-0.0591	-0.0185	0.0611
52	0.1147	0.1442	0.0897
53	0.0310	0.0261	-0.0633
54	-0.0751	-0.0673	-0.0769
55	-0.0382	-0.0699	0.0164
56	-0.0953	-0.0999	-0.0652
57	0.0248	-0.0008	0.0564
58	-0.0205	-0.0385	-0.0374
59	-0.0084	-0.0396	-0.0392
60	0.0848	0.1287	0.1082
61	-0.0432	-0.0485	-0.0633
62	0.0780	0.1058	0.0597
63	0.1067	0.1361	0.1909
64	0.0259	0.0411	0.0632
65	-0.0882	-0.0743	-0.0561
66	0.0293	-0.0035	0.1693
67	-0.0705	-0.0327	-0.0663
68	-0.0454	-0.0435	-0.0726
69	0.0237	0.0235	-0.0630
70	0.0789	0.0514	0.1284
71	-0.0797	-0.0621	-0.0762
72	0.0671	0.0496	0.0373
73	-0.1008	-0.0895	-0.0840
74	0.0553	0.0581	0.0398
75	0.0468	0.0492	-0.0028
76	0.0430	0.0281	0.1004
77	-0.0802	-0.0925	-0.0498
78	-0.0886	-0.0976	-0.0612
79	0.1282	0.0969	-0.0048
80	-0.1131	-0.1013	-0.0622
81	0.0561	0.0558	0.0958
82	-0.0700	-0.0533	-0.0657
83	-0.1198	-0.1213	-0.0704
84	0.0776	0.0448	0.0159
85	-0.0759	-0.0566	-0.0730
86	0.1367	0.1576	0.1644
87	0.0578	0.0309	0.1038
88	-0.1059	-0.0954	-0.0638
89	-0.1156	-0.0954	-0.0630
90	-0.0130	-0.0255	-0.0251
91	-0.0751	-0.0681	-0.0632
92	-0.0751	-0.0817	-0.0667
93	0.2632	0.2500	0.2118
94	0.0515	0.0777	0.1335
95	0.0240	0.0392	-0.0068
96	0.0375	0.0167	0.1440
97	0.1274	0.1043	0.1304
98	0.0852	0.0806	0.0999
99	0.2084	0.1820	0.0998
100	-0.1190	-0.1228	-0.0729
101	-0.1181	-0.0747	-0.0665
102	-0.0650	-0.0221	-0.0206
103	-0.0188	-0.0158	-0.0456
104	-0.0008	-0.0129	-0.0518
105	-0.0894	-0.0851	-0.0663
106	-0.1434	-0.1243	-0.0826
107	-0.1181	-0.1147	-0.0640
108	-0.1282	-0.1258	-0.0745
109	0.0536	0.0514	0.1267
110	0.0318	0.0673	0.1985
111	0.0962	0.0925	0.1438
112	-0.0067	-0.0212	-0.0169
113	-0.0882	-0.0714	-0.0849
114	-0.0321	-0.0677	-0.0740
115	0.1687	0.2352	0.1576
116	0.0460	-0.0112	0.0470
117	0.0051	0.0057	0.0944
118	-0.1025	-0.1065	-0.0669
119	0.0098	-0.0388	-0.0665
120	0.1131	0.0851	0.0212
121	0.1730	0.1716	0.1913
122	-0.0903	-0.0847	-0.0706
123	0.1409	0.1154	0.1121
124	-0.0548	-0.0366	-0.0007
125	0.0856	0.0607	0.0323
126	0.0506	0.0777	0.1240
127	0.0302	0.0174	0.0541

Identity — all 250 vector components

Dimension	Tiny	Base	Orange teacher
0	-0.0446	-0.0363	0.0301
1	-0.0749	-0.0584	-0.0362
2	-0.0876	-0.0655	-0.0460
3	-0.0197	0.0157	-0.0105
4	0.0040	-0.0125	0.0355
5	-0.0886	-0.0821	-0.0391
6	0.0999	0.1035	0.1417
7	-0.0539	-0.0314	-0.0379
8	-0.0399	-0.0196	-0.0692
9	0.0970	0.0865	0.1494
10	-0.0040	-0.0095	0.0673
11	-0.0122	-0.0500	-0.0448
12	0.0700	0.0782	-0.0056
13	0.0754	0.0940	0.1388
14	-0.0289	-0.0655	-0.0534
15	-0.0544	-0.0632	-0.0441
16	0.0280	0.0134	-0.0211
17	-0.0455	-0.0401	-0.0450
18	-0.0086	-0.0391	-0.0381
19	-0.0098	-0.0169	0.0085
20	0.0228	0.0908	0.1285
21	-0.0468	-0.0470	-0.0347
22	-0.0566	-0.0628	-0.0388
23	0.0058	0.0391	-0.0362
24	0.0214	-0.0117	0.0096
25	0.0553	0.0624	0.0799
26	0.0245	0.0833	0.0756
27	-0.0081	-0.0065	-0.0304
28	-0.0326	-0.0255	-0.0405
29	-0.0146	-0.0332	-0.0360
30	0.0252	-0.0093	0.0399
31	-0.0671	-0.0817	-0.0470
32	0.0145	-0.0663	-0.0385
33	-0.0353	0.0042	-0.0336
34	0.0896	0.0529	-0.0175
35	-0.0521	-0.0727	-0.0131
36	0.0651	0.1074	0.0167
37	0.0164	0.0050	0.0373
38	-0.0255	0.0151	-0.0385
39	0.0690	0.0588	-0.0222
40	-0.0428	-0.0608	-0.0434
41	-0.0563	-0.0667	-0.0430
42	0.0448	0.0282	0.0057
43	0.0624	0.0027	-0.0443
44	0.0219	0.0196	-0.0193
45	0.0705	0.0857	0.0891
46	-0.0749	-0.0817	-0.0550
47	0.0556	0.0361	0.0819
48	-0.0002	-0.0300	-0.0196
49	-0.0372	-0.0865	-0.0335
50	-0.0335	-0.0389	-0.0198
51	0.1469	0.1666	0.1975
52	-0.0588	-0.0719	-0.0369
53	-0.0592	-0.0332	-0.0362
54	0.0436	-0.0007	0.0147
55	-0.0037	0.0118	-0.0353
56	-0.0769	-0.0758	-0.0515
57	-0.0641	-0.0727	-0.0437
58	-0.0857	-0.0569	-0.0359
59	0.0313	0.0165	0.0770
60	-0.0106	-0.0312	-0.0392
61	0.0999	0.0853	0.1299
62	-0.0079	-0.0078	-0.0329
63	-0.0409	0.0062	-0.0187
64	-0.0083	-0.0624	-0.0417
65	0.0061	0.0204	-0.0032
66	-0.1116	-0.0496	-0.0472
67	0.1214	0.1035	0.1042
68	0.0081	-0.0130	0.0123
69	0.0286	0.0347	0.0484
70	0.0076	-0.0138	0.0355
71	-0.0590	-0.0270	-0.0392
72	0.0460	0.0703	-0.0341
73	0.0906	0.0270	0.0337
74	0.0209	0.0652	0.0609
75	-0.0135	-0.0436	-0.0545
76	0.0828	0.1082	0.0145
77	0.1131	0.0616	0.0087
78	0.0058	-0.0399	-0.0085
79	-0.0282	0.0041	-0.0400
80	-0.0116	-0.0048	-0.0145
81	-0.0700	-0.0569	-0.0448
82	-0.0284	-0.0123	-0.0345
83	0.1410	0.1966	0.1512
84	-0.0779	-0.0513	-0.0563
85	-0.0193	-0.0347	-0.0400
86	-0.0052	-0.0403	-0.0357
87	0.0095	-0.0180	-0.0319
88	0.0509	0.0450	0.0207
89	-0.0185	-0.0369	-0.0218
90	0.0353	0.0084	-0.0396
91	0.0289	-0.0002	-0.0329
92	0.1087	0.1216	0.0283
93	0.0251	0.0134	0.0136
94	-0.0278	-0.0149	0.0281
95	-0.0228	-0.0149	-0.0417
96	-0.0686	-0.0616	-0.0357
97	-0.0710	-0.0612	-0.0471
98	0.1151	0.1185	0.1099
99	0.0428	0.0458	0.0506
100	0.1400	0.1532	0.1270
101	0.0984	0.1674	0.1382
102	0.0818	0.0557	0.0389
103	0.0173	-0.0027	-0.0660
104	-0.0671	-0.0496	-0.0521
105	-0.0734	-0.0569	-0.0520
106	0.1351	0.1106	0.3135
107	0.0541	0.0340	0.0519
108	0.0350	0.0326	-0.0246
109	-0.0627	-0.0561	-0.0384
110	0.0200	0.0436	0.0352
111	-0.0049	-0.0464	-0.0329
112	-0.0083	-0.0324	0.0515
113	0.0600	0.0691	0.0124
114	-0.0244	-0.0430	-0.0557
115	0.1156	0.0486	0.0201
116	0.1131	0.0817	0.0530
117	-0.0127	-0.0316	-0.0497
118	0.0524	0.0612	0.0668
119	0.1410	0.1414	0.1838
120	-0.0798	-0.0470	-0.0509
121	0.1254	0.1548	0.0831
122	0.0235	0.0138	0.0450
123	0.0015	-0.0367	0.0129
124	0.1126	0.1208	0.1417
125	-0.0198	-0.0624	-0.0388
126	0.0258	-0.0001	0.0194
127	0.0551	0.0963	0.1552
128	-0.0038	-0.0381	-0.0209
129	0.0842	0.0438	0.0533
130	-0.0294	-0.0320	-0.0402
131	0.0935	0.1098	0.0626
132	-0.0122	0.0185	-0.0286
133	0.0022	0.0082	-0.0058
134	0.0521	0.0857	0.0714
135	0.0017	-0.0087	0.0127
136	-0.0404	-0.0231	-0.0428
137	-0.0119	0.0361	0.0518
138	-0.0541	-0.0509	-0.0352
139	0.0671	0.0136	-0.0409
140	0.0433	0.0186	0.0572
141	0.0744	0.0452	0.0526
142	0.0215	0.0294	0.0005
143	-0.0774	-0.0505	-0.0309
144	0.0725	0.1232	0.0983
145	-0.0416	-0.0149	-0.0508
146	0.1234	0.1516	0.1549
147	0.0105	0.0055	-0.0355
148	-0.0521	-0.0577	-0.0441
149	0.0945	0.0857	-0.0515
150	-0.0397	-0.0434	-0.0393
151	-0.0348	-0.0322	-0.0455
152	-0.0416	-0.0466	-0.0443
153	0.0002	-0.0300	-0.0625
154	0.1998	0.2195	0.1510
155	-0.0521	-0.0561	-0.0522
156	0.0553	0.0234	0.0126
157	0.0343	0.0417	0.0291
158	-0.0162	-0.0367	-0.0498
159	-0.0250	0.0326	0.0204
160	0.0458	0.0774	-0.0380
161	0.0225	0.0009	-0.0314
162	0.0681	0.0750	0.0497
163	0.0362	0.0577	0.0942
164	0.0198	0.0397	-0.0351
165	0.0365	-0.0153	-0.0045
166	-0.0798	-0.0655	-0.0465
167	-0.0553	-0.0553	-0.0507
168	0.0179	0.0172	0.0271
169	-0.0088	-0.0486	-0.0456
170	-0.0502	-0.0347	-0.0125
171	0.0453	0.0525	-0.0168
172	0.0079	0.0211	0.0674
173	-0.0185	-0.0351	-0.0318
174	0.0984	0.0620	0.0379
175	0.0619	0.0500	-0.0213
176	0.0135	-0.0171	-0.0340
177	-0.0150	0.0137	0.0654
178	0.0793	0.1027	0.0191
179	-0.0867	-0.0395	-0.0492
180	0.0867	0.0999	0.1085
181	0.0730	0.0387	0.0453
182	-0.0290	-0.0391	-0.0345
183	-0.0027	0.0166	-0.0260
184	-0.0588	-0.0695	-0.0406
185	-0.0345	-0.0436	-0.0478
186	0.0242	-0.0015	0.0052
187	-0.0588	-0.0750	-0.0417
188	-0.0725	-0.0399	-0.0375
189	0.0419	0.0415	0.0791
190	0.0362	0.0513	-0.0076
191	-0.0160	-0.0075	-0.0534
192	-0.0695	-0.0482	-0.0484
193	-0.0411	-0.0632	-0.0421
194	-0.0499	-0.0393	0.0199
195	-0.0283	-0.0580	-0.0380
196	-0.0695	-0.0758	-0.0388
197	0.0343	0.0620	0.0673
198	-0.0705	-0.0754	-0.0386
199	0.3055	0.2148	0.2273
200	-0.0282	-0.0234	-0.0295
201	0.0242	0.0351	-0.0372
202	-0.0710	-0.0809	-0.0831
203	-0.0783	-0.0671	-0.0498
204	-0.0632	-0.0274	-0.0330
205	-0.0600	0.0203	-0.0090
206	-0.0186	-0.0063	-0.0412
207	-0.0867	-0.0636	-0.0540
208	-0.0744	-0.0620	-0.0414
209	-0.0406	-0.0446	0.0341
210	-0.0208	0.0136	-0.0475
211	0.0122	0.0147	0.0626
212	-0.0509	-0.0369	-0.0584
213	0.0475	0.0580	0.0377
214	0.0234	0.0194	-0.0258
215	-0.0433	-0.0458	-0.0336
216	0.0375	0.0573	0.0353
217	0.0278	0.0197	0.0181
218	-0.0421	-0.0636	-0.0464
219	0.0234	0.0187	-0.0107
220	0.0222	0.0095	0.0116
221	0.0886	0.0813	0.1188
222	0.0656	0.0432	0.0515
223	0.1635	0.1208	0.1177
224	-0.0666	-0.0387	-0.0365
225	0.0268	-0.0417	-0.0332
226	0.0300	-0.0011	0.0110
227	-0.0219	-0.0185	-0.0226
228	-0.0185	0.0108	-0.0475
229	-0.0921	-0.0644	-0.0438
230	-0.0583	-0.0774	-0.0407
231	-0.0073	-0.0092	0.0724
232	-0.0392	-0.0379	-0.0548
233	-0.0091	0.0318	-0.0253
234	-0.0612	-0.0790	-0.0339
235	0.0487	-0.0167	-0.0328
236	-0.0155	-0.0157	-0.0343
237	-0.0377	-0.0024	-0.0357
238	-0.0690	-0.0604	-0.0438
239	0.0283	0.0727	0.0003
240	0.1038	0.1579	0.0521
241	-0.0590	-0.0620	-0.0372
242	-0.0813	-0.0766	-0.0588
243	0.0169	0.0557	-0.0291
244	0.0222	0.0381	-0.0425
245	-0.0039	-0.0569	-0.0380
246	0.0783	0.0967	0.1232
247	0.1332	0.0995	0.2095
248	0.0852	0.0505	0.0285
249	-0.0573	-0.0391	-0.0565

Source: P3 source-disjoint test split · p3_02007567 · SHA-256 a5461e9ad194504a…

p05Speech + burstsP3 curated burst test

Sadness + 1 known burst(s)

Synthetic speech with inserted bursts · P3 synthetic speech/burst mixture · 12.0 s

Tiny Base · values are model estimates, not ground truth

Strongest emotions relative to training

Contemplation

z +3.19 / +3.60raw 1.99 / 2.24

Sadness

z +3.31 / +3.42raw 2.51 / 2.60

Confusion

z +2.76 / +3.01raw 1.49 / 1.63

Longing

z +2.80 / +2.45raw 1.86 / 1.64

Doubt

z +2.54 / +2.63raw 1.19 / 1.23

Helplessness

z +2.56 / +2.33raw 1.78 / 1.62

Disappointment

z +2.39 / +2.44raw 1.67 / 1.71

The center of each bar is the S9 teacher median. Positive z is to the right; negative z is to the left. Ranking uses z, not raw teacher units.

Strongest VoiceNet dimensions relative to training

ASMR style (S_ASMR)

z +2.47 / +2.59raw 4.85 / 5.02

Whispered talking style (S_WHIS)

z +2.33 / +2.55raw 5.36 / 5.71

Vocal register (REGS)

z +1.96 / +2.06raw 3.68 / 3.82

Narrator style (S_NARR)

z +1.85 / +1.85raw 3.98 / 3.98

Background noise (BKGN)

z +1.56 / +1.33raw 3.89 / 3.72

Newsreader style (S_NEWS)

z +1.48 / +1.51raw 1.25 / 1.27

Articulation clarity (CLRT)

z +1.46 / +1.47raw 3.40 / 3.40

All 57 VoiceNet predictions, including raw units, are in the full table below. These seven are ranked by z; the top values may differ from the strongest raw dimensions.

Voice, speed and quality scores in context

Genuineness (0–6)z -0.85 / -0.86raw 0.96 / 0.93

Vocal-burst blend (0–10)z -2.41 / -2.38raw 0.08 / 0.17

Content enjoyment (CE)z +0.64 / +0.64raw 5.45 / 5.45

Production quality (PQ)z -0.01 / +0.19raw 7.04 / 7.21

Speech signal quality, calibratedz +0.17 / +0.29raw 3.57 / 3.63

Background quality, calibratedz +0.10 / +0.19raw 3.48 / 3.56

Overall quality, calibratedz +0.20 / +0.39raw 2.96 / 3.08

P.808 MOS estimatez +0.38 / +0.43raw 3.61 / 3.63

score content enjoymentz +0.77 / +0.70raw 4.74 / 4.72

score overall qualityz +0.50 / +0.14raw 2.91 / 2.72

Background Noisez -1.24 / -2.50raw 0.48 / 0.15

Tempo (TEMP)z -0.93 / -0.89raw 1.01 / 1.05

Arousal (AROU)z -0.95 / -0.95raw 1.27 / 1.27

Valence (VALN)z -0.38 / -0.21raw 1.91 / 2.09

Recording quality (RCQL)z +1.00 / +1.16raw 3.64 / 3.79

Background noise (BKGN)z +1.56 / +1.33raw 3.89 / 3.72

talking speedz -0.14 / +0.24raw 8.49 / 9.94

Characters per second (CPS): 9.58 raw · z +0.15

P3 metadata teacher estimate; not a Whisper output. Reference: 86,334 P3 training teacher values, median 9.03, SD 3.76. Cross-language character counts depend on writing system; compare with care.

Orange speaker embedding reconstruction

Cosine against Orange on this same clip (higher means closer to that teacher vector):

Embedding	Tiny	Base
Timbre · 128D	0.834	0.911
Identity · 250D	0.854	0.890

Vocal-burst regions

Known

Tiny

Base

0 s12.0 s

Purple marks known inserted burst intervals; other vocal sounds may be unlabeled.

Tiny: 1 regions, count-head estimate 0.92; Base: 1 regions, count-head estimate 1.09.

Exact predicted start and end times

Model	Region	Start (s)	End (s)	Duration (s)
Tiny	1	7.84	8.16	0.32
Base	1	7.82	8.16	0.34

Known inserted intervals: 7.85–8.16 s

All 192 score slots · raw and z values

#	Target	Tiny raw	Tiny z	Base raw	Base z	Train median	Train SD
Emotion scores Forty clip-level Empathic Insight emotion teacher outputs. Each row evaluates one named emotion score.
0	Affectionemo_Affection	0.551	+0.96	0.983	+1.71	0.007	0.570
1	Amusementemo_Amusement	0.020	+0.02	0.013	+0.02	-0.001	0.885
2	Angeremo_Anger	0.066	+0.10	0.012	+0.01	0.004	0.613
3	Astonishment Surpriseemo_Astonishment_Surprise	0.046	+0.07	-0.005	-0.02	0.005	0.572
4	Aweemo_Awe	0.028	+0.07	0.022	+0.05	0.000	0.427
5	Bitternessemo_Bitterness	0.334	+0.77	0.625	+1.47	0.013	0.415
6	Concentrationemo_Concentration	1.521	+1.20	1.561	+1.25	0.634	0.741
7	Confusionemo_Confusion	1.493	+2.76	1.626	+3.01	0.001	0.540
8	Contemplationemo_Contemplation	1.987	+3.19	2.236	+3.60	0.082	0.598
9	Contemptemo_Contempt	0.032	+0.07	-0.020	-0.04	-0.000	0.464
10	Contentmentemo_Contentment	0.279	+0.54	0.396	+0.77	0.000	0.514
11	Disappointmentemo_Disappointment	1.673	+2.39	1.706	+2.44	0.000	0.700
12	Disgustemo_Disgust	0.057	+0.10	0.023	+0.03	0.007	0.489
13	Distressemo_Distress	1.717	+2.09	1.596	+1.94	0.000	0.821
14	Doubtemo_Doubt	1.190	+2.54	1.231	+2.63	0.006	0.466
15	Elationemo_Elation	-0.073	-0.12	-0.062	-0.10	0.012	0.728
16	Embarrassmentemo_Embarrassment	0.138	+0.22	0.180	+0.32	0.043	0.430
17	Emotional Numbnessemo_Emotional_Numbness	1.303	+1.42	1.412	+1.54	0.004	0.917
18	Fatigue Exhaustionemo_Fatigue_Exhaustion	0.862	+1.55	0.557	+0.98	0.028	0.539
19	Fearemo_Fear	0.663	+1.06	0.329	+0.52	0.015	0.610
20	Helplessnessemo_Helplessness	1.781	+2.56	1.620	+2.33	-0.004	0.696
21	Hope Enthusiasm Optimismemo_Hope_Enthusiasm_Optimism	0.077	-0.05	0.092	-0.03	0.117	0.760
22	Impatience and Irritabilityemo_Impatience_and_Irritability	0.268	+0.17	0.129	-0.03	0.149	0.705
23	Infatuationemo_Infatuation	0.468	+0.91	1.015	+1.93	-0.015	0.533
24	Interestemo_Interest	1.405	-0.20	1.438	-0.17	1.589	0.907
25	Intoxication Altered States of Consciousnessemo_Intoxication_Altered_States_of_Consciousness	0.008	+0.06	0.038	+0.11	-0.025	0.559
26	Jealousy and Envyemo_Jealousy_and_Envy	0.236	+0.40	0.177	+0.27	0.059	0.442
27	Longingemo_Longing	1.856	+2.80	1.637	+2.45	0.087	0.632
28	Malevolence Maliceemo_Malevolence_Malice	0.096	+0.08	0.027	-0.05	0.055	0.534
29	Painemo_Pain	0.447	+0.77	0.327	+0.57	-0.002	0.579
30	Pleasure Ecstasyemo_Pleasure_Ecstasy	0.013	-0.01	0.016	-0.00	0.017	0.614
31	Prideemo_Pride	0.031	+0.06	0.024	+0.04	0.002	0.509
32	Reliefemo_Relief	0.910	+1.29	0.899	+1.27	0.033	0.681
33	Sadnessemo_Sadness	2.513	+3.31	2.596	+3.42	0.000	0.759
34	Sexual Lustemo_Sexual_Lust	0.155	+0.25	0.189	+0.32	0.030	0.494
35	Shameemo_Shame	1.014	+1.96	1.132	+2.19	0.013	0.510
36	Sournessemo_Sourness	-0.003	+0.01	-0.004	+0.00	-0.005	0.439
37	Teasingemo_Teasing	0.018	+0.03	-0.031	-0.06	0.000	0.545
38	Thankfulness Gratitudeemo_Thankfulness_Gratitude	0.176	+0.19	0.429	+0.56	0.041	0.697
39	Triumphemo_Triumph	0.078	+0.16	0.066	+0.14	-0.007	0.521
VoiceNet dimensions Fifty-seven VoiceNet voice, delivery, style, and recording dimensions. Codes are expanded in the target column.
40	Perceived voice age (AGEV)vn_AGEV_reg	4.227	+1.00	4.512	+1.23	2.984	1.238
41	Arousal (AROU)vn_AROU_reg	1.266	-0.95	1.266	-0.95	2.359	1.147
42	Arousal shift (ARSH)vn_ARSH_reg	1.831	-0.86	1.547	-1.19	2.580	0.867
43	Vocal attack (ATCK)vn_ATCK_reg	1.224	-0.72	1.049	-0.86	2.162	1.295
44	Background noise (BKGN)vn_BKGN_reg	3.887	+1.56	3.716	+1.33	2.703	0.761
45	Brightness (BRGT)vn_BRGT_reg	1.849	-0.18	1.758	-0.29	1.991	0.813
46	Speech chunking (CHNK)vn_CHNK_reg	1.346	-0.40	1.393	-0.37	1.847	1.239
47	Articulation clarity (CLRT)vn_CLRT_reg	3.396	+1.46	3.403	+1.47	2.018	0.945
48	Cognitive load (COGL)vn_COGL_reg	3.224	+1.07	2.997	+0.85	2.094	1.061
49	Dynamic arc (DARC)vn_DARC_reg	1.288	-0.24	1.243	-0.27	1.615	1.380
50	Disfluency (DFLU)vn_DFLU_reg	2.727	+0.20	2.891	+0.34	2.488	1.184
51	Emphasis (EMPH)vn_EMPH_reg	1.992	-0.40	2.164	-0.29	2.607	1.524
52	Esthetics (ESTH)vn_ESTH_reg	3.128	+0.93	3.384	+1.26	2.402	0.782
53	Content appropriateness (EXPL)vn_EXPL_reg	0.126	+0.12	0.218	+0.41	0.086	0.322
54	Focus (FOCS)vn_FOCS_reg	1.045	-1.18	1.097	-1.13	2.344	1.102
55	Fullness (FULL)vn_FULL_reg	2.255	+0.54	2.136	+0.40	1.778	0.889
56	Perceived gender (GEND)vn_GEND_reg	1.642	-1.52	1.505	-1.61	4.055	1.588
57	Harmonicity (HARM)vn_HARM_reg	1.573	-1.09	1.534	-1.13	2.480	0.836
58	Metallic character (METL)vn_METL_reg	1.220	-0.42	1.097	-0.55	1.621	0.958
59	Pitch range (RANG)vn_RANG_reg	2.646	-0.30	2.693	-0.25	2.914	0.897
60	Recording quality (RCQL)vn_RCQL_reg	3.645	+1.00	3.785	+1.16	2.754	0.888
61	Vocal register (REGS)vn_REGS_reg	3.680	+1.96	3.817	+2.06	1.198	1.268
62	Respiration (RESP)vn_RESP_reg	3.050	+0.35	3.081	+0.38	2.680	1.056
63	Roughness (ROUG)vn_ROUG_reg	1.258	-0.87	1.052	-1.11	2.033	0.887
64	Chest resonance (R_CHST)vn_R_CHST_reg	1.610	-0.62	1.477	-0.78	2.135	0.844
65	Head resonance (R_HEAD)vn_R_HEAD_reg	2.973	+1.00	2.948	+0.97	2.148	0.822
66	Mask resonance (R_MASK)vn_R_MASK_reg	2.391	+0.48	2.359	+0.45	1.908	1.005
67	Mixed resonance (R_MIXD)vn_R_MIXD_reg	1.852	+0.50	1.800	+0.43	1.436	0.841
68	Nasal resonance (R_NASL)vn_R_NASL_reg	3.601	+0.77	3.572	+0.75	2.791	1.047
69	Oral resonance (R_ORAL)vn_R_ORAL_reg	2.119	-0.09	2.017	-0.22	2.184	0.741
70	Throat resonance (R_THRT)vn_R_THRT_reg	2.713	+0.80	2.697	+0.78	2.070	0.803
71	Smoothness (SMTH)vn_SMTH_reg	2.106	-0.03	2.186	+0.04	2.143	1.093
72	Stance (STNC)vn_STNC_reg	1.693	-0.83	1.409	-1.08	2.633	1.137
73	Speech structure (STRU)vn_STRU_reg	2.765	+0.66	2.861	+0.76	2.137	0.958
74	ASMR style (S_ASMR)vn_S_ASMR_reg	4.851	+2.47	5.023	+2.59	1.370	1.411
75	Authoritative style (S_AUTH)vn_S_AUTH_reg	1.006	-0.08	0.840	-0.24	1.088	1.043
76	Cartoonish style (S_CART)vn_S_CART_reg	1.819	+0.18	1.900	+0.24	1.560	1.401
77	Casual style (S_CASU)vn_S_CASU_reg	2.205	-1.24	2.534	-0.98	3.793	1.278
78	Conversational style (S_CONV)vn_S_CONV_reg	2.171	-0.32	2.212	-0.29	2.594	1.318
79	Dramatic style (S_DRAM)vn_S_DRAM_reg	1.947	-0.67	1.827	-0.78	2.721	1.148
80	Formal style (S_FORM)vn_S_FORM_reg	2.301	+1.08	2.226	+1.01	1.195	1.021
81	Monologue style (S_MONO)vn_S_MONO_reg	4.177	+1.05	4.415	+1.24	2.824	1.284
82	Narrator style (S_NARR)vn_S_NARR_reg	3.975	+1.85	3.975	+1.85	1.307	1.446
83	Newsreader style (S_NEWS)vn_S_NEWS_reg	1.249	+1.48	1.267	+1.51	0.408	0.568
84	Playful style (S_PLAY)vn_S_PLAY_reg	1.202	-0.87	1.207	-0.87	2.352	1.315
85	Ranting or angry style (S_RANT)vn_S_RANT_reg	-0.300	-1.17	-0.490	-1.32	1.213	1.289
86	Storytelling style (S_STRY)vn_S_STRY_reg	2.952	+0.34	3.246	+0.56	2.480	1.366
87	Teacher or didactic style (S_TECH)vn_S_TECH_reg	2.061	+1.15	2.089	+1.18	0.646	1.227
88	Whispered talking style (S_WHIS)vn_S_WHIS_reg	5.364	+2.33	5.714	+2.55	1.597	1.618
89	Tempo (TEMP)vn_TEMP_reg	1.013	-0.93	1.055	-0.89	2.117	1.190
90	Tension (TENS)vn_TENS_reg	1.420	-0.16	1.312	-0.29	1.559	0.852
91	Valence (VALN)vn_VALN_reg	1.906	-0.38	2.091	-0.21	2.328	1.118
92	Valence shift (VALS)vn_VALS_reg	2.075	-0.41	2.410	-0.10	2.518	1.079
93	Velocity flux (VFLX)vn_VFLX_reg	1.410	-0.70	1.594	-0.55	2.256	1.208
94	Volatility (VOLT)vn_VOLT_reg	1.836	-0.85	1.809	-0.88	2.586	0.886
95	Vulnerability (VULN)vn_VULN_reg	3.344	+0.71	3.862	+1.23	2.648	0.984
96	Warmth (WARM)vn_WARM_reg	2.742	+0.18	2.819	+0.27	2.578	0.909
Genuineness, blend, and legacy quality Genuineness and vocal-burst blend are predicted. R_quality has Ladder training labels but no valid P3 test labels.
97	Genuineness (0–6)genuineness_0_6	0.955	-0.85	0.930	-0.86	2.332	1.621
98	Vocal-burst blend (0–10)blend_0_10	0.083	-2.41	0.168	-2.38	6.676	2.738
99	Legacy R_quality (no P3 test labels)R_quality	0.190	-2.68	0.190	-2.68	1.095	0.338
Empathic Insight Plus extra scores Nineteen additional clip-level teacher scores, including background noise and content enjoyment.
100	Ageeiv_extra:Age	3.172	-0.27	3.184	-0.23	3.250	0.293
101	Arousaleiv_extra:Arousal	1.028	-0.60	1.072	-0.50	1.289	0.435
102	Authenticityeiv_extra:Authenticity	2.961	+1.92	3.031	+2.38	2.667	0.153
103	Background Noiseeiv_extra:Background_Noise	0.481	-1.24	0.146	-2.50	0.808	0.264
104	Confident vs. Hesitanteiv_extra:Confident_vs._Hesitant	1.589	+1.81	1.596	+1.84	1.040	0.303
105	Gendereiv_extra:Gender	1.582	+2.20	1.488	+2.11	-0.621	0.999
106	High-Pitched vs. Low-Pitchedeiv_extra:High-Pitched_vs._Low-Pitched	1.710	-0.47	1.712	-0.46	1.827	0.250
107	Monotone vs. Expressiveeiv_extra:Monotone_vs._Expressive	1.984	+0.27	2.096	+0.50	1.859	0.470
108	Recording Qualityeiv_extra:Recording_Quality	2.371	+0.68	2.450	+0.92	2.144	0.332
109	Serious vs. Humorouseiv_extra:Serious_vs._Humorous	0.656	-0.80	0.652	-0.82	0.929	0.340
110	Soft vs. Harsheiv_extra:Soft_vs._Harsh	0.915	+1.98	0.905	+1.95	0.281	0.320
111	Submissive vs. Dominanteiv_extra:Submissive_vs._Dominant	0.279	-0.30	0.340	-0.11	0.376	0.324
112	Valenceeiv_extra:Valence	-0.552	-1.46	-1.014	-2.68	0.005	0.380
113	Vulnerable vs. Emotionally Detachedeiv_extra:Vulnerable_vs._Emotionally_Detached	1.150	-1.29	1.092	-1.43	1.715	0.437
114	Warm vs. Coldeiv_extra:Warm_vs._Cold	0.040	-0.04	0.113	+0.21	0.051	0.300
115	score background qualityeiv_extra:score_background_quality	3.361	+0.09	3.203	-0.14	3.301	0.693
116	score content enjoymenteiv_extra:score_content_enjoyment	4.739	+0.77	4.719	+0.70	4.507	0.303
117	score overall qualityeiv_extra:score_overall_quality	2.905	+0.50	2.722	+0.14	2.652	0.507
118	score speech qualityeiv_extra:score_speech_quality	1.807	-0.01	1.811	+0.02	1.808	0.146
Meta AudioBox Aesthetics Four AudioBox aesthetic teacher outputs. Expansions follow the official Meta model card.
119	Content enjoyment (CE)audiobox:CE	5.455	+0.64	5.455	+0.64	4.799	1.018
120	Content usefulness (CU)audiobox:CU	5.744	+0.10	5.939	+0.29	5.649	1.001
121	Production complexity (PC)audiobox:PC	2.729	+0.25	2.754	+0.26	2.331	1.617
122	Production quality (PQ)audiobox:PQ	7.036	-0.01	7.210	+0.19	7.044	0.879
Microsoft DNSMOS Seven DNSMOS teacher outputs: raw and calibrated SIG/BAK/OVRL estimates plus P.808 MOS.
123	Speech signal quality, rawdnsmos:SIG_raw	4.040	+0.21	4.150	+0.37	3.900	0.669
124	Background quality, rawdnsmos:BAK_raw	3.452	+0.21	3.575	+0.32	3.211	1.124
125	Overall quality, rawdnsmos:OVRL_raw	3.275	+0.23	3.459	+0.46	3.085	0.812
126	Speech signal quality, calibrateddnsmos:SIG	3.571	+0.17	3.632	+0.29	3.488	0.501
127	Background quality, calibrateddnsmos:BAK	3.479	+0.10	3.562	+0.19	3.389	0.928
128	Overall quality, calibrateddnsmos:OVRL	2.960	+0.20	3.079	+0.39	2.840	0.606
129	P.808 MOS estimatednsmos:P808_MOS	3.609	+0.38	3.634	+0.43	3.421	0.496
Vocal-burst count The regression target is log(1 + count). A separate table also reports count error after inverse transformation.
130	Vocal-burst count, log(1 + count)burst_count_log1p	0.652	+1.01	0.737	+1.14	0.000	0.647
VoiceCLAP attributes Sixty-one individual VoiceCLAP attribute teacher scores. The raw 768D VoiceCLAP embedding is stored in sidecars but is not a model output.
131	Affectionvoiceclap_attribute:Affection	1.033	+0.15	1.070	+0.22	0.947	0.554
132	Agevoiceclap_attribute:Age	3.208	-0.04	3.226	-0.01	3.229	0.547
133	Amusementvoiceclap_attribute:Amusement	-0.163	-0.97	-0.123	-0.90	0.392	0.572
134	Angervoiceclap_attribute:Anger	0.605	-0.77	0.591	-0.79	0.992	0.506
135	Arousalvoiceclap_attribute:Arousal	0.633	-1.26	0.754	-1.07	1.420	0.622
136	Astonishment Surprisevoiceclap_attribute:Astonishment_Surprise	0.045	-0.97	0.223	-0.60	0.509	0.479
137	Authenticityvoiceclap_attribute:Authenticity	3.083	+1.87	3.155	+2.31	2.770	0.167
138	Awevoiceclap_attribute:Awe	0.476	-0.24	0.484	-0.21	0.539	0.259
139	Background Noisevoiceclap_attribute:Background_Noise	0.347	-0.84	0.335	-0.88	0.567	0.264
140	Bitternessvoiceclap_attribute:Bitterness	0.646	+0.23	0.679	+0.37	0.592	0.236
141	Concentrationvoiceclap_attribute:Concentration	1.857	+1.21	1.770	+1.05	1.214	0.531
142	Confident vs. Hesitantvoiceclap_attribute:Confident_vs._Hesitant	1.619	+1.17	1.676	+1.30	1.069	0.468
143	Confusionvoiceclap_attribute:Confusion	1.090	+1.34	1.032	+1.17	0.643	0.334
144	Contemplationvoiceclap_attribute:Contemplation	1.988	+2.98	2.019	+3.06	0.780	0.406
145	Contemptvoiceclap_attribute:Contempt	0.062	-1.91	0.040	-1.97	0.709	0.339
146	Contentmentvoiceclap_attribute:Contentment	0.658	+0.23	0.913	+1.06	0.588	0.307
147	Disappointmentvoiceclap_attribute:Disappointment	0.983	+0.77	0.966	+0.71	0.760	0.291
148	Disgustvoiceclap_attribute:Disgust	0.224	-1.93	0.201	-2.05	0.625	0.207
149	Distressvoiceclap_attribute:Distress	1.237	+0.89	1.353	+1.22	0.927	0.350
150	Doubtvoiceclap_attribute:Doubt	0.830	+1.57	0.799	+1.40	0.535	0.188
151	Elationvoiceclap_attribute:Elation	0.106	-1.09	0.330	-0.53	0.539	0.397
152	Embarrassmentvoiceclap_attribute:Embarrassment	0.190	-0.37	0.198	-0.35	0.307	0.314
153	Emotional Numbnessvoiceclap_attribute:Emotional_Numbness	1.046	+1.44	0.922	+0.97	0.664	0.266
154	Fatigue Exhaustionvoiceclap_attribute:Fatigue_Exhaustion	0.966	+1.93	0.990	+2.02	0.462	0.261
155	Fearvoiceclap_attribute:Fear	0.656	+0.18	0.647	+0.14	0.618	0.212
156	Gendervoiceclap_attribute:Gender	1.191	+1.34	1.340	+1.48	-0.151	1.005
157	Helplessnessvoiceclap_attribute:Helplessness	1.151	+1.84	1.252	+2.21	0.658	0.268
158	High-Pitched vs. Low-Pitchedvoiceclap_attribute:High-Pitched_vs._Low-Pitched	1.843	+0.01	1.775	-0.17	1.840	0.375
159	Hope Enthusiasm Optimismvoiceclap_attribute:Hope_Enthusiasm_Optimism	0.432	-0.69	0.554	-0.38	0.705	0.396
160	Impatience and Irritabilityvoiceclap_attribute:Impatience_and_Irritability	0.405	-1.20	0.430	-1.15	1.052	0.541
161	Infatuationvoiceclap_attribute:Infatuation	0.578	-0.09	0.640	+0.10	0.608	0.332
162	Interestvoiceclap_attribute:Interest	1.279	-0.72	1.386	-0.48	1.598	0.440
163	Intoxication Altered States of Consciousnessvoiceclap_attribute:Intoxication_Altered_States_of_Consciousness	0.129	-0.80	0.240	-0.57	0.502	0.463
164	Jealousy & Envyvoiceclap_attribute:Jealousy_&_Envy	0.462	-0.25	0.441	-0.33	0.523	0.245
165	Longingvoiceclap_attribute:Longing	1.027	+2.23	1.037	+2.27	0.538	0.220
166	Malevolence Malicevoiceclap_attribute:Malevolence_Malice	0.295	-1.56	0.243	-1.70	0.833	0.346
167	Monotone vs. Expressivevoiceclap_attribute:Monotone_vs._Expressive	1.721	-0.09	1.944	+0.28	1.775	0.594
168	Painvoiceclap_attribute:Pain	0.610	+1.05	0.638	+1.18	0.381	0.218
169	Pleasure Ecstasyvoiceclap_attribute:Pleasure_Ecstasy	0.222	-0.93	0.413	-0.30	0.503	0.301
170	Pridevoiceclap_attribute:Pride	0.658	-0.35	0.604	-0.51	0.780	0.349
171	Recording Qualityvoiceclap_attribute:Recording_Quality	2.589	+0.84	2.603	+0.88	2.313	0.328
172	Reliefvoiceclap_attribute:Relief	1.041	+0.04	1.142	+0.28	1.025	0.415
173	Sadnessvoiceclap_attribute:Sadness	1.501	+2.39	1.569	+2.61	0.752	0.313
174	Serious vs. Humorousvoiceclap_attribute:Serious_vs._Humorous	0.233	-1.00	0.278	-0.93	0.803	0.568
175	Sexual Lustvoiceclap_attribute:Sexual_Lust	0.039	-1.42	0.147	-1.17	0.635	0.419
176	Shamevoiceclap_attribute:Shame	1.035	+1.80	1.112	+2.07	0.526	0.283
177	Soft vs. Harshvoiceclap_attribute:Soft_vs._Harsh	0.872	+1.98	0.999	+2.33	0.160	0.360
178	Sournessvoiceclap_attribute:Sourness	0.328	-1.30	0.290	-1.43	0.706	0.291
179	Submissive vs. Dominantvoiceclap_attribute:Submissive_vs._Dominant	0.242	-1.06	0.211	-1.15	0.623	0.359
180	Teasingvoiceclap_attribute:Teasing	-0.035	-1.52	-0.053	-1.57	0.540	0.379
181	Thankfulness Gratitudevoiceclap_attribute:Thankfulness_Gratitude	1.532	+0.28	1.784	+0.76	1.384	0.529
182	Triumphvoiceclap_attribute:Triumph	0.266	-1.25	0.399	-0.88	0.716	0.359
183	Valencevoiceclap_attribute:Valence	-0.403	-0.62	-0.273	-0.42	-0.007	0.635
184	Vulnerable vs. Emotionally Detachedvoiceclap_attribute:Vulnerable_vs._Emotionally_Detached	1.528	-0.20	1.084	-1.00	1.638	0.556
185	Warm vs. Coldvoiceclap_attribute:Warm_vs._Cold	0.204	+0.67	0.328	+0.99	-0.066	0.400
186	durationvoiceclap_attribute:duration	12.965	+0.32	13.330	+0.38	10.914	6.354
187	score background qualityvoiceclap_attribute:score_background_quality	3.454	+0.42	3.474	+0.46	3.245	0.498
188	score content enjoymentvoiceclap_attribute:score_content_enjoyment	4.673	+0.12	4.652	-0.03	4.656	0.147
189	score overall qualityvoiceclap_attribute:score_overall_quality	2.879	+0.59	2.907	+0.66	2.635	0.412
190	score speech qualityvoiceclap_attribute:score_speech_quality	1.870	-0.30	1.874	-0.24	1.891	0.069
191	talking speedvoiceclap_attribute:talking_speed	8.492	-0.14	9.943	+0.24	9.028	3.756

All Orange embedding components

The cosine above is the meaningful vector-level comparison; component values have no standalone semantic label.

Timbre — all 128 vector components

Dimension	Tiny	Base	Orange teacher
0	0.0263	0.0966	0.1611
1	0.1999	0.2210	0.1793
2	0.0440	0.0544	0.0296
3	-0.0319	-0.0116	-0.0215
4	-0.0853	-0.0855	-0.0750
5	-0.0511	-0.0364	-0.0582
6	0.0486	0.0708	0.0993
7	0.1099	0.0806	0.0546
8	0.1322	0.1048	0.1009
9	0.0073	0.0146	-0.0192
10	-0.0965	-0.0778	-0.0742
11	-0.0189	-0.0520	-0.0802
12	-0.1092	-0.0860	-0.0803
13	0.0873	0.0753	0.1320
14	0.0896	0.0463	-0.0317
15	0.0350	0.0733	0.0736
16	-0.0830	-0.0753	-0.0668
17	-0.0830	-0.1138	-0.0830
18	-0.0915	-0.0782	-0.0736
19	-0.0479	-0.0675	-0.0755
20	-0.0162	-0.0467	-0.0766
21	0.1738	0.1932	0.1622
22	0.0780	0.1187	0.0976
23	0.0557	0.0093	0.0466
24	0.0479	0.0190	0.0194
25	0.0168	0.0270	-0.0120
26	-0.1092	-0.0962	-0.0748
27	0.0269	0.0184	0.1087
28	-0.1030	-0.1064	-0.0880
29	-0.0177	-0.0610	-0.0854
30	0.0192	0.0643	0.1018
31	-0.1115	-0.0864	-0.0483
32	0.0239	0.0307	-0.0126
33	0.1776	0.1506	0.1261
34	-0.0738	-0.0802	-0.0715
35	0.0673	0.0211	0.0641
36	-0.0600	-0.1011	-0.0858
37	0.1330	0.0634	0.0742
38	0.0673	0.1072	0.1492
39	0.0607	0.0309	0.0169
40	-0.0224	0.0016	0.0150
41	0.0325	0.0432	0.0723
42	-0.1084	-0.0855	-0.0805
43	-0.0903	-0.0872	-0.0821
44	0.0128	0.0393	-0.0023
45	-0.0923	-0.0233	-0.0306
46	-0.0421	-0.0790	-0.0753
47	-0.0999	-0.1048	-0.0807
48	-0.1099	-0.0790	-0.0779
49	-0.0195	0.0017	-0.0094
50	0.0946	0.0798	0.0471
51	-0.0198	-0.0008	-0.0416
52	0.0680	0.0245	-0.0476
53	-0.0279	-0.0465	-0.0153
54	-0.0953	-0.0843	-0.0893
55	0.0192	0.0262	-0.0252
56	-0.0834	-0.0839	-0.0757
57	0.1376	0.1916	0.1167
58	-0.0684	-0.0778	-0.0141
59	0.0554	0.0786	0.1284
60	0.0684	0.1383	0.0925
61	0.1199	0.0684	0.0249
62	-0.0092	-0.0089	0.0300
63	0.0461	0.1130	0.1554
64	0.1169	0.1351	0.1783
65	-0.0934	-0.0745	-0.0651
66	0.0199	0.0610	0.0955
67	-0.0880	-0.0688	-0.0770
68	0.1676	0.1433	0.1152
69	0.1253	0.0679	0.0305
70	0.1761	0.1334	0.1355
71	0.0550	0.0569	0.0422
72	0.1937	0.1785	0.1565
73	0.0750	0.0704	0.1494
74	0.0016	-0.0197	-0.0657
75	0.2353	0.1842	0.2090
76	0.1369	0.1228	0.0224
77	-0.0846	-0.0860	-0.0729
78	-0.0765	-0.0720	-0.0710
79	0.1053	0.0235	-0.0140
80	-0.1061	-0.1089	-0.0723
81	0.1238	0.1236	0.0869
82	-0.0115	-0.0301	-0.0657
83	-0.0673	-0.0446	-0.0817
84	0.0500	0.0589	0.1469
85	-0.0361	-0.0194	-0.0238
86	0.1376	0.1703	0.1724
87	0.0125	0.0015	0.0283
88	-0.1030	-0.0741	-0.0742
89	-0.1046	-0.0802	-0.0732
90	0.0584	0.1179	0.1460
91	-0.0081	-0.0040	0.0518
92	-0.0263	-0.0475	-0.0775
93	0.0340	0.0501	0.0510
94	0.1315	0.1252	0.1520
95	-0.0329	-0.0350	-0.0487
96	-0.0607	-0.0630	-0.0275
97	0.0842	0.0819	0.1125
98	-0.0119	-0.0610	-0.0806
99	0.2245	0.2161	0.1515
100	-0.0088	-0.0226	0.0395
101	-0.0792	-0.0851	-0.0771
102	0.0417	0.0182	0.0865
103	-0.0642	-0.0872	-0.0842
104	0.0461	0.0444	0.0493
105	-0.0619	-0.1154	-0.0770
106	-0.1007	-0.1044	-0.0959
107	-0.0780	-0.0925	-0.0743
108	-0.1046	-0.0933	-0.0865
109	0.1046	0.1416	0.1666
110	-0.0429	-0.0338	-0.0928
111	0.0684	0.0688	0.0556
112	-0.0323	-0.0422	-0.0348
113	-0.0604	-0.0356	-0.0635
114	0.0371	0.0178	-0.0229
115	0.1369	0.1015	0.0621
116	0.0934	0.1081	0.0594
117	-0.0727	-0.0868	-0.0716
118	-0.0926	-0.0815	-0.0777
119	0.0051	0.0323	-0.0239
120	0.1699	0.1997	0.1801
121	0.0054	-0.0332	-0.0402
122	-0.0911	-0.1072	-0.0820
123	-0.0515	-0.0259	-0.0066
124	-0.0327	0.0087	0.1066
125	-0.0175	0.0260	0.1129
126	0.0386	0.0317	0.0264
127	0.0680	0.1375	0.0879

Identity — all 250 vector components

Dimension	Tiny	Base	Orange teacher
0	-0.0312	-0.0427	-0.0451
1	-0.0425	-0.0383	-0.0400
2	0.0135	0.0544	0.0551
3	-0.0359	-0.0445	-0.0541
4	0.0457	0.0583	0.0464
5	0.0767	0.0593	0.1240
6	0.0814	0.0932	0.0453
7	-0.0718	-0.0482	-0.0419
8	0.0274	0.0575	0.0558
9	0.0492	0.0880	0.0726
10	-0.0154	-0.0019	-0.0274
11	-0.0533	-0.0417	-0.0560
12	0.1142	0.1072	0.0855
13	0.1804	0.2206	0.2203
14	-0.0140	-0.0070	-0.0065
15	0.1072	0.0989	0.0714
16	0.0082	-0.0136	-0.0238
17	-0.0297	0.0065	-0.0497
18	-0.0046	-0.0002	-0.0134
19	-0.0390	0.0051	0.0157
20	0.0287	0.0347	0.0868
21	-0.0277	-0.0208	-0.0384
22	-0.0413	-0.0513	-0.0429
23	-0.0630	-0.0435	-0.0400
24	0.0972	0.1310	0.1317
25	-0.0416	0.0129	0.0322
26	0.1136	0.1176	0.2103
27	0.0250	0.0095	0.0442
28	0.0492	0.0539	0.0233
29	-0.0387	-0.0585	-0.0398
30	-0.0278	-0.0328	-0.0360
31	0.0217	0.0179	-0.0498
32	0.1459	0.1761	0.1725
33	0.0548	0.0260	0.0210
34	0.0879	0.0704	0.0215
35	-0.0274	-0.0300	-0.0422
36	0.1113	0.0616	0.0309
37	-0.0280	-0.0267	-0.0286
38	-0.0419	-0.0373	-0.0574
39	0.0327	0.0211	-0.0038
40	0.0196	0.0221	0.0231
41	-0.0338	-0.0030	-0.0475
42	0.1441	0.1543	0.0992
43	-0.0803	-0.1031	-0.0489
44	-0.0038	-0.0242	-0.0463
45	0.0094	0.0092	-0.0241
46	-0.0030	-0.0324	0.0212
47	0.1277	0.1124	0.0736
48	0.0171	0.0065	0.0288
49	0.0867	0.0834	0.0956
50	0.1107	0.0968	0.1833
51	0.0562	0.0585	0.0218
52	-0.0723	-0.0520	-0.0408
53	0.0554	0.0772	0.0415
54	-0.0838	-0.0570	-0.0699
55	0.0097	0.0224	0.0093
56	0.0296	0.0234	-0.0037
57	0.0082	-0.0042	0.0408
58	-0.0372	-0.0443	-0.0397
59	0.0767	0.0735	0.0804
60	-0.0220	0.0016	-0.0403
61	-0.0398	-0.0329	-0.0384
62	0.0677	0.0989	0.0620
63	-0.0392	-0.0414	-0.0290
64	-0.0008	-0.0445	-0.0461
65	-0.0199	-0.0199	-0.0226
66	0.0004	0.0414	0.0138
67	0.0536	0.0236	-0.0316
68	0.0674	0.0598	0.0939
69	-0.0218	0.0041	0.0272
70	-0.0091	-0.0183	-0.0360
71	-0.0350	-0.0362	-0.0271
72	0.0130	0.0228	0.0177
73	0.0665	0.0546	0.0160
74	-0.0521	-0.0629	-0.0446
75	-0.0155	-0.0448	-0.0602
76	0.0521	0.0495	0.0711
77	-0.1318	-0.1321	-0.0878
78	0.1043	0.0906	0.1562
79	-0.0174	-0.0134	-0.0073
80	-0.0791	-0.0533	-0.0439
81	-0.0384	-0.0241	-0.0495
82	-0.0011	-0.0126	-0.0397
83	0.0961	0.0979	0.1351
84	-0.0283	0.0131	-0.0623
85	-0.0469	-0.0225	-0.0327
86	-0.0097	-0.0198	-0.0281
87	-0.0193	-0.0350	-0.0352
88	0.0095	0.0080	-0.0205
89	-0.0492	-0.0386	-0.0399
90	0.1072	0.0286	0.0510
91	0.0808	0.0854	0.1904
92	-0.0246	-0.0443	-0.0382
93	-0.0685	-0.0777	-0.0501
94	-0.0310	-0.0219	0.0462
95	0.0410	0.0689	0.0422
96	0.0659	0.0658	0.1094
97	-0.0750	-0.0510	-0.0520
98	-0.0065	0.0378	0.0027
99	-0.1125	-0.0999	-0.0553
100	0.2015	0.1564	0.1852
101	0.1066	0.1491	0.0399
102	0.0407	0.0344	-0.0033
103	0.0354	0.0193	-0.0577
104	0.0212	-0.0035	-0.0223
105	-0.0028	-0.0066	0.0403
106	-0.0556	-0.0699	-0.0340
107	0.0387	0.0520	0.0185
108	-0.0312	-0.0396	-0.0329
109	-0.0849	-0.0668	-0.0425
110	-0.0177	-0.0277	-0.0374
111	0.0914	0.1010	0.0471
112	0.0419	0.0813	0.0581
113	0.0890	0.0304	0.0163
114	-0.0371	-0.0557	-0.0616
115	-0.0808	-0.0849	-0.0313
116	0.0773	0.0948	0.0648
117	-0.0735	-0.0803	-0.0721
118	0.0142	0.0111	0.0649
119	0.0597	0.0590	0.1024
120	-0.1060	-0.0963	-0.0563
121	0.0738	0.0917	0.0620
122	-0.0501	-0.0448	-0.0417
123	-0.0316	-0.0236	-0.0452
124	0.1582	0.1460	0.0967
125	-0.0121	0.0220	-0.0127
126	0.0436	-0.0162	0.0223
127	-0.0139	-0.0407	-0.0454
128	-0.0335	-0.0435	-0.0550
129	0.0049	-0.0197	-0.0420
130	0.0381	0.0725	0.1056
131	-0.0510	-0.0564	-0.0386
132	-0.0315	-0.0303	-0.0468
133	-0.0469	-0.0339	-0.0338
134	0.1336	0.0870	0.0740
135	0.0065	0.0241	0.0095
136	0.0920	0.0751	0.0381
137	-0.0199	-0.0057	-0.0108
138	-0.0463	-0.0337	-0.0389
139	-0.0250	-0.0181	-0.0204
140	0.0867	0.1222	0.1057
141	-0.0682	-0.0564	-0.0437
142	0.0308	0.0417	0.0629
143	0.0879	0.0968	0.1080
144	-0.0375	0.0170	0.0214
145	-0.0321	-0.0180	-0.0271
146	-0.0195	-0.0177	-0.0369
147	0.0110	-0.0438	-0.0392
148	0.0027	-0.0047	-0.0318
149	0.1722	0.1378	0.1357
150	-0.0738	-0.0614	-0.0435
151	-0.0059	-0.0229	-0.0465
152	-0.0398	-0.0684	-0.0490
153	-0.0124	-0.0430	-0.0534
154	0.0237	0.0381	0.0160
155	0.0773	0.0798	0.0476
156	0.0208	0.0311	0.0529
157	0.0246	0.0150	0.0247
158	0.0151	0.0049	-0.0108
159	-0.0726	-0.0518	-0.0517
160	0.0274	0.0254	0.0525
161	-0.0265	-0.0077	0.0016
162	-0.0183	-0.0153	-0.0157
163	0.0390	0.0489	0.0652
164	0.0089	0.0147	0.0308
165	-0.1002	-0.0829	-0.0632
166	0.0155	0.0505	0.0494
167	0.0425	0.0075	0.0199
168	-0.0972	-0.0772	-0.0624
169	0.1066	0.0777	0.0930
170	0.0015	0.0023	0.0480
171	0.0665	0.0823	0.0379
172	-0.0049	-0.0042	-0.0179
173	-0.0302	-0.0143	-0.0518
174	-0.0527	-0.0370	-0.0453
175	-0.1172	-0.1181	-0.0697
176	-0.0321	-0.0502	-0.0375
177	-0.0181	-0.0458	-0.0364
178	0.0321	0.0251	0.0010
179	-0.0026	0.0289	0.0128
180	0.0978	0.1108	0.1208
181	0.0136	0.0254	0.0442
182	-0.0483	-0.0419	-0.0381
183	-0.0580	-0.0709	-0.0832
184	-0.0554	-0.0585	-0.0449
185	-0.0271	-0.0306	-0.0148
186	0.0600	0.0448	0.0566
187	-0.0603	-0.0237	0.0195
188	-0.0160	-0.0227	-0.0132
189	0.0565	0.0870	0.0551
190	0.0536	0.0476	0.0525
191	-0.0171	-0.0787	-0.0590
192	0.0688	0.0357	-0.0016
193	-0.0656	-0.0792	-0.0465
194	-0.0090	-0.0120	-0.0174
195	-0.0838	-0.0645	-0.0420
196	0.0562	0.0725	0.1050
197	-0.0332	-0.0201	0.0068
198	0.0289	0.0062	0.0131
199	-0.0065	-0.0061	-0.0482
200	-0.0738	-0.0678	-0.0511
201	0.0100	-0.0232	-0.0416
202	-0.0524	-0.0142	-0.0325
203	-0.0130	-0.0260	-0.0192
204	0.0247	0.0154	0.0261
205	0.0144	0.0347	0.0200
206	0.0756	0.0619	0.0247
207	-0.0647	-0.0603	-0.0597
208	-0.0289	-0.0079	-0.0262
209	-0.0161	-0.0265	-0.0482
210	0.1084	0.1056	0.1292
211	-0.0372	-0.0234	-0.0339
212	0.0392	0.0435	0.0568
213	0.1201	0.0798	0.1010
214	-0.0283	-0.0451	-0.0490
215	-0.0398	-0.0337	-0.0371
216	0.2449	0.2817	0.2708
217	0.0025	-0.0320	-0.0495
218	-0.0738	-0.0813	-0.0512
219	-0.0472	-0.0197	-0.0334
220	-0.0779	-0.1046	-0.0487
221	0.0926	0.1233	0.1186
222	-0.0231	-0.0280	-0.0100
223	-0.0253	-0.0241	-0.0354
224	-0.0262	-0.0272	-0.0403
225	0.1172	0.1238	0.1154
226	0.1072	0.0725	0.0562
227	-0.0398	-0.0482	-0.0583
228	0.0967	0.0844	0.1165
229	-0.0271	-0.0401	-0.0275
230	-0.0820	-0.0629	-0.0450
231	0.0606	0.0580	0.0635
232	0.0036	0.0020	-0.0528
233	-0.0486	-0.0564	-0.0001
234	-0.0048	0.0211	-0.0184
235	-0.0375	-0.0417	-0.0363
236	-0.0283	-0.0339	-0.0379
237	-0.0195	-0.0107	0.0158
238	-0.0012	0.0076	0.0362
239	-0.0492	-0.0448	-0.0456
240	0.0058	-0.0036	0.0043
241	0.0738	0.0337	0.0125
242	-0.0568	-0.0388	-0.0211
243	-0.0603	-0.0572	-0.0567
244	-0.0195	-0.0042	0.0313
245	-0.0116	-0.0059	-0.0420
246	-0.0545	-0.0523	-0.0357
247	0.0004	-0.0165	-0.0372
248	-0.0609	-0.0720	-0.0505
249	0.1013	0.0979	0.0723

Source: P3 source-disjoint test split · p3_02004911 · SHA-256 63d4f9c77d41cc0c…

p06Speech + burstsP3 curated burst test

Triumph + 1 known burst(s)

Synthetic speech with inserted bursts · P3 synthetic speech/burst mixture · 16.0 s

Tiny Base · values are model estimates, not ground truth

Strongest emotions relative to training

Anger

z +2.31 / +2.11raw 1.42 / 1.29

Impatience and Irritability

z +2.11 / +1.89raw 1.64 / 1.48

Triumph

z +2.09 / +1.12raw 1.08 / 0.57

Malevolence Malice

z +1.93 / +1.96raw 1.09 / 1.10

Teasing

z +1.71 / +1.91raw 0.93 / 1.04

Hope Enthusiasm Optimism

z +1.61 / +0.91raw 1.34 / 0.81

Disgust

z +1.04 / +1.56raw 0.52 / 0.77

The center of each bar is the S9 teacher median. Positive z is to the right; negative z is to the left. Ranking uses z, not raw teacher units.

Strongest VoiceNet dimensions relative to training

Tension (TENS)

z +2.91 / +2.70raw 4.04 / 3.86

Cartoonish style (S_CART)

z +2.82 / +2.79raw 5.51 / 5.47

Dynamic arc (DARC)

z +2.37 / +1.96raw 4.89 / 4.33

Pitch range (RANG)

z +2.26 / +2.06raw 4.95 / 4.77

Arousal (AROU)

z +2.22 / +1.92raw 4.90 / 4.56

Stance (STNC)

z +2.19 / +2.03raw 5.12 / 4.94

Roughness (ROUG)

z +2.17 / +2.02raw 3.96 / 3.82

All 57 VoiceNet predictions, including raw units, are in the full table below. These seven are ranked by z; the top values may differ from the strongest raw dimensions.

Voice, speed and quality scores in context

Genuineness (0–6)z +0.74 / +0.56raw 3.53 / 3.24

Vocal-burst blend (0–10)z -0.64 / -0.74raw 4.93 / 4.66

Content enjoyment (CE)z +0.58 / +0.33raw 5.39 / 5.14

Production quality (PQ)z +0.68 / +0.75raw 7.64 / 7.70

Speech signal quality, calibratedz +0.28 / +0.36raw 3.63 / 3.67

Background quality, calibratedz +0.34 / +0.74raw 3.70 / 4.08

Overall quality, calibratedz +0.45 / +0.84raw 3.11 / 3.35

P.808 MOS estimatez -0.08 / +0.25raw 3.38 / 3.54

score content enjoymentz +0.86 / +0.84raw 4.77 / 4.76

score overall qualityz +0.39 / +0.50raw 2.85 / 2.91

Background Noisez +0.11 / +0.25raw 0.84 / 0.87

Tempo (TEMP)z +0.87 / +0.56raw 3.15 / 2.78

Arousal (AROU)z +2.22 / +1.92raw 4.90 / 4.56

Valence (VALN)z -0.22 / -0.38raw 2.08 / 1.90

Recording quality (RCQL)z -1.67 / -1.71raw 1.27 / 1.23

Background noise (BKGN)z -0.67 / -0.69raw 2.20 / 2.18

talking speedz -1.21 / -1.33raw 4.50 / 4.03

Characters per second (CPS): 7.26 raw · z -0.47

P3 metadata teacher estimate; not a Whisper output. Reference: 86,334 P3 training teacher values, median 9.03, SD 3.76. Cross-language character counts depend on writing system; compare with care.

Orange speaker embedding reconstruction

Cosine against Orange on this same clip (higher means closer to that teacher vector):

Embedding	Tiny	Base
Timbre · 128D	0.818	0.884
Identity · 250D	0.781	0.755

Vocal-burst regions

Known

Tiny

Base

0 s16.0 s

Purple marks known inserted burst intervals; other vocal sounds may be unlabeled.

Tiny: 2 regions, count-head estimate 0.46; Base: 1 regions, count-head estimate 0.80.

Exact predicted start and end times

Model	Region	Start (s)	End (s)	Duration (s)
Tiny	1	2.00	2.22	0.22
Tiny	2	2.24	3.08	0.84
Base	1	1.94	2.94	1.00

Known inserted intervals: 1.94–2.86 s

All 192 score slots · raw and z values

#	Target	Tiny raw	Tiny z	Base raw	Base z	Train median	Train SD
Emotion scores Forty clip-level Empathic Insight emotion teacher outputs. Each row evaluates one named emotion score.
0	Affectionemo_Affection	0.804	+1.40	0.478	+0.83	0.007	0.570
1	Amusementemo_Amusement	1.040	+1.18	1.142	+1.29	-0.001	0.885
2	Angeremo_Anger	1.417	+2.31	1.294	+2.11	0.004	0.613
3	Astonishment Surpriseemo_Astonishment_Surprise	0.272	+0.47	0.331	+0.57	0.005	0.572
4	Aweemo_Awe	0.018	+0.04	0.005	+0.01	0.000	0.427
5	Bitternessemo_Bitterness	0.622	+1.46	0.568	+1.33	0.013	0.415
6	Concentrationemo_Concentration	1.012	+0.51	1.009	+0.51	0.634	0.741
7	Confusionemo_Confusion	0.441	+0.82	0.194	+0.36	0.001	0.540
8	Contemplationemo_Contemplation	0.117	+0.06	0.069	-0.02	0.082	0.598
9	Contemptemo_Contempt	0.602	+1.30	0.641	+1.38	-0.000	0.464
10	Contentmentemo_Contentment	0.716	+1.39	0.455	+0.89	0.000	0.514
11	Disappointmentemo_Disappointment	0.366	+0.52	0.327	+0.47	0.000	0.700
12	Disgustemo_Disgust	0.515	+1.04	0.770	+1.56	0.007	0.489
13	Distressemo_Distress	0.202	+0.25	0.202	+0.25	0.000	0.821
14	Doubtemo_Doubt	-0.051	-0.12	0.023	+0.04	0.006	0.466
15	Elationemo_Elation	0.996	+1.35	0.622	+0.84	0.012	0.728
16	Embarrassmentemo_Embarrassment	0.212	+0.39	0.425	+0.89	0.043	0.430
17	Emotional Numbnessemo_Emotional_Numbness	-0.045	-0.05	-0.049	-0.06	0.004	0.917
18	Fatigue Exhaustionemo_Fatigue_Exhaustion	0.018	-0.02	0.049	+0.04	0.028	0.539
19	Fearemo_Fear	-0.032	-0.08	-0.020	-0.06	0.015	0.610
20	Helplessnessemo_Helplessness	-0.072	-0.10	-0.031	-0.04	-0.004	0.696
21	Hope Enthusiasm Optimismemo_Hope_Enthusiasm_Optimism	1.339	+1.61	0.812	+0.91	0.117	0.760
22	Impatience and Irritabilityemo_Impatience_and_Irritability	1.637	+2.11	1.482	+1.89	0.149	0.705
23	Infatuationemo_Infatuation	-0.043	-0.05	0.003	+0.03	-0.015	0.533
24	Interestemo_Interest	2.195	+0.67	2.110	+0.57	1.589	0.907
25	Intoxication Altered States of Consciousnessemo_Intoxication_Altered_States_of_Consciousness	0.564	+1.05	0.598	+1.12	-0.025	0.559
26	Jealousy and Envyemo_Jealousy_and_Envy	0.107	+0.11	0.045	-0.03	0.059	0.442
27	Longingemo_Longing	0.058	-0.05	0.050	-0.06	0.087	0.632
28	Malevolence Maliceemo_Malevolence_Malice	1.086	+1.93	1.102	+1.96	0.055	0.534
29	Painemo_Pain	-0.026	-0.04	0.035	+0.06	-0.002	0.579
30	Pleasure Ecstasyemo_Pleasure_Ecstasy	0.736	+1.17	0.512	+0.81	0.017	0.614
31	Prideemo_Pride	0.744	+1.46	0.372	+0.73	0.002	0.509
32	Reliefemo_Relief	0.108	+0.11	0.067	+0.05	0.033	0.681
33	Sadnessemo_Sadness	0.020	+0.03	0.023	+0.03	0.000	0.759
34	Sexual Lustemo_Sexual_Lust	0.079	+0.10	0.090	+0.12	0.030	0.494
35	Shameemo_Shame	0.120	+0.21	0.144	+0.26	0.013	0.510
36	Sournessemo_Sourness	0.364	+0.84	0.339	+0.78	-0.005	0.439
37	Teasingemo_Teasing	0.930	+1.71	1.043	+1.91	0.000	0.545
38	Thankfulness Gratitudeemo_Thankfulness_Gratitude	0.713	+0.96	0.469	+0.61	0.041	0.697
39	Triumphemo_Triumph	1.080	+2.09	0.575	+1.12	-0.007	0.521
VoiceNet dimensions Fifty-seven VoiceNet voice, delivery, style, and recording dimensions. Codes are expanded in the target column.
40	Perceived voice age (AGEV)vn_AGEV_reg	3.122	+0.11	3.380	+0.32	2.984	1.238
41	Arousal (AROU)vn_AROU_reg	4.901	+2.22	4.558	+1.92	2.359	1.147
42	Arousal shift (ARSH)vn_ARSH_reg	3.392	+0.94	3.091	+0.59	2.580	0.867
43	Vocal attack (ATCK)vn_ATCK_reg	4.351	+1.69	4.207	+1.58	2.162	1.295
44	Background noise (BKGN)vn_BKGN_reg	2.197	-0.67	2.179	-0.69	2.703	0.761
45	Brightness (BRGT)vn_BRGT_reg	1.725	-0.33	1.495	-0.61	1.991	0.813
46	Speech chunking (CHNK)vn_CHNK_reg	0.713	-0.92	0.528	-1.06	1.847	1.239
47	Articulation clarity (CLRT)vn_CLRT_reg	2.064	+0.05	2.037	+0.02	2.018	0.945
48	Cognitive load (COGL)vn_COGL_reg	0.786	-1.23	0.753	-1.26	2.094	1.061
49	Dynamic arc (DARC)vn_DARC_reg	4.890	+2.37	4.326	+1.96	1.615	1.380
50	Disfluency (DFLU)vn_DFLU_reg	2.750	+0.22	2.859	+0.31	2.488	1.184
51	Emphasis (EMPH)vn_EMPH_reg	5.271	+1.75	4.854	+1.47	2.607	1.524
52	Esthetics (ESTH)vn_ESTH_reg	0.810	-2.04	0.865	-1.97	2.402	0.782
53	Content appropriateness (EXPL)vn_EXPL_reg	0.385	+0.93	0.345	+0.80	0.086	0.322
54	Focus (FOCS)vn_FOCS_reg	3.941	+1.45	3.342	+0.91	2.344	1.102
55	Fullness (FULL)vn_FULL_reg	1.542	-0.27	1.078	-0.79	1.778	0.889
56	Perceived gender (GEND)vn_GEND_reg	5.088	+0.65	5.213	+0.73	4.055	1.588
57	Harmonicity (HARM)vn_HARM_reg	1.495	-1.18	1.495	-1.18	2.480	0.836
58	Metallic character (METL)vn_METL_reg	3.001	+1.44	2.806	+1.24	1.621	0.958
59	Pitch range (RANG)vn_RANG_reg	4.946	+2.26	4.765	+2.06	2.914	0.897
60	Recording quality (RCQL)vn_RCQL_reg	1.275	-1.67	1.232	-1.71	2.754	0.888
61	Vocal register (REGS)vn_REGS_reg	0.510	-0.54	0.274	-0.73	1.198	1.268
62	Respiration (RESP)vn_RESP_reg	3.185	+0.48	2.966	+0.27	2.680	1.056
63	Roughness (ROUG)vn_ROUG_reg	3.958	+2.17	3.821	+2.02	2.033	0.887
64	Chest resonance (R_CHST)vn_R_CHST_reg	3.262	+1.34	3.016	+1.04	2.135	0.844
65	Head resonance (R_HEAD)vn_R_HEAD_reg	1.749	-0.49	1.535	-0.75	2.148	0.822
66	Mask resonance (R_MASK)vn_R_MASK_reg	2.538	+0.63	2.223	+0.31	1.908	1.005
67	Mixed resonance (R_MIXD)vn_R_MIXD_reg	0.991	-0.53	0.938	-0.59	1.436	0.841
68	Nasal resonance (R_NASL)vn_R_NASL_reg	4.417	+1.55	4.351	+1.49	2.791	1.047
69	Oral resonance (R_ORAL)vn_R_ORAL_reg	2.479	+0.40	2.220	+0.05	2.184	0.741
70	Throat resonance (R_THRT)vn_R_THRT_reg	3.295	+1.53	3.068	+1.24	2.070	0.803
71	Smoothness (SMTH)vn_SMTH_reg	1.627	-0.47	1.442	-0.64	2.143	1.093
72	Stance (STNC)vn_STNC_reg	5.118	+2.19	4.940	+2.03	2.633	1.137
73	Speech structure (STRU)vn_STRU_reg	1.488	-0.68	1.359	-0.81	2.137	0.958
74	ASMR style (S_ASMR)vn_S_ASMR_reg	-0.309	-1.19	-0.190	-1.11	1.370	1.411
75	Authoritative style (S_AUTH)vn_S_AUTH_reg	2.599	+1.45	2.681	+1.53	1.088	1.043
76	Cartoonish style (S_CART)vn_S_CART_reg	5.509	+2.82	5.466	+2.79	1.560	1.401
77	Casual style (S_CASU)vn_S_CASU_reg	5.953	+1.69	5.475	+1.32	3.793	1.278
78	Conversational style (S_CONV)vn_S_CONV_reg	1.904	-0.52	1.860	-0.56	2.594	1.318
79	Dramatic style (S_DRAM)vn_S_DRAM_reg	5.174	+2.14	4.951	+1.94	2.721	1.148
80	Formal style (S_FORM)vn_S_FORM_reg	-0.314	-1.48	-0.228	-1.39	1.195	1.021
81	Monologue style (S_MONO)vn_S_MONO_reg	1.344	-1.15	1.528	-1.01	2.824	1.284
82	Narrator style (S_NARR)vn_S_NARR_reg	0.270	-0.72	0.783	-0.36	1.307	1.446
83	Newsreader style (S_NEWS)vn_S_NEWS_reg	0.106	-0.53	0.169	-0.42	0.408	0.568
84	Playful style (S_PLAY)vn_S_PLAY_reg	3.305	+0.72	3.690	+1.02	2.352	1.315
85	Ranting or angry style (S_RANT)vn_S_RANT_reg	3.597	+1.85	3.837	+2.04	1.213	1.289
86	Storytelling style (S_STRY)vn_S_STRY_reg	5.129	+1.94	5.282	+2.05	2.480	1.366
87	Teacher or didactic style (S_TECH)vn_S_TECH_reg	0.153	-0.40	0.729	+0.07	0.646	1.227
88	Whispered talking style (S_WHIS)vn_S_WHIS_reg	1.117	-0.30	1.086	-0.32	1.597	1.618
89	Tempo (TEMP)vn_TEMP_reg	3.147	+0.87	2.781	+0.56	2.117	1.190
90	Tension (TENS)vn_TENS_reg	4.039	+2.91	3.857	+2.70	1.559	0.852
91	Valence (VALN)vn_VALN_reg	2.081	-0.22	1.905	-0.38	2.328	1.118
92	Valence shift (VALS)vn_VALS_reg	1.837	-0.63	1.717	-0.74	2.518	1.079
93	Velocity flux (VFLX)vn_VFLX_reg	1.264	-0.82	0.802	-1.20	2.256	1.208
94	Volatility (VOLT)vn_VOLT_reg	4.394	+2.04	4.238	+1.86	2.586	0.886
95	Vulnerability (VULN)vn_VULN_reg	0.217	-2.47	0.326	-2.36	2.648	0.984
96	Warmth (WARM)vn_WARM_reg	2.068	-0.56	2.004	-0.63	2.578	0.909
Genuineness, blend, and legacy quality Genuineness and vocal-burst blend are predicted. R_quality has Ladder training labels but no valid P3 test labels.
97	Genuineness (0–6)genuineness_0_6	3.531	+0.74	3.236	+0.56	2.332	1.621
98	Vocal-burst blend (0–10)blend_0_10	4.935	-0.64	4.659	-0.74	6.676	2.738
99	Legacy R_quality (no P3 test labels)R_quality	1.084	-0.03	1.010	-0.25	1.095	0.338
Empathic Insight Plus extra scores Nineteen additional clip-level teacher scores, including background noise and content enjoyment.
100	Ageeiv_extra:Age	3.155	-0.33	3.198	-0.18	3.250	0.293
101	Arousaleiv_extra:Arousal	2.526	+2.84	2.363	+2.47	1.289	0.435
102	Authenticityeiv_extra:Authenticity	2.821	+1.00	2.759	+0.60	2.667	0.153
103	Background Noiseeiv_extra:Background_Noise	0.838	+0.11	0.874	+0.25	0.808	0.264
104	Confident vs. Hesitanteiv_extra:Confident_vs._Hesitant	1.061	+0.07	0.984	-0.18	1.040	0.303
105	Gendereiv_extra:Gender	-1.301	-0.68	-1.130	-0.51	-0.621	0.999
106	High-Pitched vs. Low-Pitchedeiv_extra:High-Pitched_vs._Low-Pitched	2.265	+1.75	2.120	+1.17	1.827	0.250
107	Monotone vs. Expressiveeiv_extra:Monotone_vs._Expressive	2.690	+1.77	2.748	+1.89	1.859	0.470
108	Recording Qualityeiv_extra:Recording_Quality	2.070	-0.22	2.052	-0.28	2.144	0.332
109	Serious vs. Humorouseiv_extra:Serious_vs._Humorous	1.360	+1.27	1.440	+1.50	0.929	0.340
110	Soft vs. Harsheiv_extra:Soft_vs._Harsh	-0.128	-1.28	-0.146	-1.33	0.281	0.320
111	Submissive vs. Dominanteiv_extra:Submissive_vs._Dominant	1.207	+2.57	1.252	+2.71	0.376	0.324
112	Valenceeiv_extra:Valence	0.396	+1.03	0.106	+0.27	0.005	0.380
113	Vulnerable vs. Emotionally Detachedeiv_extra:Vulnerable_vs._Emotionally_Detached	1.299	-0.95	1.258	-1.04	1.715	0.437
114	Warm vs. Coldeiv_extra:Warm_vs._Cold	-0.119	-0.57	-0.178	-0.76	0.051	0.300
115	score background qualityeiv_extra:score_background_quality	3.472	+0.25	3.594	+0.42	3.301	0.693
116	score content enjoymenteiv_extra:score_content_enjoyment	4.769	+0.86	4.763	+0.84	4.507	0.303
117	score overall qualityeiv_extra:score_overall_quality	2.850	+0.39	2.905	+0.50	2.652	0.507
118	score speech qualityeiv_extra:score_speech_quality	1.812	+0.03	1.847	+0.27	1.808	0.146
Meta AudioBox Aesthetics Four AudioBox aesthetic teacher outputs. Expansions follow the official Meta model card.
119	Content enjoyment (CE)audiobox:CE	5.387	+0.58	5.135	+0.33	4.799	1.018
120	Content usefulness (CU)audiobox:CU	6.253	+0.60	6.210	+0.56	5.649	1.001
121	Production complexity (PC)audiobox:PC	2.028	-0.19	1.934	-0.25	2.331	1.617
122	Production quality (PQ)audiobox:PQ	7.641	+0.68	7.699	+0.75	7.044	0.879
Microsoft DNSMOS Seven DNSMOS teacher outputs: raw and calibrated SIG/BAK/OVRL estimates plus P.808 MOS.
123	Speech signal quality, rawdnsmos:SIG_raw	4.121	+0.33	4.210	+0.46	3.900	0.669
124	Background quality, rawdnsmos:BAK_raw	3.590	+0.34	4.250	+0.92	3.211	1.124
125	Overall quality, rawdnsmos:OVRL_raw	3.465	+0.47	3.859	+0.95	3.085	0.812
126	Speech signal quality, calibrateddnsmos:SIG	3.628	+0.28	3.669	+0.36	3.488	0.501
127	Background quality, calibrateddnsmos:BAK	3.702	+0.34	4.075	+0.74	3.389	0.928
128	Overall quality, calibrateddnsmos:OVRL	3.115	+0.45	3.349	+0.84	2.840	0.606
129	P.808 MOS estimatednsmos:P808_MOS	3.379	-0.08	3.545	+0.25	3.421	0.496
Vocal-burst count The regression target is log(1 + count). A separate table also reports count error after inverse transformation.
130	Vocal-burst count, log(1 + count)burst_count_log1p	0.380	+0.59	0.590	+0.91	0.000	0.647
VoiceCLAP attributes Sixty-one individual VoiceCLAP attribute teacher scores. The raw 768D VoiceCLAP embedding is stored in sidecars but is not a model output.
131	Affectionvoiceclap_attribute:Affection	0.758	-0.34	0.841	-0.19	0.947	0.554
132	Agevoiceclap_attribute:Age	2.625	-1.11	3.025	-0.37	3.229	0.547
133	Amusementvoiceclap_attribute:Amusement	1.303	+1.59	1.321	+1.62	0.392	0.572
134	Angervoiceclap_attribute:Anger	1.929	+1.85	1.810	+1.62	0.992	0.506
135	Arousalvoiceclap_attribute:Arousal	2.894	+2.37	2.695	+2.05	1.420	0.622
136	Astonishment Surprisevoiceclap_attribute:Astonishment_Surprise	1.313	+1.68	1.049	+1.13	0.509	0.479
137	Authenticityvoiceclap_attribute:Authenticity	2.797	+0.16	2.807	+0.22	2.770	0.167
138	Awevoiceclap_attribute:Awe	0.546	+0.03	0.423	-0.45	0.539	0.259
139	Background Noisevoiceclap_attribute:Background_Noise	0.905	+1.28	0.841	+1.04	0.567	0.264
140	Bitternessvoiceclap_attribute:Bitterness	1.075	+2.05	1.065	+2.01	0.592	0.236
141	Concentrationvoiceclap_attribute:Concentration	0.601	-1.16	0.634	-1.09	1.214	0.531
142	Confident vs. Hesitantvoiceclap_attribute:Confident_vs._Hesitant	1.336	+0.57	1.206	+0.29	1.069	0.468
143	Confusionvoiceclap_attribute:Confusion	0.816	+0.52	0.844	+0.60	0.643	0.334
144	Contemplationvoiceclap_attribute:Contemplation	0.303	-1.18	0.338	-1.09	0.780	0.406
145	Contemptvoiceclap_attribute:Contempt	1.250	+1.60	1.298	+1.74	0.709	0.339
146	Contentmentvoiceclap_attribute:Contentment	0.468	-0.39	0.571	-0.05	0.588	0.307
147	Disappointmentvoiceclap_attribute:Disappointment	1.251	+1.69	1.048	+0.99	0.760	0.291
148	Disgustvoiceclap_attribute:Disgust	0.908	+1.37	0.829	+0.99	0.625	0.207
149	Distressvoiceclap_attribute:Distress	1.244	+0.91	1.013	+0.25	0.927	0.350
150	Doubtvoiceclap_attribute:Doubt	0.408	-0.67	0.425	-0.58	0.535	0.188
151	Elationvoiceclap_attribute:Elation	1.255	+1.80	1.218	+1.71	0.539	0.397
152	Embarrassmentvoiceclap_attribute:Embarrassment	0.447	+0.45	0.576	+0.86	0.307	0.314
153	Emotional Numbnessvoiceclap_attribute:Emotional_Numbness	0.129	-2.01	0.092	-2.15	0.664	0.266
154	Fatigue Exhaustionvoiceclap_attribute:Fatigue_Exhaustion	0.162	-1.15	0.249	-0.82	0.462	0.261
155	Fearvoiceclap_attribute:Fear	0.777	+0.75	0.575	-0.20	0.618	0.212
156	Gendervoiceclap_attribute:Gender	-1.462	-1.30	-1.140	-0.98	-0.151	1.005
157	Helplessnessvoiceclap_attribute:Helplessness	0.568	-0.33	0.476	-0.68	0.658	0.268
158	High-Pitched vs. Low-Pitchedvoiceclap_attribute:High-Pitched_vs._Low-Pitched	2.321	+1.28	2.251	+1.10	1.840	0.375
159	Hope Enthusiasm Optimismvoiceclap_attribute:Hope_Enthusiasm_Optimism	1.398	+1.75	1.280	+1.45	0.705	0.396
160	Impatience and Irritabilityvoiceclap_attribute:Impatience_and_Irritability	2.382	+2.46	1.971	+1.70	1.052	0.541
161	Infatuationvoiceclap_attribute:Infatuation	0.362	-0.74	0.498	-0.33	0.608	0.332
162	Interestvoiceclap_attribute:Interest	1.909	+0.71	1.859	+0.59	1.598	0.440
163	Intoxication Altered States of Consciousnessvoiceclap_attribute:Intoxication_Altered_States_of_Consciousness	1.112	+1.32	1.068	+1.22	0.502	0.463
164	Jealousy & Envyvoiceclap_attribute:Jealousy_&_Envy	0.666	+0.59	0.728	+0.84	0.523	0.245
165	Longingvoiceclap_attribute:Longing	0.287	-1.14	0.269	-1.22	0.538	0.220
166	Malevolence Malicevoiceclap_attribute:Malevolence_Malice	1.517	+1.98	1.365	+1.54	0.833	0.346
167	Monotone vs. Expressivevoiceclap_attribute:Monotone_vs._Expressive	2.898	+1.89	2.921	+1.93	1.775	0.594
168	Painvoiceclap_attribute:Pain	0.480	+0.45	0.404	+0.10	0.381	0.218
169	Pleasure Ecstasyvoiceclap_attribute:Pleasure_Ecstasy	0.772	+0.89	0.912	+1.36	0.503	0.301
170	Pridevoiceclap_attribute:Pride	1.226	+1.28	1.324	+1.56	0.780	0.349
171	Recording Qualityvoiceclap_attribute:Recording_Quality	1.772	-1.65	1.956	-1.09	2.313	0.328
172	Reliefvoiceclap_attribute:Relief	0.647	-0.91	0.559	-1.12	1.025	0.415
173	Sadnessvoiceclap_attribute:Sadness	0.604	-0.47	0.567	-0.59	0.752	0.313
174	Serious vs. Humorousvoiceclap_attribute:Serious_vs._Humorous	1.378	+1.01	1.267	+0.82	0.803	0.568
175	Sexual Lustvoiceclap_attribute:Sexual_Lust	0.561	-0.18	0.599	-0.09	0.635	0.419
176	Shamevoiceclap_attribute:Shame	0.675	+0.52	0.709	+0.65	0.526	0.283
177	Soft vs. Harshvoiceclap_attribute:Soft_vs._Harsh	-0.361	-1.44	-0.299	-1.27	0.160	0.360
178	Sournessvoiceclap_attribute:Sourness	0.931	+0.78	1.084	+1.30	0.706	0.291
179	Submissive vs. Dominantvoiceclap_attribute:Submissive_vs._Dominant	1.220	+1.67	1.220	+1.67	0.623	0.359
180	Teasingvoiceclap_attribute:Teasing	1.337	+2.10	1.456	+2.42	0.540	0.379
181	Thankfulness Gratitudevoiceclap_attribute:Thankfulness_Gratitude	1.408	+0.05	1.640	+0.48	1.384	0.529
182	Triumphvoiceclap_attribute:Triumph	1.611	+2.49	1.544	+2.31	0.716	0.359
183	Valencevoiceclap_attribute:Valence	-0.874	-1.37	-0.618	-0.96	-0.007	0.635
184	Vulnerable vs. Emotionally Detachedvoiceclap_attribute:Vulnerable_vs._Emotionally_Detached	1.066	-1.03	1.040	-1.08	1.638	0.556
185	Warm vs. Coldvoiceclap_attribute:Warm_vs._Cold	-0.491	-1.06	-0.466	-1.00	-0.066	0.400
186	durationvoiceclap_attribute:duration	15.792	+0.77	16.509	+0.88	10.914	6.354
187	score background qualityvoiceclap_attribute:score_background_quality	3.351	+0.21	3.505	+0.52	3.245	0.498
188	score content enjoymentvoiceclap_attribute:score_content_enjoyment	4.757	+0.69	4.818	+1.10	4.656	0.147
189	score overall qualityvoiceclap_attribute:score_overall_quality	2.634	-0.00	2.797	+0.39	2.635	0.412
190	score speech qualityvoiceclap_attribute:score_speech_quality	1.897	+0.09	1.879	-0.18	1.891	0.069
191	talking speedvoiceclap_attribute:talking_speed	4.498	-1.21	4.029	-1.33	9.028	3.756

All Orange embedding components

The cosine above is the meaningful vector-level comparison; component values have no standalone semantic label.

Timbre — all 128 vector components

Dimension	Tiny	Base	Orange teacher
0	0.2557	0.2986	0.2585
1	-0.1336	-0.1128	-0.0905
2	-0.0985	-0.1056	-0.0894
3	-0.0779	-0.0414	-0.0346
4	0.0180	0.0265	0.0437
5	0.0529	0.0356	0.0288
6	-0.0894	-0.0935	-0.0826
7	0.0976	0.0321	0.0013
8	0.1404	0.0975	0.1326
9	0.0716	0.0813	0.0684
10	0.0097	-0.0286	-0.0226
11	-0.1000	-0.0853	-0.1066
12	0.0127	-0.0152	-0.0916
13	-0.0971	-0.0701	-0.0899
14	-0.1082	-0.0924	-0.0948
15	0.0687	0.0670	0.0427
16	-0.0957	-0.0772	-0.0736
17	0.0875	0.0564	0.0787
18	-0.0550	-0.0488	-0.0699
19	-0.0808	-0.0894	-0.0862
20	0.1269	0.1082	0.1198
21	0.0363	0.0163	-0.0838
22	-0.0808	-0.0914	-0.0857
23	-0.0471	-0.0513	-0.0225
24	-0.0332	-0.0386	0.0034
25	-0.0764	-0.0874	-0.0800
26	-0.0329	-0.0635	-0.0511
27	0.0124	-0.0681	-0.0850
28	0.0001	-0.0747	-0.0481
29	0.0126	-0.0154	-0.0268
30	0.2192	0.2367	0.2222
31	0.0332	0.1143	0.0854
32	0.1413	0.1295	0.1365
33	-0.1519	-0.1371	-0.1004
34	0.0085	-0.0033	0.0369
35	0.2279	0.1818	0.0806
36	-0.1115	-0.0838	-0.0979
37	-0.0952	-0.1021	-0.1078
38	-0.1130	-0.0940	-0.0909
39	-0.0942	-0.1036	-0.0779
40	0.0865	0.0762	0.0081
41	-0.1317	-0.1163	-0.0804
42	0.0522	0.0142	0.0273
43	-0.0401	-0.0752	-0.0938
44	0.1731	0.1432	0.0906
45	-0.0351	-0.0612	-0.0309
46	-0.0577	-0.0503	-0.0189
47	0.0430	0.0447	0.0268
48	-0.0042	0.0227	0.0154
49	0.0716	0.1072	0.1124
50	0.0909	0.0777	0.0361
51	-0.0961	-0.0777	-0.0196
52	-0.0358	-0.0025	0.0623
53	-0.1034	-0.0919	-0.0929
54	-0.0913	-0.0762	-0.0956
55	-0.0488	-0.0460	-0.0876
56	0.0947	0.0853	0.0200
57	-0.1163	-0.1138	-0.0999
58	0.0764	0.0670	0.0584
59	-0.0003	0.0223	-0.0314
60	0.0697	0.0858	-0.0271
61	0.0332	0.0356	-0.0047
62	0.1211	0.1310	0.2065
63	0.0735	0.1046	0.0673
64	0.0127	0.0853	0.0597
65	-0.0584	-0.0833	-0.0743
66	0.0278	0.0637	0.0576
67	0.0251	0.0556	0.0584
68	-0.0572	-0.0087	0.0716
69	-0.0538	-0.0691	-0.0834
70	0.1509	0.1199	0.0865
71	-0.0178	-0.0411	0.0085
72	-0.1058	-0.0995	-0.0882
73	0.0255	0.0019	-0.0397
74	-0.1053	-0.0924	-0.0995
75	0.0358	0.0404	-0.0028
76	-0.0788	-0.1183	-0.0884
77	0.1120	0.1041	0.2041
78	0.0481	0.0150	0.1223
79	-0.0889	-0.0726	-0.0790
80	0.0344	0.0711	0.1489
81	-0.1259	-0.1199	-0.0825
82	-0.1096	-0.1214	-0.0872
83	-0.0440	-0.0340	-0.0057
84	-0.1067	-0.0975	-0.1129
85	-0.0445	-0.0612	-0.0967
86	0.0697	0.0787	0.1083
87	-0.0716	-0.0843	-0.0887
88	0.1433	0.1473	0.1398
89	0.0817	0.0731	-0.0035
90	-0.0498	-0.0424	0.0314
91	-0.0808	-0.1041	-0.0837
92	-0.1101	-0.0904	-0.0884
93	0.1836	0.1585	0.0689
94	0.0603	0.0604	0.1053
95	-0.0435	0.0333	0.0653
96	-0.1053	-0.0592	-0.0476
97	-0.0418	0.0024	0.0569
98	-0.0256	-0.0899	-0.0920
99	-0.0437	-0.0197	0.0889
100	0.1139	0.1102	0.1506
101	-0.0711	-0.0787	-0.0881
102	-0.0144	0.0010	-0.0912
103	-0.0836	-0.0955	-0.0961
104	-0.0735	-0.0660	-0.0287
105	-0.0531	-0.0899	-0.0878
106	-0.1110	-0.1300	-0.1095
107	-0.0976	-0.0742	-0.0523
108	0.0827	0.0899	0.1284
109	0.0144	0.0163	0.0417
110	0.0572	0.0249	0.0375
111	-0.1178	-0.1143	-0.1057
112	-0.1110	-0.1351	-0.0898
113	-0.0942	-0.1321	-0.1282
114	-0.0423	-0.1021	-0.0981
115	-0.0351	-0.0929	-0.0467
116	-0.0880	-0.0772	-0.0781
117	0.1615	0.1117	0.1853
118	-0.0202	0.0246	0.0431
119	-0.0860	-0.1041	-0.0881
120	0.0052	-0.0138	-0.0333
121	-0.0406	-0.0526	-0.0090
122	-0.0073	-0.0173	-0.0891
123	0.0018	0.0551	0.1220
124	0.0433	0.0500	-0.0450
125	0.0344	0.0061	-0.0443
126	-0.0510	-0.0675	-0.0442
127	0.0918	0.0853	0.1060

Identity — all 250 vector components

Dimension	Tiny	Base	Orange teacher
0	-0.0255	-0.0259	-0.0323
1	0.1178	0.1224	0.1202
2	0.1277	0.1076	0.0630
3	-0.0913	-0.1004	-0.0887
4	-0.0565	-0.0331	-0.0425
5	0.0508	0.0738	0.0619
6	-0.1088	-0.1008	-0.0686
7	-0.0293	-0.0513	0.0622
8	-0.0338	-0.0087	-0.0865
9	0.0150	-0.0124	0.0109
10	0.0145	0.0033	0.0497
11	0.0098	-0.0065	0.0077
12	-0.0813	-0.0765	-0.0512
13	-0.0894	-0.0693	-0.0413
14	-0.0676	-0.0304	-0.0667
15	-0.0847	-0.0725	-0.0551
16	0.0603	0.0295	-0.0086
17	-0.0634	-0.0630	-0.0562
18	-0.0175	-0.0018	-0.0476
19	0.0785	0.1049	0.0657
20	0.0231	-0.0012	-0.0468
21	-0.0572	-0.0504	-0.0434
22	-0.0752	-0.0558	-0.0485
23	-0.0248	-0.0446	0.0246
24	0.0162	0.0018	-0.0399
25	-0.0283	0.0022	-0.0296
26	0.1428	0.0963	0.1737
27	-0.0286	-0.0504	-0.0380
28	-0.0575	-0.0707	-0.0506
29	-0.0381	-0.0554	0.0085
30	0.0085	0.0293	-0.0378
31	-0.0228	-0.0554	-0.0587
32	0.0586	0.0538	-0.0481
33	0.0119	0.0030	-0.0176
34	-0.0220	-0.0085	0.0270
35	-0.0918	-0.0869	-0.0602
36	-0.0690	-0.0689	-0.0494
37	-0.0287	-0.0331	-0.0323
38	-0.0329	-0.0369	-0.0020
39	-0.0657	-0.0320	-0.0674
40	-0.0447	-0.0644	-0.0542
41	-0.0212	-0.0059	-0.0108
42	-0.0653	-0.0675	-0.0465
43	0.0362	0.0567	0.0714
44	0.0002	0.0005	0.0922
45	-0.0556	-0.0547	-0.0324
46	-0.0456	-0.0506	0.0089
47	0.1457	0.1332	0.0851
48	-0.0681	-0.0513	-0.0499
49	0.0634	0.0720	0.0524
50	0.0131	0.0105	0.0130
51	-0.0115	0.0008	0.0150
52	-0.0103	-0.0419	-0.0376
53	0.0523	0.0236	0.0417
54	-0.0724	-0.0729	-0.0790
55	0.1608	0.0995	0.0548
56	-0.0525	-0.0232	-0.0643
57	-0.0023	0.0230	-0.0088
58	-0.0395	-0.0324	-0.0331
59	-0.0286	-0.0360	-0.0651
60	-0.0352	-0.0371	-0.0490
61	0.0253	-0.0004	0.0886
62	-0.0643	-0.0556	-0.0411
63	0.0480	0.0729	-0.0508
64	-0.0601	-0.0511	-0.0521
65	-0.0157	0.0165	-0.0571
66	-0.0534	-0.0569	-0.0392
67	-0.0497	-0.0236	-0.0492
68	0.0419	0.0639	0.0746
69	-0.0111	-0.0224	-0.0051
70	-0.0941	-0.0950	-0.0678
71	-0.0104	-0.0155	-0.0490
72	0.0054	0.0040	-0.0030
73	-0.0936	-0.1103	-0.0834
74	-0.0257	-0.0246	0.0850
75	-0.0195	-0.0356	-0.0062
76	0.0193	-0.0322	-0.0445
77	-0.0302	-0.0264	0.0179
78	0.0520	0.0563	0.0020
79	-0.0362	-0.0358	-0.0500
80	0.0993	0.1395	0.1410
81	0.0539	0.0317	0.0536
82	-0.0442	-0.0358	-0.0449
83	0.0411	0.0477	-0.0415
84	0.0974	0.0909	0.1281
85	-0.0463	-0.0693	-0.0500
86	-0.0345	-0.0331	-0.0446
87	-0.0170	-0.0308	-0.0399
88	-0.0615	-0.0475	-0.0493
89	-0.0138	-0.0443	-0.0452
90	0.0355	0.0036	0.0559
91	0.0156	0.0078	-0.0587
92	-0.0329	-0.0441	-0.0432
93	0.0813	0.0819	0.1633
94	-0.0381	-0.0520	-0.0759
95	-0.0523	-0.0698	-0.0521
96	-0.0471	-0.0594	-0.0446
97	-0.0589	-0.0511	-0.0113
98	-0.0333	-0.0797	-0.0528
99	-0.0305	-0.0344	-0.0625
100	-0.0421	-0.0626	-0.0441
101	-0.0785	-0.1053	-0.0472
102	0.0253	0.0216	-0.0536
103	-0.0390	-0.0533	0.0120
104	-0.0809	-0.0608	-0.0651
105	-0.0385	-0.0198	-0.0649
106	-0.0572	-0.0468	-0.0385
107	0.0066	0.0162	0.0010
108	-0.0006	-0.0358	-0.0371
109	0.0073	0.0134	0.0867
110	-0.0297	-0.0199	-0.0189
111	0.0093	0.0117	0.0892
112	-0.0307	-0.0338	-0.0403
113	-0.0264	-0.0572	0.0033
114	-0.0158	-0.0378	0.1013
115	-0.0202	-0.0075	-0.0354
116	0.0103	0.0005	-0.0070
117	0.0695	0.0353	0.0065
118	0.1381	0.1521	0.1414
119	0.0259	0.0108	-0.0384
120	0.0506	0.0138	0.0514
121	-0.0261	-0.0169	-0.0537
122	0.0002	-0.0117	-0.0472
123	0.0207	-0.0146	0.0110
124	-0.0851	-0.0932	-0.0498
125	0.1844	0.2143	0.1018
126	0.1551	0.1323	0.1260
127	-0.0188	-0.0271	-0.0436
128	-0.0048	-0.0200	-0.0468
129	-0.0044	-0.0133	0.0250
130	-0.0288	-0.0248	-0.0502
131	0.1069	0.0707	0.1542
132	0.0121	0.0057	0.0833
133	0.1267	0.0963	0.0980
134	0.0589	0.0828	0.0369
135	0.0672	0.0648	0.0979
136	-0.0142	-0.0335	-0.0293
137	0.0894	0.0797	-0.0228
138	0.0695	0.0909	-0.0112
139	-0.0056	-0.0380	-0.0511
140	-0.0851	-0.0538	-0.0589
141	-0.0064	0.0109	-0.0462
142	-0.0497	-0.0493	-0.0432
143	0.0932	0.1251	0.0237
144	-0.0629	-0.0653	-0.0520
145	0.0180	0.0271	-0.0249
146	0.1353	0.0995	0.1443
147	-0.0175	-0.0475	0.0236
148	0.0078	-0.0608	-0.0551
149	-0.0955	-0.1148	-0.0643
150	-0.0539	-0.0549	-0.0491
151	-0.0610	-0.0425	-0.0569
152	-0.0520	-0.0824	-0.0554
153	-0.0620	-0.0657	-0.0130
154	-0.0262	-0.0450	-0.0487
155	-0.0733	-0.0770	-0.0651
156	-0.0144	-0.0071	-0.0424
157	-0.0215	-0.0585	-0.0889
158	-0.0402	-0.0342	-0.0384
159	-0.0007	0.0084	-0.0584
160	-0.0293	-0.0127	-0.0474
161	-0.0648	-0.0190	-0.0182
162	-0.0000	-0.0080	-0.0565
163	-0.1083	-0.0824	-0.0556
164	-0.1007	-0.0801	-0.0439
165	0.1031	0.0941	0.1190
166	-0.0456	-0.0594	-0.0581
167	0.0856	0.1242	0.0850
168	-0.0847	-0.0999	-0.0596
169	-0.0648	-0.1076	-0.0569
170	-0.0196	-0.0385	-0.0467
171	0.0799	0.0873	0.1047
172	0.0359	0.0203	-0.0035
173	0.0051	-0.0019	-0.0359
174	-0.0761	-0.0603	-0.0513
175	-0.0048	0.0077	-0.0007
176	-0.0409	-0.0165	-0.0424
177	-0.0333	-0.0560	-0.0411
178	0.0352	0.0522	-0.0254
179	0.0525	0.0213	0.1007
180	0.0936	0.0716	0.0513
181	-0.0435	-0.0432	-0.0651
182	-0.0499	-0.0416	-0.0431
183	-0.0584	-0.0837	-0.0231
184	0.1409	0.1548	0.1246
185	0.1239	0.1197	0.1154
186	-0.0743	-0.0761	-0.0357
187	0.0728	0.0594	0.0126
188	0.0466	0.0450	0.0648
189	-0.0837	-0.0556	-0.0792
190	0.1258	0.1539	0.0436
191	0.1192	0.0797	0.1852
192	-0.0223	-0.0249	-0.0604
193	0.0183	-0.0122	-0.0526
194	0.0085	0.0143	-0.0516
195	0.0832	0.0806	0.1299
196	-0.0714	-0.0468	-0.0485
197	0.1178	0.0801	0.0771
198	-0.0388	-0.0567	-0.0482
199	-0.0302	-0.0215	-0.0548
200	-0.0681	-0.0450	-0.0577
201	0.0121	0.0037	-0.0211
202	-0.0880	-0.0981	-0.0701
203	-0.0433	-0.0398	-0.0623
204	0.0409	-0.0024	0.0326
205	-0.0228	-0.0513	-0.0195
206	0.0033	-0.0369	-0.0515
207	-0.0008	0.0335	0.0865
208	0.0319	0.0295	0.0064
209	0.1135	0.0878	0.1329
210	0.1230	0.0959	-0.0074
211	0.0074	0.0120	-0.0384
212	0.1504	0.1710	0.1071
213	-0.0343	-0.0457	0.0219
214	-0.0079	-0.0295	-0.0528
215	0.0119	0.0250	0.0020
216	-0.0577	-0.0437	-0.0598
217	-0.1022	-0.0891	-0.0667
218	0.0303	0.0280	0.0620
219	-0.0194	0.0172	-0.0034
220	-0.0244	-0.0398	0.0604
221	-0.0264	-0.0405	-0.0433
222	0.0705	0.1044	0.0014
223	0.0249	0.0078	-0.0280
224	-0.0601	-0.0621	-0.0456
225	-0.0055	-0.0385	-0.0415
226	-0.0591	-0.0869	-0.0304
227	-0.0570	-0.0241	-0.0659
228	-0.0174	-0.0288	0.0052
229	0.0032	-0.0179	-0.0453
230	0.1012	0.1013	0.1578
231	0.0804	0.0788	0.0911
232	-0.0842	-0.0446	-0.0500
233	0.0402	-0.0095	0.0032
234	0.0589	0.0023	0.0048
235	0.1532	0.1413	0.1693
236	-0.0499	-0.0473	-0.0428
237	-0.0393	-0.0576	-0.0509
238	-0.0459	-0.0299	-0.0547
239	0.1187	0.1485	0.1361
240	0.0471	0.0392	0.0884
241	0.0199	0.0191	-0.0007
242	-0.0378	-0.0183	-0.0735
243	-0.0847	-0.0720	-0.0641
244	0.0489	0.0504	-0.0392
245	-0.0326	-0.0468	-0.0475
246	0.1107	0.1215	0.0524
247	-0.0615	-0.0457	-0.0420
248	-0.0314	-0.0504	-0.0017
249	0.0393	0.0716	0.0724

Source: P3 source-disjoint test split · p3_02009875 · SHA-256 0bae3ca8a72fbb3d…

Reproducibility. The model repository provides the per-target normalization JSON, inference and training code, and the independent test evaluation. P3 test clips are source-disjoint but cherry-picked using teacher scores. Their examples must not be used to estimate average accuracy. Audio provenance is stated under each card.