Interactive listening evidence · Base & Medium

Vocal burst 19: Exasperated Sigh, Frustrated Groan, Heavy Breathing +1 more

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 →

19. Exasperated Sigh, Frustrated Groan, Heavy Breathing, Snort

emolia_c0862Xwhimpering__en.c024.k2

vc_sidon · en/synth · 11.50 s · test split

4 Gemini eventsBase count 3.1Medium count 3.1

Source key: emolia_c0862__X__whimpering__en.c024.k2 · Audio SHA256: fc5cac64b84023da0a9232d3d1c9958f20ee8b2a6023de9ae25a8aa47d75d62c

Gemini annotation · selection aid

0.05–1.70 s: Heavy Breathing · group breath_fast
5.48–6.82 s: Exasperated Sigh · group sigh_neg
10.15–10.58 s: Snort · group sniff
10.60–11.45 s: Frustrated Groan · group sigh_neg

Base predictions

20 ms frame probability; dashed line = 0.5 threshold

0.04–1.02 s: Breath 47%, Sharp Inhale 13%, Other / rare burst 9% · onset 0.98
0.10–1.10 s: Breath 54%, Sharp Inhale 12%, Other / rare burst 8% · onset 0.74
0.20–1.14 s: Breath 59%, Sharp Inhale 9%, Other / rare burst 8% · onset 0.73
1.24–2.00 s: Breath 56%, Other / rare burst 16%, Sharp Inhale 7% · onset 0.70
1.36–2.00 s: Breath 58%, Other / rare burst 14%, Sharp Inhale 7% · onset 0.57
1.48–2.00 s: Breath 58%, Other / rare burst 12%, Sharp Inhale 8% · onset 0.72
1.62–2.14 s: Breath 57%, Sharp Inhale 14%, Other / rare burst 7% · onset 0.52
1.72–2.26 s: Breath 51%, Sharp Inhale 18%, Other / rare burst 6% · onset 0.70
5.18–5.98 s: Exasperated Sigh 32%, Breath 19%, Sharp Inhale 10% · onset 0.66
5.24–6.08 s: Exasperated Sigh 30%, Breath 21%, Sharp Inhale 11% · onset 0.72
5.30–6.04 s: Exasperated Sigh 31%, Breath 20%, Sharp Inhale 12% · onset 0.82
5.38–6.14 s: Exasperated Sigh 31%, Breath 21%, Sharp Inhale 12% · onset 0.88
5.48–6.16 s: Exasperated Sigh 30%, Breath 21%, Sharp Inhale 14% · onset 0.97
5.62–6.30 s: Exasperated Sigh 27%, Breath 24%, Sharp Inhale 14% · onset 0.83
5.70–6.38 s: Breath 29%, Exasperated Sigh 25%, Sharp Inhale 12% · onset 0.60
5.86–6.70 s: Breath 30%, Exasperated Sigh 15%, Sharp Inhale 9% · onset 0.74
5.92–6.76 s: Breath 28%, Exasperated Sigh 14%, Sharp Inhale 9% · onset 0.76
5.98–6.84 s: Breath 27%, Exasperated Sigh 12%, Sharp Inhale 8% · onset 0.68
6.06–6.74 s: Breath 27%, Exasperated Sigh 12%, Sharp Inhale 8% · onset 0.60
6.16–6.76 s: Breath 27%, Exasperated Sigh 11%, Sharp Inhale 8% · onset 0.58
6.36–6.86 s: Breath 25%, Sharp Inhale 12%, Exasperated Sigh 8% · onset 0.73
6.44–6.96 s: Breath 20%, Sharp Inhale 16%, Exasperated Sigh 7% · onset 0.78
10.28–10.94 s: Hum 26%, Exasperated Sigh 9%, Displeased Grunt 7% · onset 0.63
10.44–11.02 s: Hum 35%, Displeased Grunt 8%, Exasperated Sigh 7% · onset 0.83
10.62–11.20 s: Hum 62%, Affirmative Grunt 10%, Displeased Grunt 6% · onset 0.80
10.68–11.26 s: Hum 75%, Affirmative Grunt 10%, Displeased Grunt 3% · onset 0.65
10.80–11.32 s: Hum 86%, Affirmative Grunt 8%, Displeased Grunt 1% · onset 0.74
10.86–11.38 s: Hum 91%, Affirmative Grunt 6%, Displeased Grunt 1% · onset 0.72
10.94–11.44 s: Hum 94%, Affirmative Grunt 4%, Displeased Grunt 0% · onset 0.75
11.04–11.50 s: Hum 91%, Affirmative Grunt 7%, Displeased Grunt 0% · onset 0.78
11.12–11.50 s: Hum 90%, Affirmative Grunt 8%, Displeased Grunt 0% · onset 0.51

Frame-positive regions: 4 · CPS 9.13 · Orange timbre cosine 0.910 · identity cosine 0.824

Medium predictions

20 ms frame probability; dashed line = 0.5 threshold

0.04–1.26 s: Breath 64%, Other / rare burst 24%, Sharp Inhale 2% · onset 0.99
0.14–1.56 s: Breath 59%, Other / rare burst 29%, Sharp Inhale 2% · onset 0.58
0.20–1.16 s: Breath 63%, Other / rare burst 23%, Sharp Inhale 2% · onset 0.73
1.50–2.12 s: Breath 68%, Other / rare burst 12%, Sharp Inhale 5% · onset 0.53
1.72–2.28 s: Breath 72%, Sharp Inhale 7%, Other / rare burst 6% · onset 0.53
5.18–6.06 s: Breath 21%, Exasperated Sigh 21%, Sharp Inhale 10% · onset 0.75
5.32–6.40 s: Breath 24%, Exasperated Sigh 18%, Sharp Inhale 8% · onset 0.82
5.38–6.38 s: Breath 25%, Exasperated Sigh 17%, Sharp Inhale 8% · onset 0.78
5.46–6.30 s: Breath 23%, Exasperated Sigh 17%, Sharp Inhale 10% · onset 0.86
5.52–6.42 s: Breath 24%, Exasperated Sigh 16%, Sharp Inhale 10% · onset 0.86
5.62–6.38 s: Breath 24%, Exasperated Sigh 15%, Sharp Inhale 10% · onset 0.83
5.80–6.76 s: Breath 34%, Other / rare burst 9%, Exasperated Sigh 8% · onset 0.50
5.98–6.80 s: Breath 37%, Other / rare burst 10%, Exasperated Sigh 8% · onset 0.66
6.14–6.76 s: Breath 40%, Other / rare burst 10%, Sharp Inhale 6% · onset 0.83
6.20–7.00 s: Breath 42%, Exasperated Sigh 8%, Sharp Inhale 8% · onset 0.61
6.28–6.80 s: Breath 37%, Sharp Inhale 9%, Other / rare burst 8% · onset 0.72
6.36–6.90 s: Breath 36%, Sharp Inhale 11%, Other / rare burst 6% · onset 0.62
6.48–7.02 s: Breath 38%, Sharp Inhale 15%, Exasperated Sigh 7% · onset 0.65
10.12–11.08 s: Hum 38%, Snort 6%, Breath 5% · onset 0.64
10.28–11.30 s: Hum 77%, Affirmative Grunt 6%, Low Mumble 3% · onset 0.63
10.40–11.44 s: Hum 88%, Affirmative Grunt 3%, Exhausted Groan 1% · onset 0.70
10.46–11.44 s: Hum 90%, Affirmative Grunt 3%, Exhausted Groan 1% · onset 0.74
10.54–11.50 s: Hum 90%, Affirmative Grunt 4%, Exhausted Groan 1% · onset 0.74
10.64–11.50 s: Hum 91%, Affirmative Grunt 4%, Exhausted Groan 1% · onset 0.78
10.76–11.50 s: Hum 92%, Affirmative Grunt 4%, Other / rare burst 0% · onset 0.79
10.82–11.50 s: Hum 93%, Affirmative Grunt 3%, Other / rare burst 0% · onset 0.78
10.90–11.50 s: Hum 91%, Affirmative Grunt 4%, Other / rare burst 1% · onset 0.74
10.98–11.50 s: Hum 91%, Affirmative Grunt 4%, Other / rare burst 1% · onset 0.83
11.10–11.50 s: Hum 92%, Affirmative Grunt 3%, Other / rare burst 1% · onset 0.87

Frame-positive regions: 3 · CPS 9.01 · Orange timbre cosine 0.939 · identity cosine 0.845

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

Target	Base raw	Base z	Medium raw	Medium z
`emo_Affection`	0.04	0.05	0.08	0.13
`emo_Amusement`	0.07	0.08	0.08	0.09
`emo_Anger`	0.10	0.16	0.14	0.22
`emo_Astonishment_Surprise`	0.11	0.19	0.03	0.03
`emo_Awe`	0.04	0.10	0.02	0.05
`emo_Bitterness`	0.27	0.61	0.23	0.51
`emo_Concentration`	2.17	2.07	2.04	1.90
`emo_Confusion`	0.29	0.53	0.15	0.27
`emo_Contemplation`	2.03	3.26	1.96	3.14
`emo_Contempt`	0.10	0.21	0.12	0.26
`emo_Contentment`	0.36	0.71	0.37	0.73
`emo_Disappointment`	1.19	1.70	0.89	1.28
`emo_Disgust`	0.08	0.15	0.10	0.19
`emo_Distress`	1.84	2.25	1.17	1.42
`emo_Doubt`	1.25	2.67	0.89	1.90
`emo_Elation`	-0.02	-0.05	-0.03	-0.06
`emo_Embarrassment`	0.01	-0.08	0.01	-0.07
`emo_Emotional_Numbness`	0.51	0.55	0.37	0.40
`emo_Fatigue_Exhaustion`	2.65	4.87	2.61	4.80
`emo_Fear`	0.21	0.32	0.08	0.11
`emo_Helplessness`	1.78	2.56	1.29	1.86
`emo_Hope_Enthusiasm_Optimism`	0.29	0.23	0.26	0.18
`emo_Impatience_and_Irritability`	1.02	1.23	0.86	1.00
`emo_Infatuation`	-0.04	-0.04	-0.00	0.02
`emo_Interest`	1.30	-0.31	1.42	-0.18
`emo_Intoxication_Altered_States_of_Consciousness`	0.02	0.08	0.03	0.10
`emo_Jealousy_and_Envy`	-0.02	-0.17	-0.02	-0.18
`emo_Longing`	0.63	0.86	0.53	0.70
`emo_Malevolence_Malice`	0.03	-0.06	0.01	-0.09
`emo_Pain`	0.32	0.56	0.22	0.39
`emo_Pleasure_Ecstasy`	0.00	-0.03	0.01	-0.01
`emo_Pride`	0.18	0.34	0.09	0.17
`emo_Relief`	0.06	0.04	0.06	0.04
`emo_Sadness`	1.01	1.34	0.74	0.97
`emo_Sexual_Lust`	-0.03	-0.12	0.01	-0.03
`emo_Shame`	0.06	0.09	0.02	0.01
`emo_Sourness`	0.32	0.73	0.28	0.64
`emo_Teasing`	0.04	0.07	0.03	0.05
`emo_Thankfulness_Gratitude`	0.02	-0.03	-0.02	-0.09
`emo_Triumph`	0.00	0.02	0.00	0.02
`vn_AGEV_reg`	3.06	0.06	3.49	0.41
`vn_AROU_reg`	1.98	-0.33	1.93	-0.37
`vn_ARSH_reg`	2.82	0.27	2.48	-0.11
`vn_ATCK_reg`	2.67	0.40	2.52	0.28
`vn_BKGN_reg`	3.99	1.70	3.98	1.68
`vn_BRGT_reg`	3.02	1.27	2.82	1.02
`vn_CHNK_reg`	2.19	0.27	2.21	0.29
`vn_CLRT_reg`	3.74	1.82	4.00	2.09
`vn_COGL_reg`	1.85	-0.23	1.83	-0.24
`vn_DARC_reg`	2.91	0.93	2.99	1.00
`vn_DFLU_reg`	1.33	-0.98	1.17	-1.11
`vn_EMPH_reg`	3.05	0.29	2.90	0.19
`vn_ESTH_reg`	3.27	1.12	3.34	1.20
`vn_EXPL_reg`	0.03	-0.18	0.02	-0.21
`vn_FOCS_reg`	3.76	1.28	3.72	1.25
`vn_FULL_reg`	3.30	1.71	3.38	1.80
`vn_GEND_reg`	4.93	0.55	4.76	0.45
`vn_HARM_reg`	2.98	0.60	3.17	0.82
`vn_METL_reg`	1.42	-0.21	1.38	-0.25
`vn_RANG_reg`	2.07	-0.94	2.02	-1.00
`vn_RCQL_reg`	3.78	1.15	3.88	1.26
`vn_REGS_reg`	1.17	-0.02	1.53	0.26
`vn_RESP_reg`	3.16	0.45	3.17	0.46
`vn_ROUG_reg`	2.57	0.61	2.37	0.38
`vn_R_CHST_reg`	3.59	1.72	3.59	1.72
`vn_R_HEAD_reg`	1.29	-1.05	1.51	-0.78
`vn_R_MASK_reg`	2.34	0.43	2.35	0.44
`vn_R_MIXD_reg`	3.38	2.31	3.39	2.32
`vn_R_NASL_reg`	1.44	-1.29	1.65	-1.09
`vn_R_ORAL_reg`	3.59	1.90	3.32	1.54
`vn_R_THRT_reg`	3.00	1.16	2.87	0.99
`vn_SMTH_reg`	2.98	0.77	3.21	0.98
`vn_STNC_reg`	2.91	0.25	2.67	0.03
`vn_STRU_reg`	3.55	1.47	3.65	1.58
`vn_S_ASMR_reg`	1.00	-0.26	1.33	-0.03
`vn_S_AUTH_reg`	2.35	1.21	2.23	1.09
`vn_S_CART_reg`	0.54	-0.73	-0.04	-1.14
`vn_S_CASU_reg`	3.25	-0.43	2.92	-0.68
`vn_S_CONV_reg`	3.50	0.69	3.40	0.61
`vn_S_DRAM_reg`	2.45	-0.23	2.14	-0.51
`vn_S_FORM_reg`	1.50	0.30	1.93	0.72
`vn_S_MONO_reg`	2.75	-0.05	2.79	-0.03
`vn_S_NARR_reg`	2.35	0.72	2.18	0.60
`vn_S_NEWS_reg`	0.53	0.21	0.56	0.28
`vn_S_PLAY_reg`	0.70	-1.25	0.62	-1.31
`vn_S_RANT_reg`	0.59	-0.48	0.50	-0.56
`vn_S_STRY_reg`	1.82	-0.48	1.44	-0.76
`vn_S_TECH_reg`	1.94	1.05	1.80	0.94
`vn_S_WHIS_reg`	0.92	-0.42	1.04	-0.34
`vn_TEMP_reg`	2.27	0.13	2.29	0.14
`vn_TENS_reg`	2.54	1.15	2.28	0.85
`vn_VALN_reg`	1.97	-0.32	2.23	-0.09
`vn_VALS_reg`	2.66	0.13	2.53	0.01
`vn_VFLX_reg`	2.93	0.56	3.15	0.74
`vn_VOLT_reg`	1.78	-0.92	1.53	-1.19
`vn_VULN_reg`	2.37	-0.28	2.22	-0.43
`vn_WARM_reg`	3.29	0.79	3.24	0.73
`genuineness_0_6`	4.37	1.26	4.63	1.42
`blend_0_10`	6.59	-0.03	7.14	0.17
`R_quality`	0.47	-1.84	0.59	-1.49
`eiv_extra:Age`	3.23	-0.06	3.32	0.25
`eiv_extra:Arousal`	1.36	0.16	1.06	-0.52
`eiv_extra:Authenticity`	3.02	2.31	3.03	2.35
`eiv_extra:Background_Noise`	0.33	-1.80	0.32	-1.86
`eiv_extra:Confident_vs._Hesitant`	1.53	1.63	1.29	0.82
`eiv_extra:Gender`	-0.43	0.19	-0.15	0.48
`eiv_extra:High-Pitched_vs._Low-Pitched`	1.79	-0.14	1.69	-0.54
`eiv_extra:Monotone_vs._Expressive`	1.86	0.01	1.53	-0.71
`eiv_extra:Recording_Quality`	2.53	1.17	2.57	1.30
`eiv_extra:Serious_vs._Humorous`	0.79	-0.40	0.74	-0.54
`eiv_extra:Soft_vs._Harsh`	0.56	0.88	0.57	0.91
`eiv_extra:Submissive_vs._Dominant`	0.33	-0.13	0.31	-0.20
`eiv_extra:Valence`	-0.32	-0.84	-0.12	-0.32
`eiv_extra:Vulnerable_vs._Emotionally_Detached`	1.35	-0.83	1.29	-0.97
`eiv_extra:Warm_vs._Cold`	-0.01	-0.19	0.07	0.05
`eiv_extra:score_background_quality`	3.96	0.95	3.90	0.86
`eiv_extra:score_content_enjoyment`	4.75	0.79	4.81	1.01
`eiv_extra:score_overall_quality`	3.18	1.04	3.15	0.98
`eiv_extra:score_speech_quality`	1.80	-0.07	1.91	0.73
`audiobox:CE`	6.01	1.19	6.10	1.28
`audiobox:CU`	7.24	1.59	7.43	1.78
`audiobox:PC`	1.60	-0.45	1.57	-0.47
`audiobox:PQ`	8.07	1.17	8.16	1.27
`dnsmos:SIG_raw`	4.13	0.35	4.15	0.38
`dnsmos:BAK_raw`	4.48	1.13	4.49	1.14
`dnsmos:OVRL_raw`	3.95	1.07	3.96	1.08
`dnsmos:SIG`	3.61	0.24	3.62	0.27
`dnsmos:BAK`	4.18	0.85	4.18	0.86
`dnsmos:OVRL`	3.40	0.92	3.39	0.91
`dnsmos:P808_MOS`	4.03	1.23	4.03	1.22
`burst_count_log1p`	1.42	2.20	1.41	2.17
`voiceclap_attribute:Affection`	-0.22	-2.11	-0.15	-1.97
`voiceclap_attribute:Age`	3.24	0.03	3.17	-0.10
`voiceclap_attribute:Amusement`	0.00	-0.68	-0.13	-0.91
`voiceclap_attribute:Anger`	0.47	-1.04	0.29	-1.39
`voiceclap_attribute:Arousal`	1.45	0.05	1.02	-0.64
`voiceclap_attribute:Astonishment_Surprise`	-0.02	-1.11	-0.08	-1.23
`voiceclap_attribute:Authenticity`	2.93	0.95	2.95	1.08
`voiceclap_attribute:Awe`	-0.09	-2.42	0.10	-1.69
`voiceclap_attribute:Background_Noise`	0.38	-0.72	0.36	-0.77
`voiceclap_attribute:Bitterness`	0.42	-0.74	0.34	-1.06
`voiceclap_attribute:Concentration`	1.88	1.25	1.99	1.46
`voiceclap_attribute:Confident_vs._Hesitant`	1.18	0.24	1.22	0.32
`voiceclap_attribute:Confusion`	0.30	-1.02	0.30	-1.04
`voiceclap_attribute:Contemplation`	1.94	2.85	2.19	3.48
`voiceclap_attribute:Contempt`	0.27	-1.30	0.19	-1.54
`voiceclap_attribute:Contentment`	0.69	0.32	0.84	0.81
`voiceclap_attribute:Disappointment`	0.77	0.03	0.71	-0.18
`voiceclap_attribute:Disgust`	0.18	-2.16	0.10	-2.55
`voiceclap_attribute:Distress`	0.97	0.12	0.80	-0.36
`voiceclap_attribute:Doubt`	0.90	1.93	0.90	1.94
`voiceclap_attribute:Elation`	-0.35	-2.24	-0.19	-1.83
`voiceclap_attribute:Embarrassment`	-0.09	-1.26	0.00	-0.97
`voiceclap_attribute:Emotional_Numbness`	0.11	-2.09	0.15	-1.92
`voiceclap_attribute:Fatigue_Exhaustion`	1.27	3.09	1.72	4.82
`voiceclap_attribute:Fear`	0.14	-2.24	0.03	-2.79
`voiceclap_attribute:Gender`	-0.34	-0.19	-0.26	-0.10
`voiceclap_attribute:Helplessness`	0.79	0.48	0.83	0.65
`voiceclap_attribute:High-Pitched_vs._Low-Pitched`	1.54	-0.80	1.65	-0.51
`voiceclap_attribute:Hope_Enthusiasm_Optimism`	0.07	-1.60	0.24	-1.17
`voiceclap_attribute:Impatience_and_Irritability`	0.83	-0.41	0.66	-0.72
`voiceclap_attribute:Infatuation`	-0.14	-2.24	-0.21	-2.46
`voiceclap_attribute:Interest`	1.21	-0.89	1.20	-0.91
`voiceclap_attribute:Intoxication_Altered_States_of_Consciousness`	0.03	-1.01	-0.10	-1.30
`voiceclap_attribute:Jealousy_&_Envy`	0.01	-2.09	-0.11	-2.60
`voiceclap_attribute:Longing`	0.06	-2.17	0.16	-1.71
`voiceclap_attribute:Malevolence_Malice`	0.13	-2.03	0.04	-2.29
`voiceclap_attribute:Monotone_vs._Expressive`	1.49	-0.48	1.54	-0.40
`voiceclap_attribute:Pain`	0.31	-0.35	0.28	-0.48
`voiceclap_attribute:Pleasure_Ecstasy`	-0.23	-2.44	-0.15	-2.16
`voiceclap_attribute:Pride`	0.01	-2.21	0.02	-2.18
`voiceclap_attribute:Recording_Quality`	2.51	0.61	2.56	0.75
`voiceclap_attribute:Relief`	-0.07	-2.64	0.19	-2.01
`voiceclap_attribute:Sadness`	0.44	-1.00	0.53	-0.72
`voiceclap_attribute:Serious_vs._Humorous`	0.77	-0.06	0.77	-0.07
`voiceclap_attribute:Sexual_Lust`	-0.06	-1.65	-0.10	-1.76
`voiceclap_attribute:Shame`	-0.03	-1.95	-0.04	-1.98
`voiceclap_attribute:Soft_vs._Harsh`	0.20	0.13	0.48	0.88
`voiceclap_attribute:Sourness`	0.51	-0.69	0.48	-0.77
`voiceclap_attribute:Submissive_vs._Dominant`	0.45	-0.50	0.28	-0.97
`voiceclap_attribute:Teasing`	0.12	-1.12	-0.04	-1.54
`voiceclap_attribute:Thankfulness_Gratitude`	-0.11	-2.83	-0.12	-2.84
`voiceclap_attribute:Triumph`	-0.29	-2.81	-0.12	-2.31
`voiceclap_attribute:Valence`	-0.74	-1.16	-0.30	-0.47
`voiceclap_attribute:Vulnerable_vs._Emotionally_Detached`	1.53	-0.20	1.53	-0.20
`voiceclap_attribute:Warm_vs._Cold`	-0.21	-0.37	0.11	0.45
`voiceclap_attribute:duration`	11.49	0.09	10.13	-0.12
`voiceclap_attribute:score_background_quality`	3.76	1.03	3.65	0.81
`voiceclap_attribute:score_content_enjoyment`	4.79	0.93	4.70	0.28
`voiceclap_attribute:score_overall_quality`	3.03	0.95	2.93	0.70
`voiceclap_attribute:score_speech_quality`	1.90	0.14	1.90	0.17
`voiceclap_attribute:talking_speed`	9.16	0.03	8.56	-0.13

← All 50 examples ← Previous Next →