Interactive listening evidence · Base & Medium

Vocal burst 22: Exhausted Groan, Hiss

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 →

22. Exhausted Groan, Hiss

refvoice_0786VVALN__extremely_low__en.c013.k2

vc_sidon · en/synth · 10.86 s · test split

3 Gemini eventsBase count 4.3Medium count 4.3

Source key: refvoice_0786__V__VALN__extremely_low__en.c013.k2 · Audio SHA256: 4f592128b6815a614bdf1041698371c55fbacb35b98833a83a7e19943951575c

Gemini annotation · selection aid

0.85–2.25 s: Exhausted Groan · group sigh_neg
6.85–8.45 s: Exhausted Groan · group sigh_neg
9.70–10.75 s: Hiss · group hiss

Base predictions

20 ms frame probability; dashed line = 0.5 threshold

0.00–1.30 s: Breath 50%, Other / rare burst 24%, Exasperated Sigh 6% · onset 0.99
0.10–1.94 s: Breath 37%, Other / rare burst 25%, Exhausted Groan 11% · onset 0.68
1.12–2.30 s: Other / rare burst 31%, Breath 14%, Exhausted Groan 12% · onset 0.57
1.24–2.22 s: Other / rare burst 25%, Breath 13%, Exhausted Groan 12% · onset 0.83
1.48–2.24 s: Other / rare burst 21%, Exhausted Groan 11%, Breath 10% · onset 0.71
1.98–2.98 s: Other / rare burst 21%, Breath 12%, Effort Grunt 9% · onset 0.70
2.24–3.18 s: Other / rare burst 19%, Breath 13%, Effort Grunt 8% · onset 0.60
2.48–3.46 s: Other / rare burst 21%, Effort Grunt 9%, Breath 8% · onset 0.76
2.72–3.82 s: Other / rare burst 22%, Effort Grunt 9%, Tongue Click 8% · onset 0.68
2.98–3.98 s: Other / rare burst 23%, Tongue Click 10%, Effort Grunt 8% · onset 0.62
3.22–4.16 s: Other / rare burst 24%, Tongue Click 10%, Effort Grunt 9% · onset 0.71
3.36–5.20 s: Other / rare burst 27%, Effort Grunt 14%, Whispered Mumble 5% · onset 0.60
3.42–4.64 s: Other / rare burst 23%, Effort Grunt 12%, Tongue Click 5% · onset 0.70
3.48–4.58 s: Other / rare burst 22%, Effort Grunt 12%, Breath 6% · onset 0.65
3.74–4.74 s: Other / rare burst 20%, Effort Grunt 14%, Exhausted Groan 6% · onset 0.78
3.98–4.78 s: Other / rare burst 18%, Effort Grunt 16%, Exhausted Groan 8% · onset 0.82
4.12–5.00 s: Effort Grunt 18%, Other / rare burst 17%, Exhausted Groan 9% · onset 0.59
4.18–4.94 s: Effort Grunt 19%, Other / rare burst 14%, Exhausted Groan 8% · onset 0.61
4.34–5.10 s: Effort Grunt 19%, Other / rare burst 15%, Exhausted Groan 9% · onset 0.58
4.50–5.28 s: Effort Grunt 17%, Other / rare burst 16%, Exhausted Groan 10% · onset 0.68
5.42–6.22 s: Other / rare burst 20%, Effort Grunt 9%, Breath 9% · onset 0.67
5.82–6.82 s: Other / rare burst 34%, Breath 14%, Exhausted Groan 10% · onset 0.66
5.90–6.98 s: Other / rare burst 36%, Breath 13%, Exhausted Groan 11% · onset 0.61
6.44–7.52 s: Other / rare burst 32%, Exhausted Groan 12%, Breath 10% · onset 0.68
6.84–7.76 s: Other / rare burst 24%, Effort Grunt 14%, Exhausted Groan 10% · onset 0.66
6.94–7.80 s: Other / rare burst 20%, Effort Grunt 16%, Exhausted Groan 8% · onset 0.72
7.04–7.88 s: Other / rare burst 18%, Effort Grunt 16%, Breath 8% · onset 0.60
7.42–8.12 s: Effort Grunt 15%, Other / rare burst 13%, Breath 8% · onset 0.71
7.72–8.38 s: Effort Grunt 15%, Other / rare burst 11%, Breath 8% · onset 0.59
7.86–8.50 s: Effort Grunt 12%, Other / rare burst 11%, Breath 10% · onset 0.73
7.94–8.44 s: Effort Grunt 12%, Sharp Inhale 9%, Breath 9% · onset 0.65
8.00–8.64 s: Breath 13%, Effort Grunt 10%, Other / rare burst 9% · onset 0.80

Frame-positive regions: 2 · CPS 1.03 · Orange timbre cosine 0.627 · identity cosine 0.614

Medium predictions

20 ms frame probability; dashed line = 0.5 threshold

0.00–1.42 s: Other / rare burst 25%, Breath 24%, Exasperated Sigh 12% · onset 0.98
0.10–1.66 s: Other / rare burst 24%, Breath 20%, Exasperated Sigh 14% · onset 0.79
0.18–1.44 s: Other / rare burst 27%, Breath 22%, Exasperated Sigh 13% · onset 0.66
1.98–2.68 s: Other / rare burst 17%, Effort Grunt 14%, Sharp Inhale 9% · onset 0.62
3.48–4.70 s: Other / rare burst 28%, Effort Grunt 16%, Breath 10% · onset 0.66
3.72–4.80 s: Other / rare burst 26%, Effort Grunt 17%, Breath 9% · onset 0.80
3.78–4.86 s: Other / rare burst 26%, Effort Grunt 19%, Breath 8% · onset 0.77
3.88–4.82 s: Other / rare burst 23%, Effort Grunt 19%, Exhausted Groan 9% · onset 0.69
3.96–5.02 s: Effort Grunt 25%, Other / rare burst 23%, Exhausted Groan 8% · onset 0.76
4.12–5.20 s: Effort Grunt 28%, Other / rare burst 23%, Exhausted Groan 8% · onset 0.83
4.20–5.30 s: Effort Grunt 31%, Other / rare burst 22%, Exhausted Groan 8% · onset 0.78
4.30–5.34 s: Effort Grunt 31%, Other / rare burst 21%, Exhausted Groan 8% · onset 0.67
4.48–5.36 s: Effort Grunt 34%, Other / rare burst 20%, Exhausted Groan 8% · onset 0.77
4.94–5.84 s: Effort Grunt 40%, Other / rare burst 18%, Cough 4% · onset 0.66
5.30–6.22 s: Other / rare burst 27%, Effort Grunt 19%, Breath 8% · onset 0.70
5.46–6.40 s: Other / rare burst 27%, Breath 14%, Effort Grunt 13% · onset 0.64
5.52–6.50 s: Other / rare burst 28%, Breath 16%, Effort Grunt 11% · onset 0.64
5.74–6.74 s: Other / rare burst 29%, Breath 27%, Exhausted Groan 14% · onset 0.67
5.98–7.06 s: Breath 37%, Other / rare burst 22%, Exhausted Groan 18% · onset 0.63
6.06–7.32 s: Breath 26%, Other / rare burst 26%, Exhausted Groan 20% · onset 0.64
6.26–7.28 s: Breath 25%, Other / rare burst 22%, Exhausted Groan 19% · onset 0.62
6.32–7.40 s: Other / rare burst 24%, Breath 20%, Exhausted Groan 19% · onset 0.74
6.38–7.44 s: Other / rare burst 23%, Breath 21%, Exhausted Groan 19% · onset 0.65
6.48–7.46 s: Other / rare burst 24%, Breath 20%, Exhausted Groan 20% · onset 0.65
6.84–7.92 s: Other / rare burst 35%, Effort Grunt 23%, Exhausted Groan 10% · onset 0.69
6.90–8.12 s: Other / rare burst 30%, Effort Grunt 27%, Exhausted Groan 10% · onset 0.61
6.98–8.00 s: Effort Grunt 35%, Other / rare burst 30%, Exhausted Groan 6% · onset 0.70
7.34–8.34 s: Effort Grunt 31%, Other / rare burst 20%, Exhausted Groan 9% · onset 0.74
7.40–8.54 s: Effort Grunt 32%, Other / rare burst 21%, Exhausted Groan 9% · onset 0.69
7.46–8.56 s: Effort Grunt 34%, Other / rare burst 23%, Exhausted Groan 7% · onset 0.73
9.36–10.62 s: Other / rare burst 14%, Breath 13%, Effort Grunt 12% · onset 0.65
9.86–10.86 s: Other / rare burst 20%, Effort Grunt 11%, Breath 9% · onset 0.62

Frame-positive regions: 2 · CPS 0.18 · Orange timbre cosine 0.760 · identity cosine 0.675

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

Target	Base raw	Base z	Medium raw	Medium z
`emo_Affection`	0.05	0.07	0.07	0.10
`emo_Amusement`	0.17	0.20	0.14	0.16
`emo_Anger`	0.08	0.12	0.13	0.20
`emo_Astonishment_Surprise`	0.05	0.08	0.04	0.06
`emo_Awe`	0.02	0.04	-0.00	-0.01
`emo_Bitterness`	0.08	0.16	0.06	0.12
`emo_Concentration`	0.76	0.16	0.76	0.17
`emo_Confusion`	0.02	0.03	0.02	0.03
`emo_Contemplation`	0.30	0.36	0.34	0.43
`emo_Contempt`	0.05	0.11	0.02	0.05
`emo_Contentment`	0.20	0.39	0.22	0.44
`emo_Disappointment`	0.31	0.44	0.29	0.42
`emo_Disgust`	0.07	0.13	0.05	0.08
`emo_Distress`	1.16	1.41	1.28	1.56
`emo_Doubt`	0.05	0.09	0.06	0.13
`emo_Elation`	0.08	0.10	0.12	0.15
`emo_Embarrassment`	0.03	-0.02	-0.03	-0.16
`emo_Emotional_Numbness`	0.24	0.26	0.43	0.46
`emo_Fatigue_Exhaustion`	2.85	5.24	3.22	5.93
`emo_Fear`	0.33	0.51	0.12	0.18
`emo_Helplessness`	0.77	1.11	1.06	1.53
`emo_Hope_Enthusiasm_Optimism`	0.17	0.06	0.28	0.21
`emo_Impatience_and_Irritability`	0.29	0.20	0.27	0.17
`emo_Infatuation`	-0.01	0.01	0.03	0.09
`emo_Interest`	0.56	-1.13	0.36	-1.36
`emo_Intoxication_Altered_States_of_Consciousness`	0.16	0.32	0.14	0.30
`emo_Jealousy_and_Envy`	0.02	-0.08	0.00	-0.13
`emo_Longing`	0.07	-0.03	0.07	-0.03
`emo_Malevolence_Malice`	0.11	0.10	0.02	-0.06
`emo_Pain`	0.88	1.52	1.48	2.56
`emo_Pleasure_Ecstasy`	0.12	0.17	0.17	0.25
`emo_Pride`	0.05	0.09	0.05	0.09
`emo_Relief`	0.41	0.55	0.91	1.28
`emo_Sadness`	0.31	0.40	0.15	0.20
`emo_Sexual_Lust`	0.04	0.01	0.04	0.02
`emo_Shame`	0.05	0.07	-0.01	-0.05
`emo_Sourness`	0.04	0.10	0.10	0.24
`emo_Teasing`	0.07	0.12	0.10	0.18
`emo_Thankfulness_Gratitude`	0.04	0.00	0.08	0.06
`emo_Triumph`	0.07	0.15	0.04	0.09
`vn_AGEV_reg`	2.91	-0.06	2.48	-0.41
`vn_AROU_reg`	2.35	-0.01	2.70	0.30
`vn_ARSH_reg`	2.34	-0.27	2.69	0.13
`vn_ATCK_reg`	2.46	0.23	2.48	0.25
`vn_BKGN_reg`	3.31	0.80	3.45	0.98
`vn_BRGT_reg`	2.58	0.72	2.89	1.11
`vn_CHNK_reg`	0.80	-0.84	0.64	-0.98
`vn_CLRT_reg`	0.93	-1.15	1.23	-0.83
`vn_COGL_reg`	1.44	-0.61	1.50	-0.56
`vn_DARC_reg`	2.43	0.59	2.56	0.68
`vn_DFLU_reg`	0.90	-1.34	0.92	-1.32
`vn_EMPH_reg`	2.26	-0.23	2.12	-0.32
`vn_ESTH_reg`	2.08	-0.42	2.27	-0.17
`vn_EXPL_reg`	0.09	-0.00	0.15	0.21
`vn_FOCS_reg`	2.19	-0.14	2.43	0.08
`vn_FULL_reg`	2.29	0.58	2.46	0.77
`vn_GEND_reg`	2.15	-1.20	2.00	-1.29
`vn_HARM_reg`	1.11	-1.64	1.15	-1.59
`vn_METL_reg`	1.01	-0.64	1.05	-0.60
`vn_RANG_reg`	1.77	-1.27	2.11	-0.89
`vn_RCQL_reg`	3.17	0.47	3.37	0.69
`vn_REGS_reg`	3.03	1.45	2.97	1.40
`vn_RESP_reg`	4.34	1.57	5.04	2.24
`vn_ROUG_reg`	2.86	0.93	3.16	1.27
`vn_R_CHST_reg`	1.89	-0.29	1.59	-0.65
`vn_R_HEAD_reg`	1.59	-0.68	1.76	-0.47
`vn_R_MASK_reg`	1.45	-0.45	1.62	-0.29
`vn_R_MIXD_reg`	1.97	0.63	1.87	0.52
`vn_R_NASL_reg`	1.09	-1.62	1.18	-1.54
`vn_R_ORAL_reg`	2.49	0.42	2.88	0.94
`vn_R_THRT_reg`	3.05	1.22	3.37	1.62
`vn_SMTH_reg`	1.60	-0.49	1.55	-0.55
`vn_STNC_reg`	1.13	-1.32	1.04	-1.40
`vn_STRU_reg`	0.91	-1.28	1.22	-0.96
`vn_S_ASMR_reg`	1.53	0.11	2.18	0.57
`vn_S_AUTH_reg`	0.25	-0.80	-0.08	-1.12
`vn_S_CART_reg`	0.98	-0.41	1.09	-0.33
`vn_S_CASU_reg`	2.33	-1.15	2.61	-0.92
`vn_S_CONV_reg`	0.47	-1.61	1.05	-1.17
`vn_S_DRAM_reg`	3.35	0.55	3.28	0.49
`vn_S_FORM_reg`	0.13	-1.04	0.21	-0.97
`vn_S_MONO_reg`	3.59	0.59	3.62	0.62
`vn_S_NARR_reg`	0.15	-0.80	0.29	-0.70
`vn_S_NEWS_reg`	-0.08	-0.86	-0.03	-0.78
`vn_S_PLAY_reg`	-0.37	-2.07	0.48	-1.42
`vn_S_RANT_reg`	-0.15	-1.06	-0.03	-0.96
`vn_S_STRY_reg`	0.15	-1.70	0.23	-1.65
`vn_S_TECH_reg`	-0.22	-0.70	-0.02	-0.54
`vn_S_WHIS_reg`	2.35	0.47	2.12	0.33
`vn_TEMP_reg`	1.65	-0.39	1.69	-0.36
`vn_TENS_reg`	3.17	1.89	3.36	2.12
`vn_VALN_reg`	0.85	-1.32	0.75	-1.41
`vn_VALS_reg`	2.14	-0.35	2.38	-0.13
`vn_VFLX_reg`	2.70	0.37	3.18	0.76
`vn_VOLT_reg`	2.22	-0.41	2.28	-0.34
`vn_VULN_reg`	4.47	1.85	4.37	1.74
`vn_WARM_reg`	2.20	-0.41	2.18	-0.44
`genuineness_0_6`	3.87	0.95	3.83	0.92
`blend_0_10`	7.39	0.26	7.28	0.22
`R_quality`	0.61	-1.42	0.61	-1.42
`eiv_extra:Age`	1.75	-5.11	2.09	-3.95
`eiv_extra:Arousal`	1.77	1.11	1.60	0.70
`eiv_extra:Authenticity`	2.71	0.25	2.75	0.53
`eiv_extra:Background_Noise`	0.88	0.29	0.77	-0.16
`eiv_extra:Confident_vs._Hesitant`	2.22	3.91	2.40	4.51
`eiv_extra:Gender`	0.16	0.79	0.36	0.98
`eiv_extra:High-Pitched_vs._Low-Pitched`	1.51	-1.27	1.52	-1.24
`eiv_extra:Monotone_vs._Expressive`	1.70	-0.33	1.71	-0.32
`eiv_extra:Recording_Quality`	1.50	-1.95	1.42	-2.17
`eiv_extra:Serious_vs._Humorous`	0.47	-1.35	0.51	-1.25
`eiv_extra:Soft_vs._Harsh`	1.17	2.77	1.21	2.91
`eiv_extra:Submissive_vs._Dominant`	-0.53	-2.78	-0.52	-2.77
`eiv_extra:Valence`	-0.55	-1.45	-0.64	-1.71
`eiv_extra:Vulnerable_vs._Emotionally_Detached`	0.77	-2.17	0.78	-2.13
`eiv_extra:Warm_vs._Cold`	-0.03	-0.27	-0.08	-0.43
`eiv_extra:score_background_quality`	3.04	-0.38	3.01	-0.43
`eiv_extra:score_content_enjoyment`	3.46	-3.45	3.47	-3.43
`eiv_extra:score_overall_quality`	2.14	-1.02	2.14	-1.02
`eiv_extra:score_speech_quality`	1.59	-1.53	1.65	-1.11
`audiobox:CE`	3.27	-1.50	3.46	-1.32
`audiobox:CU`	5.96	0.31	6.17	0.52
`audiobox:PC`	1.81	-0.32	1.97	-0.23
`audiobox:PQ`	7.34	0.33	7.52	0.54
`dnsmos:SIG_raw`	1.99	-2.86	1.89	-3.00
`dnsmos:BAK_raw`	3.01	-0.18	3.09	-0.10
`dnsmos:OVRL_raw`	1.87	-1.49	1.82	-1.56
`dnsmos:SIG`	2.17	-2.64	2.06	-2.86
`dnsmos:BAK`	3.11	-0.30	3.17	-0.24
`dnsmos:OVRL`	1.90	-1.55	1.86	-1.62
`dnsmos:P808_MOS`	2.67	-1.52	2.64	-1.57
`burst_count_log1p`	1.66	2.57	1.66	2.56
`voiceclap_attribute:Affection`	0.10	-1.53	0.28	-1.20
`voiceclap_attribute:Age`	1.97	-2.30	1.78	-2.65
`voiceclap_attribute:Amusement`	0.04	-0.62	0.19	-0.35
`voiceclap_attribute:Anger`	0.10	-1.77	0.17	-1.63
`voiceclap_attribute:Arousal`	1.59	0.27	1.88	0.74
`voiceclap_attribute:Astonishment_Surprise`	0.18	-0.69	0.16	-0.72
`voiceclap_attribute:Authenticity`	2.94	1.03	2.85	0.50
`voiceclap_attribute:Awe`	0.01	-2.05	-0.13	-2.56
`voiceclap_attribute:Background_Noise`	0.69	0.46	0.76	0.74
`voiceclap_attribute:Bitterness`	0.14	-1.91	0.16	-1.82
`voiceclap_attribute:Concentration`	0.47	-1.40	0.67	-1.03
`voiceclap_attribute:Confident_vs._Hesitant`	1.70	1.35	1.74	1.44
`voiceclap_attribute:Confusion`	0.05	-1.79	0.16	-1.46
`voiceclap_attribute:Contemplation`	0.49	-0.72	0.40	-0.93
`voiceclap_attribute:Contempt`	-0.10	-2.40	0.14	-1.68
`voiceclap_attribute:Contentment`	0.34	-0.80	0.27	-1.04
`voiceclap_attribute:Disappointment`	0.40	-1.24	0.65	-0.36
`voiceclap_attribute:Disgust`	0.03	-2.86	0.20	-2.05
`voiceclap_attribute:Distress`	1.69	2.17	1.84	2.61
`voiceclap_attribute:Doubt`	0.26	-1.48	0.30	-1.23
`voiceclap_attribute:Elation`	-0.00	-1.36	0.10	-1.11
`voiceclap_attribute:Embarrassment`	-0.10	-1.29	-0.08	-1.24
`voiceclap_attribute:Emotional_Numbness`	0.27	-1.48	0.21	-1.71
`voiceclap_attribute:Fatigue_Exhaustion`	1.56	4.20	2.18	6.57
`voiceclap_attribute:Fear`	0.44	-0.84	0.60	-0.06
`voiceclap_attribute:Gender`	0.51	0.66	0.51	0.66
`voiceclap_attribute:Helplessness`	1.28	2.31	1.37	2.67
`voiceclap_attribute:High-Pitched_vs._Low-Pitched`	1.34	-1.33	1.41	-1.15
`voiceclap_attribute:Hope_Enthusiasm_Optimism`	0.08	-1.57	0.17	-1.36
`voiceclap_attribute:Impatience_and_Irritability`	0.26	-1.46	0.60	-0.84
`voiceclap_attribute:Infatuation`	0.05	-1.69	-0.09	-2.10
`voiceclap_attribute:Interest`	0.17	-3.24	0.20	-3.18
`voiceclap_attribute:Intoxication_Altered_States_of_Consciousness`	-0.04	-1.17	0.05	-0.98
`voiceclap_attribute:Jealousy_&_Envy`	-0.02	-2.20	0.06	-1.89
`voiceclap_attribute:Longing`	0.13	-1.84	0.07	-2.11
`voiceclap_attribute:Malevolence_Malice`	0.04	-2.31	0.11	-2.10
`voiceclap_attribute:Monotone_vs._Expressive`	1.68	-0.16	1.85	0.13
`voiceclap_attribute:Pain`	1.00	2.83	0.90	2.38
`voiceclap_attribute:Pleasure_Ecstasy`	0.04	-1.54	0.02	-1.60
`voiceclap_attribute:Pride`	0.03	-2.15	-0.05	-2.38
`voiceclap_attribute:Recording_Quality`	1.74	-1.74	1.70	-1.87
`voiceclap_attribute:Relief`	0.21	-1.95	0.30	-1.74
`voiceclap_attribute:Sadness`	0.66	-0.29	0.64	-0.34
`voiceclap_attribute:Serious_vs._Humorous`	0.62	-0.33	0.77	-0.06
`voiceclap_attribute:Sexual_Lust`	0.04	-1.41	0.02	-1.47
`voiceclap_attribute:Shame`	-0.06	-2.08	-0.01	-1.89
`voiceclap_attribute:Soft_vs._Harsh`	0.87	1.99	0.82	1.83
`voiceclap_attribute:Sourness`	0.10	-2.08	0.23	-1.63
`voiceclap_attribute:Submissive_vs._Dominant`	-0.10	-2.01	0.05	-1.59
`voiceclap_attribute:Teasing`	-0.13	-1.76	0.04	-1.33
`voiceclap_attribute:Thankfulness_Gratitude`	0.18	-2.28	0.26	-2.13
`voiceclap_attribute:Triumph`	-0.13	-2.36	0.05	-1.85
`voiceclap_attribute:Valence`	-0.83	-1.30	-0.96	-1.50
`voiceclap_attribute:Vulnerable_vs._Emotionally_Detached`	0.58	-1.90	0.50	-2.05
`voiceclap_attribute:Warm_vs._Cold`	0.17	0.59	0.01	0.18
`voiceclap_attribute:duration`	8.20	-0.43	9.26	-0.26
`voiceclap_attribute:score_background_quality`	3.07	-0.34	3.32	0.15
`voiceclap_attribute:score_content_enjoyment`	4.37	-1.97	4.39	-1.82
`voiceclap_attribute:score_overall_quality`	2.17	-1.14	2.28	-0.85
`voiceclap_attribute:score_speech_quality`	1.94	0.71	1.90	0.17
`voiceclap_attribute:talking_speed`	0.22	-2.35	2.42	-1.76

← All 50 examples ← Previous Next →