Interactive listening evidence · Base & Medium

Vocal burst 26: Quiet Sob, Trembling Whimper

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 Next →

26. Quiet Sob, Trembling Whimper

k462_age2_bg1VS_ASMR__extremely_low__en.c035.k2

vc_sidon · en/synth · 12.70 s · test split

2 Gemini eventsBase count 2.9Medium count 3.4

Source key: k462_age2_bg1__V__S_ASMR__extremely_low__en.c035.k2 · Audio SHA256: 82dd096aef1dc5bbc99a12e25f6212b63b9cd768ec30ab1a634aa211c1169571

Gemini annotation · selection aid

0.00–1.48 s: Quiet Sob · group sob
2.65–4.15 s: Trembling Whimper · group sob

Base predictions

20 ms frame probability; dashed line = 0.5 threshold

0.00–1.34 s: Low Mumble 29%, Growl 20%, Other / rare burst 12% · onset 0.99
1.12–2.20 s: Other / rare burst 28%, Low Mumble 22%, Effort Grunt 9% · onset 0.53
1.74–3.04 s: Other / rare burst 15%, Effort Grunt 13%, Low Mumble 12% · onset 0.76
1.86–3.04 s: Other / rare burst 14%, Effort Grunt 13%, Low Mumble 12% · onset 0.59
1.98–3.20 s: Effort Grunt 14%, Other / rare burst 13%, Low Mumble 11% · onset 0.65
2.04–3.22 s: Effort Grunt 14%, Other / rare burst 12%, Low Mumble 11% · onset 0.54
2.20–3.30 s: Effort Grunt 14%, Other / rare burst 11%, Low Mumble 10% · onset 0.76
2.36–3.58 s: Hum 23%, Low Mumble 13%, Other / rare burst 12% · onset 0.53
2.42–3.68 s: Hum 30%, Low Mumble 13%, Other / rare burst 11% · onset 0.52
2.48–3.66 s: Hum 31%, Low Mumble 12%, Other / rare burst 11% · onset 0.79
2.68–3.90 s: Hum 43%, Other / rare burst 10%, Exhausted Groan 9% · onset 0.76
2.74–4.00 s: Hum 41%, Other / rare burst 11%, Exhausted Groan 9% · onset 0.76
2.84–4.06 s: Hum 42%, Other / rare burst 12%, Exhausted Groan 9% · onset 0.56
2.92–4.00 s: Hum 47%, Other / rare burst 10%, Exhausted Groan 9% · onset 0.72
2.98–4.02 s: Hum 50%, Other / rare burst 9%, Exhausted Groan 8% · onset 0.85
3.06–4.10 s: Hum 47%, Other / rare burst 10%, Exhausted Groan 9% · onset 0.67
3.22–4.14 s: Hum 48%, Other / rare burst 9%, Exhausted Groan 9% · onset 0.84
3.30–4.18 s: Hum 46%, Other / rare burst 10%, Exhausted Groan 10% · onset 0.67
3.44–4.32 s: Hum 35%, Other / rare burst 12%, Exhausted Groan 10% · onset 0.60
3.74–4.50 s: Other / rare burst 13%, Effort Grunt 9%, Exhausted Groan 8% · onset 0.53
3.90–4.68 s: Effort Grunt 10%, Other / rare burst 9%, Exhausted Groan 7% · onset 0.52
3.98–4.84 s: Breath 9%, Other / rare burst 8%, Effort Grunt 8% · onset 0.76
10.24–11.32 s: Breath 27%, Other / rare burst 18%, Exasperated Sigh 5% · onset 0.51
10.44–11.44 s: Breath 29%, Other / rare burst 16%, Exhausted Groan 7% · onset 0.61
10.84–11.54 s: Breath 27%, Other / rare burst 15%, Exhausted Groan 8% · onset 0.51
12.54–12.70 s: Surprised Gasp 9%, Ahem 8%, Hum 6% · onset 0.62

Frame-positive regions: 11 · CPS -0.18 · Orange timbre cosine 0.574 · identity cosine 0.576

Medium predictions

20 ms frame probability; dashed line = 0.5 threshold

0.00–1.26 s: Low Mumble 33%, Hum 13%, Growl 7% · onset 0.99
0.08–1.18 s: Low Mumble 31%, Hum 12%, Childlike Giggle 8% · onset 0.78
0.20–1.46 s: Low Mumble 33%, Hum 17%, Other / rare burst 7% · onset 0.57
1.74–2.52 s: Exhausted Groan 19%, Breath 11%, Sharp Inhale 10% · onset 0.55
1.86–2.66 s: Exhausted Groan 19%, Breath 12%, Sharp Inhale 10% · onset 0.59
1.98–2.72 s: Exhausted Groan 17%, Breath 14%, Sharp Inhale 11% · onset 0.65
2.18–3.24 s: Exhausted Groan 16%, Breath 11%, Hum 7% · onset 0.59
2.24–3.04 s: Exhausted Groan 15%, Breath 12%, Sharp Inhale 9% · onset 0.74
2.50–3.42 s: Hum 21%, Exhausted Groan 15%, Effort Grunt 6% · onset 0.76
2.56–3.62 s: Hum 36%, Exhausted Groan 14%, Other / rare burst 6% · onset 0.58
2.64–3.52 s: Hum 33%, Exhausted Groan 11%, Other / rare burst 5% · onset 0.58
2.74–3.70 s: Hum 45%, Exhausted Groan 12%, Other / rare burst 6% · onset 0.70
2.80–3.84 s: Hum 50%, Exhausted Groan 12%, Other / rare burst 6% · onset 0.57
2.88–3.72 s: Hum 55%, Exhausted Groan 9%, Low Mumble 5% · onset 0.64
3.00–3.86 s: Hum 60%, Exhausted Groan 8%, Low Mumble 5% · onset 0.75
3.26–4.12 s: Hum 49%, Exhausted Groan 8%, Other / rare burst 7% · onset 0.72
3.34–4.06 s: Hum 51%, Low Mumble 10%, Other / rare burst 6% · onset 0.50
3.40–4.12 s: Hum 40%, Low Mumble 11%, Exhausted Groan 9% · onset 0.53
4.46–5.38 s: Breath 39%, Sharp Inhale 9%, Exhausted Groan 7% · onset 0.59
9.92–10.84 s: Breath 34%, Other / rare burst 14%, Breathy Giggle 4% · onset 0.53
10.40–11.34 s: Breath 40%, Other / rare burst 12%, Exhausted Groan 7% · onset 0.53

Frame-positive regions: 9 · CPS 0.18 · Orange timbre cosine 0.569 · identity cosine 0.540

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

Target	Base raw	Base z	Medium raw	Medium z
`emo_Affection`	0.07	0.11	0.12	0.20
`emo_Amusement`	0.58	0.65	0.74	0.84
`emo_Anger`	0.01	0.01	0.14	0.22
`emo_Astonishment_Surprise`	0.15	0.25	0.08	0.13
`emo_Awe`	0.08	0.19	0.00	0.01
`emo_Bitterness`	0.05	0.10	0.04	0.07
`emo_Concentration`	0.57	-0.08	0.79	0.21
`emo_Confusion`	0.27	0.50	0.05	0.08
`emo_Contemplation`	0.36	0.47	0.66	0.97
`emo_Contempt`	0.04	0.08	0.03	0.07
`emo_Contentment`	0.47	0.91	0.78	1.52
`emo_Disappointment`	0.30	0.43	0.24	0.34
`emo_Disgust`	0.09	0.17	0.04	0.07
`emo_Distress`	0.86	1.05	0.57	0.70
`emo_Doubt`	0.34	0.72	0.22	0.47
`emo_Elation`	0.16	0.20	0.19	0.24
`emo_Embarrassment`	0.05	0.01	0.00	-0.10
`emo_Emotional_Numbness`	0.41	0.44	0.33	0.35
`emo_Fatigue_Exhaustion`	1.83	3.34	2.01	3.67
`emo_Fear`	0.20	0.30	0.01	-0.01
`emo_Helplessness`	0.89	1.29	0.57	0.83
`emo_Hope_Enthusiasm_Optimism`	0.30	0.24	0.50	0.50
`emo_Impatience_and_Irritability`	0.14	-0.01	0.20	0.07
`emo_Infatuation`	0.00	0.03	-0.03	-0.02
`emo_Interest`	0.68	-1.00	0.84	-0.83
`emo_Intoxication_Altered_States_of_Consciousness`	0.32	0.62	0.29	0.57
`emo_Jealousy_and_Envy`	0.04	-0.03	0.02	-0.10
`emo_Longing`	0.10	0.02	0.04	-0.07
`emo_Malevolence_Malice`	0.04	-0.02	0.04	-0.03
`emo_Pain`	0.58	1.00	0.78	1.36
`emo_Pleasure_Ecstasy`	0.15	0.21	0.12	0.16
`emo_Pride`	0.04	0.08	0.08	0.14
`emo_Relief`	0.25	0.32	0.30	0.39
`emo_Sadness`	0.32	0.42	0.18	0.24
`emo_Sexual_Lust`	0.01	-0.03	-0.02	-0.10
`emo_Shame`	0.05	0.08	0.02	0.01
`emo_Sourness`	0.03	0.08	0.07	0.17
`emo_Teasing`	0.21	0.39	0.22	0.41
`emo_Thankfulness_Gratitude`	0.03	-0.02	0.07	0.03
`emo_Triumph`	0.09	0.19	0.05	0.10
`vn_AGEV_reg`	3.16	0.14	2.77	-0.17
`vn_AROU_reg`	2.80	0.39	2.58	0.19
`vn_ARSH_reg`	2.64	0.07	2.70	0.13
`vn_ATCK_reg`	2.68	0.40	2.38	0.17
`vn_BKGN_reg`	3.32	0.81	3.38	0.89
`vn_BRGT_reg`	2.74	0.92	2.79	0.98
`vn_CHNK_reg`	1.43	-0.33	1.45	-0.32
`vn_CLRT_reg`	1.30	-0.76	1.74	-0.29
`vn_COGL_reg`	1.14	-0.90	1.19	-0.85
`vn_DARC_reg`	2.89	0.92	2.53	0.66
`vn_DFLU_reg`	0.28	-1.87	0.50	-1.68
`vn_EMPH_reg`	2.93	0.21	2.45	-0.10
`vn_ESTH_reg`	2.50	0.13	2.83	0.55
`vn_EXPL_reg`	0.04	-0.14	0.09	0.00
`vn_FOCS_reg`	2.71	0.33	2.81	0.43
`vn_FULL_reg`	2.50	0.81	2.76	1.10
`vn_GEND_reg`	2.38	-1.06	2.51	-0.97
`vn_HARM_reg`	2.33	-0.17	2.14	-0.41
`vn_METL_reg`	1.47	-0.15	1.06	-0.58
`vn_RANG_reg`	2.87	-0.05	2.60	-0.35
`vn_RCQL_reg`	3.45	0.79	3.53	0.87
`vn_REGS_reg`	2.71	1.19	2.80	1.26
`vn_RESP_reg`	3.04	0.34	3.34	0.62
`vn_ROUG_reg`	2.86	0.93	2.86	0.93
`vn_R_CHST_reg`	2.36	0.26	2.30	0.19
`vn_R_HEAD_reg`	2.48	0.40	2.24	0.11
`vn_R_MASK_reg`	2.21	0.30	2.03	0.13
`vn_R_MIXD_reg`	2.60	1.38	2.44	1.19
`vn_R_NASL_reg`	1.81	-0.94	1.83	-0.92
`vn_R_ORAL_reg`	2.82	0.86	2.89	0.96
`vn_R_THRT_reg`	3.52	1.81	3.11	1.29
`vn_SMTH_reg`	2.19	0.04	2.37	0.20
`vn_STNC_reg`	1.86	-0.68	1.86	-0.68
`vn_STRU_reg`	1.41	-0.75	1.66	-0.50
`vn_S_ASMR_reg`	0.65	-0.51	1.44	0.05
`vn_S_AUTH_reg`	0.43	-0.63	0.97	-0.12
`vn_S_CART_reg`	1.47	-0.07	1.16	-0.29
`vn_S_CASU_reg`	2.79	-0.79	3.00	-0.62
`vn_S_CONV_reg`	0.77	-1.38	1.63	-0.73
`vn_S_DRAM_reg`	3.16	0.38	2.89	0.15
`vn_S_FORM_reg`	0.22	-0.95	0.60	-0.58
`vn_S_MONO_reg`	3.27	0.35	2.83	0.00
`vn_S_NARR_reg`	0.66	-0.45	0.85	-0.32
`vn_S_NEWS_reg`	-0.02	-0.75	0.09	-0.55
`vn_S_PLAY_reg`	1.45	-0.69	1.69	-0.50
`vn_S_RANT_reg`	-0.20	-1.10	0.02	-0.93
`vn_S_STRY_reg`	0.69	-1.31	0.82	-1.22
`vn_S_TECH_reg`	-0.01	-0.54	0.11	-0.44
`vn_S_WHIS_reg`	1.17	-0.26	1.18	-0.26
`vn_TEMP_reg`	1.94	-0.14	1.97	-0.12
`vn_TENS_reg`	2.67	1.30	2.58	1.19
`vn_VALN_reg`	2.27	-0.05	2.27	-0.05
`vn_VALS_reg`	2.56	0.04	2.60	0.07
`vn_VFLX_reg`	2.82	0.47	2.86	0.50
`vn_VOLT_reg`	2.05	-0.60	2.04	-0.61
`vn_VULN_reg`	3.48	0.85	3.31	0.67
`vn_WARM_reg`	2.51	-0.08	2.80	0.24
`genuineness_0_6`	3.61	0.79	3.88	0.95
`blend_0_10`	7.46	0.29	7.55	0.32
`R_quality`	0.50	-1.77	0.64	-1.34
`eiv_extra:Age`	1.04	-7.53	1.56	-5.77
`eiv_extra:Arousal`	1.71	0.97	1.42	0.29
`eiv_extra:Authenticity`	2.58	-0.54	2.63	-0.26
`eiv_extra:Background_Noise`	0.86	0.20	0.80	-0.03
`eiv_extra:Confident_vs._Hesitant`	2.04	3.31	2.10	3.50
`eiv_extra:Gender`	0.26	0.88	0.06	0.69
`eiv_extra:High-Pitched_vs._Low-Pitched`	1.30	-2.11	1.44	-1.53
`eiv_extra:Monotone_vs._Expressive`	1.82	-0.09	1.66	-0.41
`eiv_extra:Recording_Quality`	1.36	-2.36	1.33	-2.45
`eiv_extra:Serious_vs._Humorous`	0.90	-0.07	1.19	0.75
`eiv_extra:Soft_vs._Harsh`	1.12	2.63	1.31	3.21
`eiv_extra:Submissive_vs._Dominant`	-0.40	-2.41	-0.52	-2.77
`eiv_extra:Valence`	-0.29	-0.77	-0.22	-0.59
`eiv_extra:Vulnerable_vs._Emotionally_Detached`	0.53	-2.71	0.67	-2.38
`eiv_extra:Warm_vs._Cold`	0.27	0.72	0.48	1.42
`eiv_extra:score_background_quality`	3.08	-0.32	3.31	0.02
`eiv_extra:score_content_enjoyment`	3.69	-2.70	3.61	-2.96
`eiv_extra:score_overall_quality`	2.32	-0.65	2.45	-0.39
`eiv_extra:score_speech_quality`	1.72	-0.63	1.77	-0.26
`audiobox:CE`	3.65	-1.13	3.40	-1.37
`audiobox:CU`	6.33	0.68	6.49	0.84
`audiobox:PC`	1.82	-0.32	1.78	-0.34
`audiobox:PQ`	7.40	0.40	7.48	0.50
`dnsmos:SIG_raw`	2.74	-1.74	2.68	-1.83
`dnsmos:BAK_raw`	3.60	0.35	3.66	0.40
`dnsmos:OVRL_raw`	2.47	-0.76	2.46	-0.77
`dnsmos:SIG`	2.75	-1.48	2.67	-1.62
`dnsmos:BAK`	3.60	0.22	3.66	0.29
`dnsmos:OVRL`	2.37	-0.78	2.37	-0.78
`dnsmos:P808_MOS`	2.53	-1.80	2.66	-1.53
`burst_count_log1p`	1.37	2.12	1.49	2.30
`voiceclap_attribute:Affection`	0.31	-1.16	0.24	-1.27
`voiceclap_attribute:Age`	1.80	-2.62	1.63	-2.93
`voiceclap_attribute:Amusement`	0.64	0.43	0.51	0.21
`voiceclap_attribute:Anger`	0.17	-1.63	0.16	-1.64
`voiceclap_attribute:Arousal`	1.60	0.29	1.60	0.29
`voiceclap_attribute:Astonishment_Surprise`	0.31	-0.41	0.13	-0.80
`voiceclap_attribute:Authenticity`	2.83	0.33	2.74	-0.17
`voiceclap_attribute:Awe`	0.04	-1.92	-0.09	-2.42
`voiceclap_attribute:Background_Noise`	0.72	0.58	0.81	0.91
`voiceclap_attribute:Bitterness`	0.01	-2.49	0.00	-2.50
`voiceclap_attribute:Concentration`	0.63	-1.11	0.87	-0.64
`voiceclap_attribute:Confident_vs._Hesitant`	1.54	1.01	1.80	1.55
`voiceclap_attribute:Confusion`	0.13	-1.53	0.13	-1.54
`voiceclap_attribute:Contemplation`	0.56	-0.55	0.56	-0.55
`voiceclap_attribute:Contempt`	-0.13	-2.49	0.09	-1.82
`voiceclap_attribute:Contentment`	0.73	0.47	0.67	0.27
`voiceclap_attribute:Disappointment`	0.13	-2.18	0.24	-1.78
`voiceclap_attribute:Disgust`	-0.05	-3.23	0.05	-2.76
`voiceclap_attribute:Distress`	0.96	0.08	0.98	0.16
`voiceclap_attribute:Doubt`	0.19	-1.85	0.39	-0.76
`voiceclap_attribute:Elation`	0.26	-0.69	0.03	-1.27
`voiceclap_attribute:Embarrassment`	-0.12	-1.35	-0.03	-1.08
`voiceclap_attribute:Emotional_Numbness`	0.04	-2.34	0.12	-2.06
`voiceclap_attribute:Fatigue_Exhaustion`	1.15	2.66	1.41	3.64
`voiceclap_attribute:Fear`	0.11	-2.38	0.16	-2.15
`voiceclap_attribute:Gender`	0.72	0.87	0.34	0.49
`voiceclap_attribute:Helplessness`	0.82	0.62	0.78	0.44
`voiceclap_attribute:High-Pitched_vs._Low-Pitched`	1.34	-1.35	1.31	-1.42
`voiceclap_attribute:Hope_Enthusiasm_Optimism`	0.39	-0.80	0.26	-1.14
`voiceclap_attribute:Impatience_and_Irritability`	0.27	-1.44	0.36	-1.28
`voiceclap_attribute:Infatuation`	0.06	-1.65	-0.04	-1.94
`voiceclap_attribute:Interest`	0.73	-1.97	0.86	-1.68
`voiceclap_attribute:Intoxication_Altered_States_of_Consciousness`	0.15	-0.75	0.02	-1.04
`voiceclap_attribute:Jealousy_&_Envy`	-0.08	-2.47	0.04	-1.97
`voiceclap_attribute:Longing`	0.13	-1.87	0.03	-2.30
`voiceclap_attribute:Malevolence_Malice`	-0.02	-2.48	0.14	-2.01
`voiceclap_attribute:Monotone_vs._Expressive`	1.85	0.12	1.98	0.35
`voiceclap_attribute:Pain`	0.64	1.19	0.49	0.51
`voiceclap_attribute:Pleasure_Ecstasy`	0.20	-1.01	0.03	-1.57
`voiceclap_attribute:Pride`	0.03	-2.13	-0.06	-2.40
`voiceclap_attribute:Recording_Quality`	1.75	-1.73	1.63	-2.09
`voiceclap_attribute:Relief`	0.19	-2.01	0.06	-2.32
`voiceclap_attribute:Sadness`	0.37	-1.21	0.26	-1.56
`voiceclap_attribute:Serious_vs._Humorous`	1.04	0.41	1.14	0.59
`voiceclap_attribute:Sexual_Lust`	0.11	-1.25	0.07	-1.35
`voiceclap_attribute:Shame`	-0.11	-2.26	-0.03	-1.95
`voiceclap_attribute:Soft_vs._Harsh`	0.93	2.13	0.95	2.20
`voiceclap_attribute:Sourness`	0.02	-2.36	0.16	-1.88
`voiceclap_attribute:Submissive_vs._Dominant`	-0.04	-1.85	-0.07	-1.94
`voiceclap_attribute:Teasing`	0.41	-0.35	0.43	-0.30
`voiceclap_attribute:Thankfulness_Gratitude`	0.16	-2.31	0.04	-2.53
`voiceclap_attribute:Triumph`	-0.00	-2.00	0.00	-1.99
`voiceclap_attribute:Valence`	-0.14	-0.21	-0.29	-0.44
`voiceclap_attribute:Vulnerable_vs._Emotionally_Detached`	0.55	-1.96	0.53	-1.99
`voiceclap_attribute:Warm_vs._Cold`	0.44	1.26	0.35	1.03
`voiceclap_attribute:duration`	7.87	-0.48	8.17	-0.43
`voiceclap_attribute:score_background_quality`	3.22	-0.06	3.29	0.09
`voiceclap_attribute:score_content_enjoyment`	4.43	-1.54	4.47	-1.24
`voiceclap_attribute:score_overall_quality`	2.36	-0.66	2.29	-0.85
`voiceclap_attribute:score_speech_quality`	1.98	1.22	1.95	0.88
`voiceclap_attribute:talking_speed`	-0.02	-2.41	2.12	-1.84

← All 50 examples ← Previous Next →