locator model_v2.pt · vocal-burst-detector-v2 ·
Empathic-Insight-Voice-Plus · in-domain baseline + reliability weighting ·
24 bursts written into the scripts from 25 located spans ·
← caption grid · ← 14-clip page
What this page shows. Every clip is scored, transcribed, located,
classified and captioned in one pass by burst_captions.py at its defaults. The
GENERAL line describes the voice; the SCRIPT gives one delivery cue per sentence,
with (vocal bursts) written in where the locator found them and
[pause X.Xs] at every silence ≥ 0.30 s.
The 25 clips are drawn from the 100 multilingual clips already in this repo, so the page
adds no new audio: the players point at ../audio/.
Why the captions changed. Each card lists its top dimensions with
three numbers: the z-score, the dimension's measured predictor reliability r
(held-out reg_pearson), and the effective ranking score |z|·r that
decides which dimensions make the caption.
Expand same scores under the previous captioner on any card to see what the identical
scores produced against the old emolia baseline with no reliability weighting. Across these
25 clips R_MIXD ("mixed resonance", the weakest head in the VoiceNet
release at r = 0.392) took a top-5 slot on 20 of 25 clips under
the old configuration and 0 of 25 now.
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
R_ORAL | Oral Resonance | +2.45 | 0.85 | 2.07 |
R_CHST | Chest Resonance | +2.13 | 0.87 | 1.85 |
FULL | Fullness | +1.83 | 0.73 | 1.33 |
S_CART | Cartoonish Style | -1.83 | 0.68 | 1.24 |
R_THRT | Throat Resonance | +1.53 | 0.72 | 1.11 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
FULL | Fullness | +1.41 | 1.00 | 1.41 |
R_ORAL | Oral Resonance | +1.39 | 1.00 | 1.39 |
DFLU | Disfluency | +1.10 | 1.00 | 1.10 |
S_CART | Cartoonish Style | -1.09 | 1.00 | 1.08 |
S_STRY | Storytelling Style | -0.97 | 1.00 | 0.97 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
S_WHIS | Whisper-Talk Style | +5.30 | 0.81 | 4.30 |
WARM | Warmth | +4.98 | 0.72 | 3.58 |
R_CHST | Chest Resonance | +4.02 | 0.87 | 3.49 |
DFLU | Disfluency | -3.71 | 0.81 | 3.01 |
ROUG | Roughness | +3.32 | 0.76 | 2.51 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
R_MIXD | Mixed Resonance | -9.89 | 1.00 | 9.89 |
WARM | Warmth | +3.17 | 1.00 | 3.17 |
ROUG | Roughness | +2.33 | 1.00 | 2.33 |
R_NASL | Nasal Resonance | -2.14 | 1.00 | 2.15 |
R_CHST | Chest Resonance | +2.00 | 1.00 | 2.00 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
S_WHIS | Whisper-Talk Style | +4.60 | 0.81 | 3.73 |
S_CASU | Casual Style | -3.45 | 0.92 | 3.16 |
S_CONV | Conversational Style | -3.72 | 0.79 | 2.95 |
ATCK | Attack | -2.15 | 0.93 | 2.00 |
VOLT | Volatility | -1.94 | 0.95 | 1.84 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
R_MIXD | Mixed Resonance | -4.62 | 1.00 | 4.62 |
VFLX | Velocity Flux | -2.45 | 1.00 | 2.45 |
FULL | Fullness | +1.70 | 1.00 | 1.70 |
ATCK | Attack | -1.65 | 1.00 | 1.65 |
S_CONV | Conversational Style | -1.56 | 1.00 | 1.56 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
VULN | Vulnerability | +4.52 | 0.81 | 3.67 |
VALN | Valence | -3.67 | 0.79 | 2.88 |
RESP | Respiration | +2.88 | 0.88 | 2.53 |
R_CHST | Chest Resonance | -2.66 | 0.87 | 2.31 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
R_MIXD | Mixed Resonance | -6.51 | 1.00 | 6.51 |
VULN | Vulnerability | +4.17 | 1.00 | 4.17 |
RESP | Respiration | +2.93 | 1.00 | 2.93 |
VALN | Valence | -2.29 | 1.00 | 2.29 |
STNC | Stance | -2.05 | 1.00 | 2.05 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
S_CONV | Conversational Style | -4.22 | 0.79 | 3.34 |
RANG | Pitch Range | +2.81 | 0.87 | 2.45 |
DFLU | Disfluency | -2.81 | 0.81 | 2.28 |
S_STRY | Storytelling Style | +2.63 | 0.84 | 2.22 |
ROUG | Roughness | +2.85 | 0.76 | 2.15 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
RANG | Pitch Range | +2.14 | 1.00 | 2.14 |
VALN | Valence | +2.09 | 1.00 | 2.09 |
TENS | Tension | +2.05 | 1.00 | 2.05 |
ROUG | Roughness | +1.98 | 1.00 | 1.98 |
METL | Metallic Character | +1.95 | 1.00 | 1.95 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
ROUG | Roughness | +7.34 | 0.76 | 5.55 |
ATCK | Attack | +3.33 | 0.93 | 3.10 |
STRU | Structure | -3.40 | 0.90 | 3.05 |
R_THRT | Throat Resonance | +3.99 | 0.72 | 2.89 |
S_DRAM | Dramatic Style | +3.06 | 0.87 | 2.67 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
R_MIXD | Mixed Resonance | -5.68 | 1.00 | 5.68 |
ROUG | Roughness | +5.27 | 1.00 | 5.27 |
EXPL | Content Appropriateness (3-point Scale) | +3.08 | 1.00 | 3.08 |
DARC | Dynamic Arc | +2.39 | 1.00 | 2.39 |
TENS | Tension | +2.34 | 1.00 | 2.35 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
S_WHIS | Whisper-Talk Style | +5.08 | 0.81 | 4.12 |
S_NARR | Narrator Style | +3.48 | 0.86 | 2.99 |
WARM | Warmth | +3.65 | 0.72 | 2.62 |
ROUG | Roughness | +3.04 | 0.76 | 2.30 |
S_ASMR | ASMR Style | +3.38 | 0.68 | 2.29 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
R_MIXD | Mixed Resonance | -9.83 | 1.00 | 9.83 |
VFLX | Velocity Flux | -2.72 | 1.00 | 2.72 |
WARM | Warmth | +2.32 | 1.00 | 2.32 |
ROUG | Roughness | +2.13 | 1.00 | 2.13 |
VULN | Vulnerability | +2.00 | 1.00 | 2.00 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
ROUG | Roughness | +4.67 | 0.76 | 3.53 |
DARC | Dynamic Arc | +3.68 | 0.83 | 3.07 |
RANG | Pitch Range | +3.47 | 0.87 | 3.02 |
ATCK | Attack | +3.05 | 0.93 | 2.84 |
S_DRAM | Dramatic Style | +3.18 | 0.87 | 2.78 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
R_MIXD | Mixed Resonance | -10.60 | 1.00 | 10.60 |
DARC | Dynamic Arc | +3.65 | 1.00 | 3.65 |
ROUG | Roughness | +3.32 | 1.00 | 3.32 |
STNC | Stance | +2.68 | 1.00 | 2.68 |
METL | Metallic Character | +2.66 | 1.00 | 2.66 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
ATCK | Attack | +3.68 | 0.93 | 3.42 |
R_HEAD | Head Resonance | +3.43 | 0.88 | 3.02 |
RANG | Pitch Range | +3.34 | 0.87 | 2.90 |
R_ORAL | Oral Resonance | +3.29 | 0.85 | 2.78 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
R_MIXD | Mixed Resonance | -9.43 | 1.00 | 9.43 |
DARC | Dynamic Arc | +2.69 | 1.00 | 2.69 |
TENS | Tension | +2.60 | 1.00 | 2.60 |
R_HEAD | Head Resonance | +2.58 | 1.00 | 2.58 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
S_MONO | Monologue Style | -4.89 | 0.73 | 3.59 |
S_DRAM | Dramatic Style | +2.46 | 0.87 | 2.15 |
VALS | Valence Shift | +2.66 | 0.80 | 2.12 |
DARC | Dynamic Arc | +2.50 | 0.83 | 2.08 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
R_MIXD | Mixed Resonance | -7.78 | 1.00 | 7.78 |
S_MONO | Monologue Style | -2.68 | 1.00 | 2.69 |
EXPL | Content Appropriateness (3-point Scale) | +2.55 | 1.00 | 2.55 |
VALS | Valence Shift | +2.48 | 1.00 | 2.48 |
DARC | Dynamic Arc | +2.47 | 1.00 | 2.48 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
STRU | Structure | -3.46 | 0.90 | 3.11 |
EMPH | Emphasis | -2.58 | 0.88 | 2.26 |
R_MASK | Mask Resonance | -2.35 | 0.83 | 1.95 |
ESTH | Esthetics | -2.20 | 0.80 | 1.76 |
CLRT | Articulation Clarity | -1.88 | 0.89 | 1.66 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
EXPL | Content Appropriateness (3-point Scale) | +1.89 | 1.00 | 1.89 |
CHNK | Chunking | -1.89 | 1.00 | 1.89 |
CLRT | Articulation Clarity | -1.87 | 1.00 | 1.87 |
RESP | Respiration | +1.83 | 1.00 | 1.83 |
R_MASK | Mask Resonance | -1.64 | 1.00 | 1.64 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
STRU | Structure | +4.34 | 0.90 | 3.90 |
DFLU | Disfluency | -4.44 | 0.81 | 3.60 |
S_FORM | Formal Style | +3.62 | 0.89 | 3.20 |
R_CHST | Chest Resonance | +3.18 | 0.87 | 2.76 |
S_CASU | Casual Style | -2.90 | 0.92 | 2.66 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
RCQL | Recording Quality | +1.95 | 1.00 | 1.95 |
S_NEWS | Newsreader Style | +1.95 | 1.00 | 1.95 |
DFLU | Disfluency | -1.83 | 1.00 | 1.83 |
STRU | Structure | +1.69 | 1.00 | 1.69 |
CLRT | Articulation Clarity | +1.69 | 1.00 | 1.69 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
S_WHIS | Whisper-Talk Style | +3.98 | 0.81 | 3.22 |
ATCK | Attack | -3.31 | 0.93 | 3.08 |
R_HEAD | Head Resonance | -3.17 | 0.88 | 2.79 |
EMPH | Emphasis | -3.06 | 0.88 | 2.68 |
WARM | Warmth | +3.56 | 0.72 | 2.56 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
R_MIXD | Mixed Resonance | -11.64 | 1.00 | 11.64 |
CLRT | Articulation Clarity | -2.40 | 1.00 | 2.40 |
ATCK | Attack | -2.39 | 1.00 | 2.39 |
WARM | Warmth | +2.26 | 1.00 | 2.26 |
BRGT | Brightness | -2.18 | 1.00 | 2.18 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
VULN | Vulnerability | +3.92 | 0.81 | 3.19 |
HARM | Harmonicity | -3.65 | 0.79 | 2.89 |
S_WHIS | Whisper-Talk Style | +3.47 | 0.81 | 2.81 |
VALN | Valence | -3.48 | 0.79 | 2.73 |
RESP | Respiration | +2.65 | 0.88 | 2.33 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
R_MIXD | Mixed Resonance | -7.75 | 1.00 | 7.75 |
VULN | Vulnerability | +3.65 | 1.00 | 3.65 |
RESP | Respiration | +2.74 | 1.00 | 2.74 |
HARM | Harmonicity | -2.29 | 1.00 | 2.29 |
STNC | Stance | -2.27 | 1.00 | 2.27 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
S_WHIS | Whisper-Talk Style | +1.68 | 0.81 | 1.36 |
S_FORM | Formal Style | +1.44 | 0.89 | 1.27 |
R_ORAL | Oral Resonance | +1.47 | 0.85 | 1.25 |
S_AUTH | Authoritative Style | +1.48 | 0.83 | 1.23 |
DFLU | Disfluency | -1.47 | 0.81 | 1.20 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
CLRT | Articulation Clarity | -0.98 | 1.00 | 0.98 |
ARSH | Arousal Shift | -0.96 | 1.00 | 0.96 |
CHNK | Chunking | +0.96 | 1.00 | 0.96 |
ATCK | Attack | -0.94 | 1.00 | 0.94 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
STRU | Structure | -2.87 | 0.90 | 2.58 |
CLRT | Articulation Clarity | -1.97 | 0.89 | 1.75 |
ATCK | Attack | -1.62 | 0.93 | 1.50 |
VALS | Valence Shift | +1.87 | 0.80 | 1.49 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
R_MIXD | Mixed Resonance | -10.42 | 1.00 | 10.42 |
CLRT | Articulation Clarity | -1.95 | 1.00 | 1.95 |
VALS | Valence Shift | +1.85 | 1.00 | 1.85 |
VULN | Vulnerability | +1.76 | 1.00 | 1.76 |
CHNK | Chunking | -1.62 | 1.00 | 1.62 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
ATCK | Attack | +4.30 | 0.93 | 4.00 |
ROUG | Roughness | +4.96 | 0.76 | 3.76 |
R_ORAL | Oral Resonance | +4.13 | 0.85 | 3.50 |
S_MONO | Monologue Style | -4.33 | 0.73 | 3.18 |
DARC | Dynamic Arc | +3.68 | 0.83 | 3.07 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
R_MIXD | Mixed Resonance | -8.89 | 1.00 | 8.89 |
VFLX | Velocity Flux | +3.73 | 1.00 | 3.73 |
DARC | Dynamic Arc | +3.65 | 1.00 | 3.65 |
ROUG | Roughness | +3.53 | 1.00 | 3.53 |
TENS | Tension | +3.10 | 1.00 | 3.10 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
ROUG | Roughness | +8.25 | 0.76 | 6.24 |
ATCK | Attack | +5.53 | 0.93 | 5.15 |
TENS | Tension | +5.53 | 0.77 | 4.24 |
VOLT | Volatility | +3.98 | 0.95 | 3.78 |
METL | Metallic Character | +5.58 | 0.66 | 3.66 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
R_MIXD | Mixed Resonance | -11.12 | 1.00 | 11.12 |
ROUG | Roughness | +5.93 | 1.00 | 5.93 |
TENS | Tension | +4.40 | 1.00 | 4.40 |
METL | Metallic Character | +4.03 | 1.00 | 4.03 |
DARC | Dynamic Arc | +3.65 | 1.00 | 3.65 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
ROUG | Roughness | +4.94 | 0.76 | 3.74 |
TENS | Tension | +4.39 | 0.77 | 3.37 |
ATCK | Attack | +3.61 | 0.93 | 3.36 |
SMTH | Smoothness | -3.67 | 0.89 | 3.28 |
S_MONO | Monologue Style | -4.02 | 0.73 | 2.95 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
R_MIXD | Mixed Resonance | -7.38 | 1.00 | 7.38 |
ROUG | Roughness | +3.52 | 1.00 | 3.52 |
TENS | Tension | +3.47 | 1.00 | 3.48 |
SMTH | Smoothness | -3.29 | 1.00 | 3.29 |
RESP | Respiration | +3.07 | 1.00 | 3.07 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
S_WHIS | Whisper-Talk Style | +4.61 | 0.81 | 3.73 |
ROUG | Roughness | +4.04 | 0.76 | 3.06 |
VULN | Vulnerability | +3.46 | 0.81 | 2.81 |
R_HEAD | Head Resonance | -2.85 | 0.88 | 2.52 |
HARM | Harmonicity | -3.17 | 0.79 | 2.51 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
R_MIXD | Mixed Resonance | -8.77 | 1.00 | 8.77 |
VULN | Vulnerability | +3.24 | 1.00 | 3.24 |
ROUG | Roughness | +2.86 | 1.00 | 2.86 |
BRGT | Brightness | -2.45 | 1.00 | 2.45 |
CLRT | Articulation Clarity | -2.17 | 1.00 | 2.17 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
ATCK | Attack | +3.64 | 0.93 | 3.39 |
EMPH | Emphasis | +3.79 | 0.88 | 3.32 |
STNC | Stance | +3.74 | 0.88 | 3.27 |
S_DRAM | Dramatic Style | +3.36 | 0.87 | 2.93 |
TENS | Tension | +3.75 | 0.77 | 2.88 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
R_MIXD | Mixed Resonance | -7.45 | 1.00 | 7.45 |
STNC | Stance | +3.18 | 1.00 | 3.18 |
TENS | Tension | +2.96 | 1.00 | 2.96 |
EMPH | Emphasis | +2.61 | 1.00 | 2.61 |
DARC | Dynamic Arc | +2.43 | 1.00 | 2.43 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
S_FORM | Formal Style | +4.24 | 0.89 | 3.76 |
DFLU | Disfluency | -4.57 | 0.81 | 3.71 |
STRU | Structure | +4.05 | 0.90 | 3.64 |
S_CASU | Casual Style | -3.44 | 0.92 | 3.15 |
WARM | Warmth | +4.25 | 0.72 | 3.05 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
R_MIXD | Mixed Resonance | -4.08 | 1.00 | 4.08 |
WARM | Warmth | +2.70 | 1.00 | 2.70 |
SMTH | Smoothness | +2.55 | 1.00 | 2.55 |
FULL | Fullness | +2.51 | 1.00 | 2.51 |
S_NEWS | Newsreader Style | +2.32 | 1.00 | 2.32 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
DFLU | Disfluency | -2.85 | 0.81 | 2.32 |
FULL | Fullness | -3.14 | 0.73 | 2.29 |
R_CHST | Chest Resonance | +2.41 | 0.87 | 2.10 |
ROUG | Roughness | -2.61 | 0.76 | 1.98 |
WARM | Warmth | +2.66 | 0.72 | 1.91 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
R_MIXD | Mixed Resonance | -5.90 | 1.00 | 5.90 |
ROUG | Roughness | -2.01 | 1.00 | 2.01 |
RESP | Respiration | +2.00 | 1.00 | 2.00 |
WARM | Warmth | +1.68 | 1.00 | 1.68 |
TENS | Tension | -1.64 | 1.00 | 1.64 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
ROUG | Roughness | +5.58 | 0.76 | 4.22 |
STRU | Structure | -3.32 | 0.90 | 2.98 |
BRGT | Brightness | -3.83 | 0.77 | 2.95 |
ESTH | Esthetics | -3.58 | 0.80 | 2.87 |
S_WHIS | Whisper-Talk Style | +3.38 | 0.81 | 2.74 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
R_MIXD | Mixed Resonance | -10.28 | 1.00 | 10.28 |
ROUG | Roughness | +3.98 | 1.00 | 3.98 |
BRGT | Brightness | -2.96 | 1.00 | 2.96 |
CLRT | Articulation Clarity | -2.79 | 1.00 | 2.79 |
R_ORAL | Oral Resonance | -2.55 | 1.00 | 2.55 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
ROUG | Roughness | +5.60 | 0.76 | 4.24 |
S_CONV | Conversational Style | -4.22 | 0.79 | 3.34 |
S_DRAM | Dramatic Style | +3.70 | 0.87 | 3.23 |
RANG | Pitch Range | +3.23 | 0.87 | 2.81 |
R_THRT | Throat Resonance | +3.80 | 0.72 | 2.75 |
| dim | name | z | r | |z|·r |
|---|---|---|---|---|
R_MIXD | Mixed Resonance | -8.56 | 1.00 | 8.56 |
ROUG | Roughness | +4.00 | 1.00 | 4.00 |
DARC | Dynamic Arc | +3.01 | 1.00 | 3.01 |
METL | Metallic Character | +2.67 | 1.00 | 2.67 |
RANG | Pitch Range | +2.39 | 1.00 | 2.39 |
Generated by build_demo25.py ·
pipeline in burst_captions.py · captioner in caption.py.
Every dimension, emotion, timestamp and burst on this page is a model prediction; nothing is
hand-written.