Interactive listening evidence · Base & Medium

Vocal burst 04: Sniff

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 →

04. Sniff

k77_age2_bg1VARSH__extremely_low__en.c036

vprof_original · en/synth · 4.32 s · test split

3 Gemini eventsBase count 2.8Medium count 2.0

Source key: k77_age2_bg1__V__ARSH__extremely_low__en.c036 · Audio SHA256: 321c43efd1acd13441fe8b9992506d0adbe72375884e7716ba3f752cf27df9f2

Gemini annotation · selection aid

0.04–0.40 s: Sniff · group sniff
1.25–1.70 s: Sniff · group sniff
3.42–3.82 s: Sniff · group sniff

Base predictions

20 ms frame probability; dashed line = 0.5 threshold

0.00–0.66 s: Throat Clearing 16%, Effort Grunt 14%, Other / rare burst 12% · onset 0.99
2.48–3.32 s: Other / rare burst 36%, Breath 22%, Exhausted Groan 5% · onset 0.60
2.74–3.52 s: Other / rare burst 45%, Breath 18%, Effort Grunt 6% · onset 0.51
2.98–3.68 s: Other / rare burst 41%, Breath 19%, Exhausted Groan 6% · onset 0.73
3.08–3.92 s: Breath 27%, Other / rare burst 21%, Exhausted Groan 10% · onset 0.53
3.22–4.06 s: Breath 33%, Other / rare burst 12%, Exasperated Sigh 11% · onset 0.86
3.32–4.12 s: Breath 28%, Exasperated Sigh 16%, Relief Sigh 10% · onset 0.60
3.42–4.00 s: Breath 16%, Exasperated Sigh 15%, Relief Sigh 12% · onset 0.81
3.48–4.12 s: Breath 22%, Exasperated Sigh 18%, Relief Sigh 12% · onset 0.82
3.74–4.32 s: Breath 35%, Exasperated Sigh 20%, Sharp Inhale 10% · onset 0.81
3.98–4.32 s: Sharp Inhale 40%, Exasperated Sigh 14%, Breath 10% · onset 0.69

Frame-positive regions: 1 · CPS 0.30 · Orange timbre cosine 0.713 · identity cosine 0.647

Medium predictions

20 ms frame probability; dashed line = 0.5 threshold

0.00–0.72 s: Other / rare burst 24%, Exhausted Groan 12%, Effort Grunt 12% · onset 1.00
0.10–0.80 s: Other / rare burst 30%, Breath 18%, Exhausted Groan 8% · onset 0.52
0.40–1.96 s: Other / rare burst 56%, Breath 31%, Exhausted Groan 2% · onset 0.56
0.56–1.90 s: Other / rare burst 54%, Breath 34%, Exhausted Groan 1% · onset 0.55
1.20–2.08 s: Other / rare burst 62%, Breath 24%, Exhausted Groan 1% · onset 0.52
1.48–2.42 s: Other / rare burst 62%, Breath 25%, Exhausted Groan 2% · onset 0.54
1.62–2.46 s: Other / rare burst 61%, Breath 26%, Exhausted Groan 2% · onset 0.53
2.52–3.42 s: Breath 41%, Other / rare burst 39%, Exhausted Groan 5% · onset 0.52
2.76–3.70 s: Breath 51%, Other / rare burst 23%, Exhausted Groan 6% · onset 0.54
2.98–3.90 s: Breath 47%, Other / rare burst 13%, Exasperated Sigh 9% · onset 0.69
3.08–3.86 s: Breath 44%, Other / rare burst 12%, Exasperated Sigh 10% · onset 0.53
3.14–3.90 s: Breath 40%, Exasperated Sigh 13%, Other / rare burst 10% · onset 0.59
3.24–4.12 s: Breath 34%, Exasperated Sigh 14%, Sharp Inhale 8% · onset 0.67
3.34–4.02 s: Breath 27%, Exasperated Sigh 13%, Sharp Inhale 10% · onset 0.56
3.40–4.10 s: Breath 24%, Sharp Inhale 13%, Relief Sigh 13% · onset 0.73

Frame-positive regions: 1 · CPS 0.18 · Orange timbre cosine 0.550 · identity cosine 0.568

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

Target	Base raw	Base z	Medium raw	Medium z
`emo_Affection`	-0.00	-0.01	0.06	0.08
`emo_Amusement`	-0.00	-0.00	0.07	0.08
`emo_Anger`	-0.11	-0.18	0.07	0.11
`emo_Astonishment_Surprise`	-0.06	-0.11	0.10	0.17
`emo_Awe`	-0.06	-0.13	0.00	0.01
`emo_Bitterness`	0.05	0.09	0.03	0.04
`emo_Concentration`	0.61	-0.03	0.44	-0.26
`emo_Confusion`	-0.07	-0.14	0.04	0.07
`emo_Contemplation`	0.18	0.17	0.17	0.14
`emo_Contempt`	-0.00	-0.00	0.03	0.06
`emo_Contentment`	0.12	0.23	0.23	0.45
`emo_Disappointment`	0.41	0.58	0.21	0.30
`emo_Disgust`	-0.01	-0.03	0.05	0.09
`emo_Distress`	1.58	1.93	1.56	1.90
`emo_Doubt`	0.01	0.00	0.00	-0.00
`emo_Elation`	-0.00	-0.02	0.05	0.05
`emo_Embarrassment`	0.02	-0.05	0.02	-0.05
`emo_Emotional_Numbness`	0.09	0.10	0.15	0.16
`emo_Fatigue_Exhaustion`	2.61	4.80	2.65	4.87
`emo_Fear`	0.44	0.70	0.40	0.64
`emo_Helplessness`	0.90	1.30	0.59	0.85
`emo_Hope_Enthusiasm_Optimism`	0.07	-0.07	0.18	0.08
`emo_Impatience_and_Irritability`	0.32	0.24	0.26	0.16
`emo_Infatuation`	-0.01	0.01	0.05	0.13
`emo_Interest`	0.34	-1.37	0.11	-1.63
`emo_Intoxication_Altered_States_of_Consciousness`	-0.03	-0.01	0.04	0.12
`emo_Jealousy_and_Envy`	-0.00	-0.14	-0.05	-0.24
`emo_Longing`	-0.03	-0.18	0.06	-0.05
`emo_Malevolence_Malice`	0.08	0.04	-0.00	-0.10
`emo_Pain`	1.37	2.37	0.55	0.95
`emo_Pleasure_Ecstasy`	0.10	0.13	0.17	0.25
`emo_Pride`	0.05	0.09	0.03	0.06
`emo_Relief`	0.18	0.22	0.65	0.91
`emo_Sadness`	0.30	0.39	0.19	0.25
`emo_Sexual_Lust`	0.00	-0.06	0.08	0.10
`emo_Shame`	-0.03	-0.08	-0.01	-0.04
`emo_Sourness`	-0.01	-0.02	0.09	0.21
`emo_Teasing`	-0.00	-0.00	0.00	0.01
`emo_Thankfulness_Gratitude`	-0.09	-0.19	0.04	-0.00
`emo_Triumph`	-0.01	-0.01	0.03	0.08
`vn_AGEV_reg`	2.94	-0.04	2.78	-0.17
`vn_AROU_reg`	2.89	0.47	3.01	0.57
`vn_ARSH_reg`	2.62	0.04	2.81	0.27
`vn_ATCK_reg`	2.63	0.36	2.33	0.13
`vn_BKGN_reg`	3.37	0.88	3.58	1.15
`vn_BRGT_reg`	2.76	0.95	2.86	1.07
`vn_CHNK_reg`	1.67	-0.14	1.19	-0.53
`vn_CLRT_reg`	1.36	-0.69	1.05	-1.03
`vn_COGL_reg`	0.83	-1.19	0.28	-1.71
`vn_DARC_reg`	2.76	0.83	2.60	0.72
`vn_DFLU_reg`	0.47	-1.70	0.34	-1.81
`vn_EMPH_reg`	2.30	-0.20	2.05	-0.36
`vn_ESTH_reg`	2.72	0.40	2.53	0.16
`vn_EXPL_reg`	0.05	-0.12	0.02	-0.22
`vn_FOCS_reg`	2.62	0.25	2.51	0.15
`vn_FULL_reg`	2.73	1.07	2.81	1.17
`vn_GEND_reg`	3.23	-0.52	3.02	-0.65
`vn_HARM_reg`	2.01	-0.57	1.88	-0.72
`vn_METL_reg`	1.30	-0.34	1.23	-0.40
`vn_RANG_reg`	1.94	-1.08	2.01	-1.00
`vn_RCQL_reg`	3.45	0.79	3.44	0.77
`vn_REGS_reg`	2.66	1.15	2.82	1.28
`vn_RESP_reg`	3.82	1.08	4.68	1.89
`vn_ROUG_reg`	2.63	0.67	2.81	0.87
`vn_R_CHST_reg`	2.42	0.34	1.95	-0.22
`vn_R_HEAD_reg`	1.84	-0.37	1.75	-0.48
`vn_R_MASK_reg`	1.71	-0.19	1.63	-0.28
`vn_R_MIXD_reg`	2.31	1.05	2.13	0.82
`vn_R_NASL_reg`	1.29	-1.43	1.15	-1.57
`vn_R_ORAL_reg`	2.66	0.64	2.72	0.73
`vn_R_THRT_reg`	3.09	1.27	3.57	1.87
`vn_SMTH_reg`	2.59	0.41	2.01	-0.12
`vn_STNC_reg`	1.89	-0.65	1.55	-0.96
`vn_STRU_reg`	1.25	-0.92	1.41	-0.75
`vn_S_ASMR_reg`	1.50	0.09	1.26	-0.08
`vn_S_AUTH_reg`	0.72	-0.35	0.23	-0.82
`vn_S_CART_reg`	0.14	-1.01	0.55	-0.72
`vn_S_CASU_reg`	2.88	-0.72	2.91	-0.69
`vn_S_CONV_reg`	1.47	-0.85	1.03	-1.18
`vn_S_DRAM_reg`	2.55	-0.15	2.86	0.12
`vn_S_FORM_reg`	0.04	-1.13	0.25	-0.92
`vn_S_MONO_reg`	2.80	-0.02	2.91	0.07
`vn_S_NARR_reg`	-0.14	-1.00	-0.35	-1.15
`vn_S_NEWS_reg`	0.15	-0.46	0.13	-0.50
`vn_S_PLAY_reg`	0.34	-1.53	0.36	-1.51
`vn_S_RANT_reg`	-0.08	-1.00	-0.37	-1.23
`vn_S_STRY_reg`	-0.37	-2.09	-0.58	-2.24
`vn_S_TECH_reg`	0.26	-0.32	0.09	-0.45
`vn_S_WHIS_reg`	1.56	-0.02	1.57	-0.01
`vn_TEMP_reg`	2.59	0.39	2.29	0.14
`vn_TENS_reg`	3.14	1.85	3.21	1.94
`vn_VALN_reg`	1.71	-0.55	1.68	-0.58
`vn_VALS_reg`	2.84	0.30	3.11	0.55
`vn_VFLX_reg`	3.17	0.76	2.99	0.61
`vn_VOLT_reg`	1.68	-1.02	2.01	-0.65
`vn_VULN_reg`	3.72	1.08	4.07	1.45
`vn_WARM_reg`	2.76	0.20	2.30	-0.31
`genuineness_0_6`	4.63	1.42	4.51	1.34
`blend_0_10`	8.66	0.73	8.47	0.66
`R_quality`	0.86	-0.71	0.79	-0.91
`eiv_extra:Age`	1.80	-4.95	2.04	-4.12
`eiv_extra:Arousal`	2.27	2.25	1.89	1.37
`eiv_extra:Authenticity`	2.64	-0.17	2.66	-0.05
`eiv_extra:Background_Noise`	0.84	0.13	0.82	0.05
`eiv_extra:Confident_vs._Hesitant`	1.96	3.03	1.86	2.72
`eiv_extra:Gender`	0.05	0.67	0.05	0.67
`eiv_extra:High-Pitched_vs._Low-Pitched`	1.07	-3.05	1.16	-2.67
`eiv_extra:Monotone_vs._Expressive`	1.49	-0.78	1.54	-0.67
`eiv_extra:Recording_Quality`	1.42	-2.17	1.56	-1.75
`eiv_extra:Serious_vs._Humorous`	-0.01	-2.76	0.21	-2.11
`eiv_extra:Soft_vs._Harsh`	0.78	1.56	1.02	2.32
`eiv_extra:Submissive_vs._Dominant`	-0.34	-2.22	-0.27	-1.99
`eiv_extra:Valence`	-0.25	-0.66	-0.33	-0.87
`eiv_extra:Vulnerable_vs._Emotionally_Detached`	0.48	-2.82	0.57	-2.62
`eiv_extra:Warm_vs._Cold`	-0.29	-1.15	-0.19	-0.79
`eiv_extra:score_background_quality`	2.36	-1.35	2.44	-1.24
`eiv_extra:score_content_enjoyment`	3.35	-3.82	3.30	-3.97
`eiv_extra:score_overall_quality`	1.56	-2.15	1.55	-2.18
`eiv_extra:score_speech_quality`	1.56	-1.71	1.59	-1.51
`audiobox:CE`	2.57	-2.19	3.12	-1.65
`audiobox:CU`	5.74	0.10	6.60	0.95
`audiobox:PC`	2.03	-0.19	2.02	-0.19
`audiobox:PQ`	6.49	-0.63	7.33	0.32
`dnsmos:SIG_raw`	1.77	-3.19	2.54	-2.04
`dnsmos:BAK_raw`	2.72	-0.44	3.37	0.14
`dnsmos:OVRL_raw`	1.72	-1.68	2.33	-0.93
`dnsmos:SIG`	1.95	-3.08	2.54	-1.89
`dnsmos:BAK`	2.78	-0.66	3.36	-0.03
`dnsmos:OVRL`	1.74	-1.82	2.21	-1.04
`dnsmos:P808_MOS`	2.38	-2.10	2.45	-1.96
`burst_count_log1p`	1.33	2.06	1.11	1.71
`voiceclap_attribute:Affection`	0.12	-1.49	0.12	-1.49
`voiceclap_attribute:Age`	2.24	-1.80	1.83	-2.56
`voiceclap_attribute:Amusement`	0.46	0.12	0.37	-0.03
`voiceclap_attribute:Anger`	0.07	-1.82	-0.03	-2.02
`voiceclap_attribute:Arousal`	1.58	0.26	1.66	0.39
`voiceclap_attribute:Astonishment_Surprise`	0.17	-0.70	0.10	-0.86
`voiceclap_attribute:Authenticity`	2.96	1.16	2.84	0.41
`voiceclap_attribute:Awe`	-0.06	-2.31	-0.26	-3.08
`voiceclap_attribute:Background_Noise`	0.51	-0.23	0.65	0.33
`voiceclap_attribute:Bitterness`	0.08	-2.15	-0.07	-2.82
`voiceclap_attribute:Concentration`	0.28	-1.76	0.52	-1.30
`voiceclap_attribute:Confident_vs._Hesitant`	1.43	0.77	1.50	0.92
`voiceclap_attribute:Confusion`	0.09	-1.67	-0.14	-2.36
`voiceclap_attribute:Contemplation`	0.33	-1.12	0.18	-1.47
`voiceclap_attribute:Contempt`	-0.05	-2.24	-0.08	-2.32
`voiceclap_attribute:Contentment`	0.37	-0.70	0.37	-0.70
`voiceclap_attribute:Disappointment`	0.18	-1.98	0.14	-2.12
`voiceclap_attribute:Disgust`	0.06	-2.71	0.03	-2.89
`voiceclap_attribute:Distress`	1.10	0.49	1.21	0.80
`voiceclap_attribute:Doubt`	0.25	-1.52	-0.03	-3.01
`voiceclap_attribute:Elation`	0.20	-0.86	0.10	-1.11
`voiceclap_attribute:Embarrassment`	-0.04	-1.10	-0.09	-1.27
`voiceclap_attribute:Emotional_Numbness`	0.18	-1.82	0.00	-2.49
`voiceclap_attribute:Fatigue_Exhaustion`	1.46	3.81	1.57	4.23
`voiceclap_attribute:Fear`	0.31	-1.45	0.26	-1.67
`voiceclap_attribute:Gender`	0.56	0.70	-0.20	-0.05
`voiceclap_attribute:Helplessness`	0.95	1.08	0.91	0.93
`voiceclap_attribute:High-Pitched_vs._Low-Pitched`	1.11	-1.95	1.36	-1.27
`voiceclap_attribute:Hope_Enthusiasm_Optimism`	0.13	-1.44	0.23	-1.21
`voiceclap_attribute:Impatience_and_Irritability`	0.26	-1.46	0.14	-1.69
`voiceclap_attribute:Infatuation`	-0.04	-1.94	-0.13	-2.21
`voiceclap_attribute:Interest`	0.12	-3.37	0.22	-3.13
`voiceclap_attribute:Intoxication_Altered_States_of_Consciousness`	-0.16	-1.44	0.02	-1.03
`voiceclap_attribute:Jealousy_&_Envy`	0.00	-2.13	0.00	-2.12
`voiceclap_attribute:Longing`	0.04	-2.28	-0.09	-2.85
`voiceclap_attribute:Malevolence_Malice`	0.06	-2.24	-0.10	-2.70
`voiceclap_attribute:Monotone_vs._Expressive`	1.63	-0.24	1.56	-0.37
`voiceclap_attribute:Pain`	0.68	1.38	0.69	1.43
`voiceclap_attribute:Pleasure_Ecstasy`	0.07	-1.45	0.04	-1.54
`voiceclap_attribute:Pride`	0.00	-2.23	0.10	-1.96
`voiceclap_attribute:Recording_Quality`	1.85	-1.43	1.69	-1.89
`voiceclap_attribute:Relief`	0.44	-1.41	0.43	-1.43
`voiceclap_attribute:Sadness`	0.47	-0.90	0.32	-1.38
`voiceclap_attribute:Serious_vs._Humorous`	0.80	-0.01	0.85	0.08
`voiceclap_attribute:Sexual_Lust`	0.02	-1.48	-0.05	-1.63
`voiceclap_attribute:Shame`	-0.04	-1.98	-0.10	-2.20
`voiceclap_attribute:Soft_vs._Harsh`	0.90	2.05	0.81	1.80
`voiceclap_attribute:Sourness`	0.11	-2.06	-0.08	-2.70
`voiceclap_attribute:Submissive_vs._Dominant`	0.03	-1.66	0.12	-1.42
`voiceclap_attribute:Teasing`	0.10	-1.15	-0.10	-1.70
`voiceclap_attribute:Thankfulness_Gratitude`	-0.07	-2.75	0.15	-2.33
`voiceclap_attribute:Triumph`	-0.06	-2.16	0.09	-1.75
`voiceclap_attribute:Valence`	-0.42	-0.65	-0.49	-0.77
`voiceclap_attribute:Vulnerable_vs._Emotionally_Detached`	0.49	-2.07	0.65	-1.77
`voiceclap_attribute:Warm_vs._Cold`	0.23	0.75	0.08	0.36
`voiceclap_attribute:duration`	2.43	-1.33	2.58	-1.31
`voiceclap_attribute:score_background_quality`	3.05	-0.39	3.22	-0.06
`voiceclap_attribute:score_content_enjoyment`	4.40	-1.77	4.30	-2.44
`voiceclap_attribute:score_overall_quality`	2.04	-1.44	2.06	-1.40
`voiceclap_attribute:score_speech_quality`	2.00	1.55	1.99	1.47
`voiceclap_attribute:talking_speed`	2.92	-1.63	1.80	-1.92

← All 50 examples ← Previous Next →