Interactive listening evidence · Base & Medium

Vocal burst 50: Frustrated Groan, Pain Moan, Scream

Gemini event spans versus independently predicted Base and Medium spans. Hear the clip and inspect both models’ event labels, 20 ms curves and 192 scores.

← All 50 examples ← Previous

50. Frustrated Groan, Pain Moan, Scream

emolia_c1544VWARM__extremely_low__en.c026.k3

vc_sidon · en/synth · 3.82 s · test split

3 Gemini eventsBase count 2.0Medium count 1.6

Source key: emolia_c1544__V__WARM__extremely_low__en.c026.k3 · Audio SHA256: d1d0848251d9d260bfcceed1e3d15d4ff41371345ed6d43cc9133b65246b65e8

Gemini annotation · selection aid

0.82–1.48 s: Scream · group scream
2.22–2.92 s: Pain Moan · group moan
2.95–3.75 s: Frustrated Groan · group sigh_neg

Base predictions

20 ms frame probability; dashed line = 0.5 threshold

0.00–0.52 s: Effort Grunt 11%, Other / rare burst 6%, Frustrated Groan 6% · onset 0.84
0.38–1.38 s: Effort Grunt 19%, Frustrated Groan 17%, Surprised Gasp 15% · onset 0.72
0.44–1.32 s: Frustrated Groan 17%, Effort Grunt 17%, Surprised Gasp 17% · onset 0.73
0.52–1.18 s: Frustrated Groan 19%, Surprised Gasp 18%, Effort Grunt 12% · onset 0.79
0.58–1.34 s: Surprised Gasp 23%, Frustrated Groan 17%, Scream 14% · onset 0.88
0.66–1.34 s: Surprised Gasp 27%, Scream 15%, Frustrated Groan 15% · onset 0.82
0.72–1.42 s: Surprised Gasp 25%, Effort Grunt 21%, Scream 13% · onset 0.75
0.80–1.48 s: Effort Grunt 27%, Surprised Gasp 22%, Scream 12% · onset 0.82
0.86–1.54 s: Effort Grunt 30%, Surprised Gasp 21%, Scream 12% · onset 0.80
1.24–2.02 s: Effort Grunt 39%, Frustrated Groan 11%, Scream 10% · onset 0.72
1.36–2.36 s: Scream 38%, Frustrated Groan 15%, Effort Grunt 12% · onset 0.50
1.46–2.26 s: Scream 38%, Other / rare burst 12%, Effort Grunt 12% · onset 0.82
1.60–2.48 s: Scream 49%, Frustrated Groan 13%, Other / rare burst 10% · onset 0.74
1.74–2.84 s: Scream 53%, Frustrated Groan 15%, Surprised Gasp 7% · onset 0.95
1.82–3.34 s: Scream 43%, Frustrated Groan 22%, Other / rare burst 7% · onset 0.75
1.98–3.66 s: Frustrated Groan 33%, Scream 20%, Growl 9% · onset 0.79
2.06–3.68 s: Frustrated Groan 36%, Scream 15%, Growl 9% · onset 0.71
2.14–3.56 s: Frustrated Groan 36%, Scream 17%, Growl 9% · onset 0.70
2.20–3.68 s: Frustrated Groan 38%, Scream 11%, Growl 9% · onset 0.71
2.36–3.78 s: Frustrated Groan 35%, Exhausted Groan 15%, Growl 9% · onset 0.67
2.48–3.70 s: Frustrated Groan 30%, Exhausted Groan 19%, Growl 10% · onset 0.63
2.54–3.76 s: Frustrated Groan 27%, Exhausted Groan 23%, Growl 10% · onset 0.50
2.72–3.76 s: Exhausted Groan 31%, Frustrated Groan 19%, Growl 11% · onset 0.62
2.86–3.82 s: Exhausted Groan 34%, Frustrated Groan 14%, Effort Grunt 12% · onset 0.55
2.98–3.76 s: Exhausted Groan 44%, Frustrated Groan 12%, Growl 9% · onset 0.86
3.22–3.82 s: Exhausted Groan 41%, Exasperated Sigh 8%, Effort Grunt 8% · onset 0.79
3.68–3.82 s: Sharp Inhale 13%, Exasperated Sigh 12%, Displeased Grunt 7% · onset 0.54
3.74–3.82 s: Sharp Inhale 17%, Tsk 6%, Hiccup 5% · onset 0.68

Frame-positive regions: 1 · CPS 2.84 · Orange timbre cosine 0.657 · identity cosine 0.503

Medium predictions

20 ms frame probability; dashed line = 0.5 threshold

0.04–0.72 s: Effort Grunt 16%, Sharp Inhale 14%, Exhausted Groan 10% · onset 0.85
0.46–1.40 s: Frustrated Groan 23%, Effort Grunt 23%, Displeased Grunt 8% · onset 0.80
0.56–1.16 s: Frustrated Groan 17%, Effort Grunt 16%, Scream 15% · onset 0.82
0.64–1.42 s: Effort Grunt 23%, Frustrated Groan 22%, Scream 10% · onset 0.79
0.70–1.50 s: Effort Grunt 24%, Frustrated Groan 23%, Surprised Gasp 9% · onset 0.84
0.80–1.70 s: Frustrated Groan 24%, Effort Grunt 23%, Displeased Grunt 8% · onset 0.78
0.86–1.78 s: Effort Grunt 25%, Frustrated Groan 23%, Other / rare burst 8% · onset 0.69
1.12–1.78 s: Effort Grunt 30%, Frustrated Groan 16%, Displeased Grunt 14% · onset 0.58
1.24–1.92 s: Effort Grunt 40%, Frustrated Groan 17%, Displeased Grunt 10% · onset 0.62
1.36–2.02 s: Effort Grunt 41%, Frustrated Groan 15%, Other / rare burst 13% · onset 0.52
1.48–2.28 s: Scream 34%, Effort Grunt 18%, Frustrated Groan 15% · onset 0.90
1.60–2.40 s: Scream 50%, Frustrated Groan 14%, Effort Grunt 8% · onset 0.84
1.72–2.50 s: Scream 58%, Frustrated Groan 11%, Growl 7% · onset 0.93
1.84–3.36 s: Scream 55%, Frustrated Groan 17%, Growl 10% · onset 0.69
2.00–3.68 s: Frustrated Groan 33%, Scream 26%, Growl 15% · onset 0.62
2.74–3.82 s: Frustrated Groan 33%, Exhausted Groan 20%, Growl 13% · onset 0.65
2.90–3.72 s: Frustrated Groan 32%, Exhausted Groan 21%, Growl 13% · onset 0.54
2.96–3.82 s: Frustrated Groan 27%, Exhausted Groan 26%, Growl 13% · onset 0.72

Frame-positive regions: 1 · CPS 2.24 · Orange timbre cosine 0.741 · identity cosine 0.607

All 192 scalar scores: Base and Medium raw plus reference z

Target	Base raw	Base z	Medium raw	Medium z
`emo_Affection`	0.02	0.03	0.04	0.05
`emo_Amusement`	0.25	0.29	0.19	0.22
`emo_Anger`	1.16	1.88	1.06	1.72
`emo_Astonishment_Surprise`	1.02	1.77	0.75	1.30
`emo_Awe`	0.09	0.20	0.06	0.14
`emo_Bitterness`	0.24	0.55	0.24	0.54
`emo_Concentration`	0.44	-0.27	0.37	-0.35
`emo_Confusion`	0.34	0.63	0.70	1.30
`emo_Contemplation`	0.04	-0.07	0.07	-0.02
`emo_Contempt`	0.13	0.29	0.14	0.30
`emo_Contentment`	0.02	0.04	0.04	0.07
`emo_Disappointment`	0.42	0.60	0.49	0.71
`emo_Disgust`	0.21	0.42	0.17	0.34
`emo_Distress`	2.35	2.86	2.16	2.63
`emo_Doubt`	0.16	0.33	0.20	0.42
`emo_Elation`	0.19	0.25	0.18	0.23
`emo_Embarrassment`	0.05	0.03	0.04	-0.01
`emo_Emotional_Numbness`	0.09	0.09	0.01	0.01
`emo_Fatigue_Exhaustion`	1.98	3.63	2.09	3.83
`emo_Fear`	0.41	0.65	0.30	0.46
`emo_Helplessness`	1.61	2.33	1.73	2.48
`emo_Hope_Enthusiasm_Optimism`	0.09	-0.04	0.12	-0.00
`emo_Impatience_and_Irritability`	1.58	2.03	1.81	2.36
`emo_Infatuation`	0.07	0.16	0.04	0.11
`emo_Interest`	0.61	-1.08	0.62	-1.07
`emo_Intoxication_Altered_States_of_Consciousness`	0.11	0.25	0.19	0.39
`emo_Jealousy_and_Envy`	-0.00	-0.13	0.01	-0.12
`emo_Longing`	0.06	-0.04	0.10	0.02
`emo_Malevolence_Malice`	-0.02	-0.14	0.07	0.02
`emo_Pain`	1.89	3.27	2.17	3.75
`emo_Pleasure_Ecstasy`	0.13	0.18	0.11	0.15
`emo_Pride`	0.09	0.17	0.12	0.24
`emo_Relief`	0.12	0.12	0.17	0.21
`emo_Sadness`	0.29	0.38	-0.15	-0.20
`emo_Sexual_Lust`	0.00	-0.06	0.03	0.01
`emo_Shame`	0.05	0.08	0.03	0.04
`emo_Sourness`	0.49	1.12	0.35	0.80
`emo_Teasing`	0.22	0.40	0.17	0.31
`emo_Thankfulness_Gratitude`	0.03	-0.02	-0.01	-0.07
`emo_Triumph`	0.14	0.27	0.11	0.22
`vn_AGEV_reg`	3.32	0.27	3.25	0.22
`vn_AROU_reg`	5.02	2.32	5.25	2.52
`vn_ARSH_reg`	3.39	0.93	3.06	0.55
`vn_ATCK_reg`	5.30	2.42	5.32	2.44
`vn_BKGN_reg`	3.83	1.49	3.71	1.32
`vn_BRGT_reg`	3.46	1.81	3.57	1.94
`vn_CHNK_reg`	1.17	-0.55	1.25	-0.48
`vn_CLRT_reg`	2.29	0.28	2.34	0.35
`vn_COGL_reg`	1.34	-0.71	1.74	-0.33
`vn_DARC_reg`	4.27	1.93	3.71	1.52
`vn_DFLU_reg`	0.62	-1.58	1.18	-1.10
`vn_EMPH_reg`	5.30	1.76	5.49	1.89
`vn_ESTH_reg`	1.98	-0.54	1.70	-0.90
`vn_EXPL_reg`	-0.02	-0.32	0.03	-0.17
`vn_FOCS_reg`	3.77	1.29	3.75	1.28
`vn_FULL_reg`	3.73	2.19	3.57	2.02
`vn_GEND_reg`	5.25	0.75	5.25	0.75
`vn_HARM_reg`	2.87	0.47	2.45	-0.04
`vn_METL_reg`	3.18	1.63	3.18	1.63
`vn_RANG_reg`	4.25	1.49	4.31	1.56
`vn_RCQL_reg`	3.39	0.72	3.34	0.66
`vn_REGS_reg`	1.77	0.45	1.66	0.36
`vn_RESP_reg`	4.28	1.52	3.84	1.10
`vn_ROUG_reg`	4.80	3.12	4.92	3.26
`vn_R_CHST_reg`	3.38	1.48	3.41	1.51
`vn_R_HEAD_reg`	1.99	-0.19	1.80	-0.43
`vn_R_MASK_reg`	2.69	0.78	2.52	0.61
`vn_R_MIXD_reg`	2.95	1.80	2.98	1.83
`vn_R_NASL_reg`	1.71	-1.03	1.46	-1.28
`vn_R_ORAL_reg`	3.50	1.77	3.18	1.35
`vn_R_THRT_reg`	4.93	3.56	4.83	3.44
`vn_SMTH_reg`	1.99	-0.14	2.03	-0.10
`vn_STNC_reg`	4.30	1.47	4.42	1.58
`vn_STRU_reg`	1.54	-0.62	1.37	-0.80
`vn_S_ASMR_reg`	-0.36	-1.23	-0.19	-1.11
`vn_S_AUTH_reg`	1.95	0.83	1.96	0.83
`vn_S_CART_reg`	3.37	1.29	3.57	1.44
`vn_S_CASU_reg`	2.65	-0.89	2.70	-0.85
`vn_S_CONV_reg`	1.36	-0.94	1.28	-0.99
`vn_S_DRAM_reg`	4.76	1.78	4.82	1.83
`vn_S_FORM_reg`	-0.15	-1.32	-0.21	-1.38
`vn_S_MONO_reg`	2.72	-0.08	2.69	-0.10
`vn_S_NARR_reg`	-0.36	-1.16	-0.39	-1.17
`vn_S_NEWS_reg`	-0.20	-1.07	-0.03	-0.77
`vn_S_PLAY_reg`	2.26	-0.07	2.00	-0.27
`vn_S_RANT_reg`	2.22	0.78	2.63	1.10
`vn_S_STRY_reg`	0.33	-1.58	0.33	-1.58
`vn_S_TECH_reg`	0.27	-0.31	0.27	-0.31
`vn_S_WHIS_reg`	-0.43	-1.25	-0.36	-1.21
`vn_TEMP_reg`	2.81	0.58	3.02	0.75
`vn_TENS_reg`	4.88	3.91	5.46	4.58
`vn_VALN_reg`	2.36	0.03	1.85	-0.43
`vn_VALS_reg`	2.69	0.16	2.67	0.14
`vn_VFLX_reg`	3.07	0.67	2.98	0.60
`vn_VOLT_reg`	3.64	1.19	3.85	1.43
`vn_VULN_reg`	2.64	-0.01	2.75	0.11
`vn_WARM_reg`	2.25	-0.36	2.25	-0.36
`genuineness_0_6`	3.65	0.82	3.32	0.61
`blend_0_10`	7.22	0.20	6.72	0.02
`R_quality`	0.39	-2.10	0.29	-2.37
`eiv_extra:Age`	3.17	-0.28	3.20	-0.18
`eiv_extra:Arousal`	2.55	2.90	2.66	3.16
`eiv_extra:Authenticity`	2.86	1.27	2.77	0.69
`eiv_extra:Background_Noise`	0.67	-0.51	0.93	0.48
`eiv_extra:Confident_vs._Hesitant`	1.27	0.76	1.87	2.73
`eiv_extra:Gender`	-0.76	-0.14	-1.28	-0.66
`eiv_extra:High-Pitched_vs._Low-Pitched`	1.47	-1.44	1.62	-0.83
`eiv_extra:Monotone_vs._Expressive`	2.24	0.81	2.57	1.51
`eiv_extra:Recording_Quality`	1.58	-1.69	1.35	-2.41
`eiv_extra:Serious_vs._Humorous`	1.39	1.34	1.47	1.59
`eiv_extra:Soft_vs._Harsh`	-0.05	-1.02	0.06	-0.70
`eiv_extra:Submissive_vs._Dominant`	0.74	1.14	0.62	0.76
`eiv_extra:Valence`	-0.83	-2.19	-1.43	-3.78
`eiv_extra:Vulnerable_vs._Emotionally_Detached`	0.75	-2.21	0.93	-1.79
`eiv_extra:Warm_vs._Cold`	-0.43	-1.60	-0.47	-1.75
`eiv_extra:score_background_quality`	3.50	0.28	3.33	0.04
`eiv_extra:score_content_enjoyment`	4.18	-1.09	4.01	-1.63
`eiv_extra:score_overall_quality`	2.64	-0.02	2.36	-0.57
`eiv_extra:score_speech_quality`	1.94	0.92	1.91	0.73
`audiobox:CE`	4.87	0.07	4.83	0.03
`audiobox:CU`	6.26	0.61	6.53	0.88
`audiobox:PC`	1.52	-0.50	1.52	-0.50
`audiobox:PQ`	7.40	0.41	7.63	0.66
`dnsmos:SIG_raw`	3.95	0.07	3.94	0.05
`dnsmos:BAK_raw`	4.34	1.01	4.21	0.89
`dnsmos:OVRL_raw`	3.69	0.75	3.66	0.71
`dnsmos:SIG`	3.50	0.03	3.48	-0.01
`dnsmos:BAK`	4.15	0.82	4.05	0.72
`dnsmos:OVRL`	3.24	0.65	3.21	0.61
`dnsmos:P808_MOS`	3.14	-0.57	3.13	-0.58
`burst_count_log1p`	1.11	1.71	0.97	1.50
`voiceclap_attribute:Affection`	-0.08	-1.86	-0.29	-2.24
`voiceclap_attribute:Age`	2.51	-1.32	2.69	-0.99
`voiceclap_attribute:Amusement`	0.95	0.97	0.85	0.79
`voiceclap_attribute:Anger`	0.79	-0.39	0.69	-0.59
`voiceclap_attribute:Arousal`	2.71	2.07	2.94	2.45
`voiceclap_attribute:Astonishment_Surprise`	1.48	2.02	1.51	2.09
`voiceclap_attribute:Authenticity`	2.96	1.15	2.84	0.44
`voiceclap_attribute:Awe`	0.36	-0.70	0.26	-1.07
`voiceclap_attribute:Background_Noise`	0.57	0.03	0.70	0.49
`voiceclap_attribute:Bitterness`	0.21	-1.62	0.26	-1.43
`voiceclap_attribute:Concentration`	0.34	-1.65	0.41	-1.52
`voiceclap_attribute:Confident_vs._Hesitant`	1.53	0.99	1.60	1.14
`voiceclap_attribute:Confusion`	0.25	-1.18	0.29	-1.05
`voiceclap_attribute:Contemplation`	-0.09	-2.14	0.10	-1.67
`voiceclap_attribute:Contempt`	0.28	-1.28	0.22	-1.43
`voiceclap_attribute:Contentment`	-0.14	-2.39	0.13	-1.49
`voiceclap_attribute:Disappointment`	0.47	-1.01	0.53	-0.80
`voiceclap_attribute:Disgust`	0.29	-1.63	0.19	-2.11
`voiceclap_attribute:Distress`	1.55	1.78	1.57	1.83
`voiceclap_attribute:Doubt`	0.07	-2.45	0.21	-1.71
`voiceclap_attribute:Elation`	0.45	-0.23	0.32	-0.55
`voiceclap_attribute:Embarrassment`	-0.00	-0.98	-0.04	-1.11
`voiceclap_attribute:Emotional_Numbness`	-0.18	-3.18	-0.18	-3.18
`voiceclap_attribute:Fatigue_Exhaustion`	1.28	3.15	1.50	3.96
`voiceclap_attribute:Fear`	0.32	-1.41	0.27	-1.62
`voiceclap_attribute:Gender`	-0.49	-0.33	-0.94	-0.79
`voiceclap_attribute:Helplessness`	1.25	2.21	1.14	1.79
`voiceclap_attribute:High-Pitched_vs._Low-Pitched`	1.47	-0.98	1.55	-0.76
`voiceclap_attribute:Hope_Enthusiasm_Optimism`	0.19	-1.30	0.22	-1.24
`voiceclap_attribute:Impatience_and_Irritability`	0.99	-0.12	0.97	-0.16
`voiceclap_attribute:Infatuation`	-0.09	-2.12	-0.24	-2.55
`voiceclap_attribute:Interest`	0.45	-2.62	0.42	-2.67
`voiceclap_attribute:Intoxication_Altered_States_of_Consciousness`	0.25	-0.55	0.25	-0.55
`voiceclap_attribute:Jealousy_&_Envy`	-0.11	-2.58	-0.10	-2.53
`voiceclap_attribute:Longing`	-0.15	-3.15	-0.21	-3.42
`voiceclap_attribute:Malevolence_Malice`	0.04	-2.31	0.07	-2.20
`voiceclap_attribute:Monotone_vs._Expressive`	2.44	1.12	2.53	1.28
`voiceclap_attribute:Pain`	0.86	2.17	0.78	1.84
`voiceclap_attribute:Pleasure_Ecstasy`	0.14	-1.20	0.20	-1.02
`voiceclap_attribute:Pride`	0.25	-1.51	0.35	-1.24
`voiceclap_attribute:Recording_Quality`	1.73	-1.77	1.52	-2.44
`voiceclap_attribute:Relief`	0.19	-2.02	0.42	-1.47
`voiceclap_attribute:Sadness`	0.33	-1.34	0.34	-1.32
`voiceclap_attribute:Serious_vs._Humorous`	1.28	0.83	1.45	1.14
`voiceclap_attribute:Sexual_Lust`	-0.19	-1.98	-0.20	-1.99
`voiceclap_attribute:Shame`	-0.01	-1.89	-0.18	-2.48
`voiceclap_attribute:Soft_vs._Harsh`	0.24	0.21	0.14	-0.05
`voiceclap_attribute:Sourness`	0.35	-1.22	0.41	-1.02
`voiceclap_attribute:Submissive_vs._Dominant`	0.58	-0.13	0.77	0.40
`voiceclap_attribute:Teasing`	0.45	-0.24	0.28	-0.69
`voiceclap_attribute:Thankfulness_Gratitude`	-0.01	-2.63	0.09	-2.44
`voiceclap_attribute:Triumph`	0.28	-1.21	0.23	-1.36
`voiceclap_attribute:Valence`	-0.75	-1.17	-0.73	-1.15
`voiceclap_attribute:Vulnerable_vs._Emotionally_Detached`	0.44	-2.16	0.46	-2.11
`voiceclap_attribute:Warm_vs._Cold`	-0.11	-0.12	-0.29	-0.56
`voiceclap_attribute:duration`	5.20	-0.90	3.62	-1.15
`voiceclap_attribute:score_background_quality`	3.14	-0.22	3.29	0.09
`voiceclap_attribute:score_content_enjoyment`	4.46	-1.34	4.47	-1.26
`voiceclap_attribute:score_overall_quality`	2.23	-0.97	2.29	-0.83
`voiceclap_attribute:score_speech_quality`	1.93	0.60	1.99	1.40
`voiceclap_attribute:talking_speed`	2.56	-1.72	3.03	-1.60

← All 50 examples ← Previous