Interactive listening evidence · Base & Medium

Vocal burst 08: Yawn

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 →

08. Yawn

k562_age4_bg1ETriumphCde.c010

vprof_original · de/synth · 10.64 s · validation split

1 Gemini eventsBase count 1.6Medium count 1.9

Source key: k562_age4_bg1__E__Triumph__C__de.c010 · Audio SHA256: 13efc6e575767bf0b5e9e88fa16f7f8ba087681999794945fd58ba24a4e10e9f

Gemini annotation · selection aid

0.00–1.25 s: Yawn · group yawn

Base predictions

20 ms frame probability; dashed line = 0.5 threshold

0.00–0.80 s: Frustrated Groan 40%, Exhausted Groan 23%, Other / rare burst 13% · onset 0.99
0.10–0.80 s: Frustrated Groan 38%, Exhausted Groan 24%, Other / rare burst 13% · onset 0.52
0.46–1.00 s: Frustrated Groan 32%, Other / rare burst 19%, Exhausted Groan 16% · onset 0.60
0.54–1.08 s: Frustrated Groan 24%, Other / rare burst 20%, Exhausted Groan 14% · onset 0.65
0.62–1.06 s: Frustrated Groan 22%, Other / rare burst 16%, Exhausted Groan 11% · onset 0.67
0.70–1.22 s: Other / rare burst 17%, Frustrated Groan 16%, Exhausted Groan 12% · onset 0.69
1.10–1.46 s: Exasperated Sigh 34%, Sharp Inhale 21%, Breath 14% · onset 0.67
1.24–1.54 s: Exasperated Sigh 30%, Sharp Inhale 28%, Breath 12% · onset 0.61
1.48–1.76 s: Exasperated Sigh 23%, Sharp Inhale 17%, Relief Sigh 6% · onset 0.68
5.42–5.84 s: Sharp Inhale 66%, Chuckle 7%, Breath 6% · onset 0.63
5.48–5.88 s: Sharp Inhale 68%, Chuckle 7%, Breath 4% · onset 0.55
7.48–8.02 s: Sharp Inhale 50%, Exasperated Sigh 15%, Breath 11% · onset 0.81
7.54–8.06 s: Sharp Inhale 54%, Exasperated Sigh 14%, Breath 11% · onset 0.73
7.60–8.12 s: Sharp Inhale 56%, Exasperated Sigh 13%, Breath 12% · onset 0.73

Frame-positive regions: 2 · CPS 17.09 · Orange timbre cosine 0.922 · identity cosine 0.943

Medium predictions

20 ms frame probability; dashed line = 0.5 threshold

0.04–0.88 s: Yawn 23%, Frustrated Groan 20%, Exhausted Groan 19% · onset 0.99
0.56–1.08 s: Exhausted Groan 18%, Other / rare burst 14%, Frustrated Groan 14% · onset 0.52
0.62–1.14 s: Exhausted Groan 18%, Other / rare burst 13%, Frustrated Groan 11% · onset 0.56
0.70–1.20 s: Exhausted Groan 19%, Other / rare burst 12%, Exasperated Sigh 9% · onset 0.62
1.22–1.64 s: Breath 19%, Sharp Inhale 18%, Exasperated Sigh 9% · onset 0.55
1.36–1.76 s: Sharp Inhale 14%, Exasperated Sigh 10%, Breath 10% · onset 0.52
7.48–7.90 s: Sharp Inhale 43%, Breath 17%, Exasperated Sigh 10% · onset 0.77
7.58–7.96 s: Sharp Inhale 56%, Breath 17%, Exasperated Sigh 6% · onset 0.59
7.64–8.10 s: Sharp Inhale 66%, Breath 14%, Exasperated Sigh 3% · onset 0.51
7.78–8.20 s: Sharp Inhale 41%, Breath 21%, Exasperated Sigh 9% · onset 0.63

Frame-positive regions: 4 · CPS 16.66 · Orange timbre cosine 0.936 · identity cosine 0.948

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

Target	Base raw	Base z	Medium raw	Medium z
`emo_Affection`	0.11	0.17	0.22	0.37
`emo_Amusement`	0.33	0.37	0.77	0.87
`emo_Anger`	0.03	0.05	0.05	0.08
`emo_Astonishment_Surprise`	0.11	0.18	0.36	0.61
`emo_Awe`	0.10	0.24	0.11	0.25
`emo_Bitterness`	0.13	0.28	0.12	0.26
`emo_Concentration`	2.27	2.20	1.66	1.39
`emo_Confusion`	0.13	0.24	0.04	0.07
`emo_Contemplation`	1.76	2.80	1.15	1.79
`emo_Contempt`	0.06	0.13	0.09	0.20
`emo_Contentment`	1.48	2.88	1.87	3.63
`emo_Disappointment`	0.36	0.52	0.15	0.21
`emo_Disgust`	0.02	0.03	0.07	0.14
`emo_Distress`	0.52	0.63	0.20	0.25
`emo_Doubt`	0.42	0.90	0.21	0.43
`emo_Elation`	0.08	0.10	0.41	0.55
`emo_Embarrassment`	-0.04	-0.19	0.02	-0.04
`emo_Emotional_Numbness`	0.21	0.22	0.16	0.17
`emo_Fatigue_Exhaustion`	1.19	2.16	0.90	1.62
`emo_Fear`	0.03	0.03	0.01	-0.01
`emo_Helplessness`	0.24	0.35	0.15	0.22
`emo_Hope_Enthusiasm_Optimism`	1.26	1.51	1.69	2.07
`emo_Impatience_and_Irritability`	0.36	0.29	0.31	0.22
`emo_Infatuation`	-0.06	-0.08	-0.02	-0.02
`emo_Interest`	2.23	0.71	2.36	0.85
`emo_Intoxication_Altered_States_of_Consciousness`	0.07	0.16	0.03	0.10
`emo_Jealousy_and_Envy`	-0.00	-0.14	-0.01	-0.15
`emo_Longing`	0.04	-0.08	0.05	-0.07
`emo_Malevolence_Malice`	0.02	-0.06	0.02	-0.06
`emo_Pain`	0.06	0.11	0.04	0.07
`emo_Pleasure_Ecstasy`	0.05	0.06	0.11	0.15
`emo_Pride`	0.43	0.85	0.60	1.17
`emo_Relief`	0.89	1.26	1.01	1.43
`emo_Sadness`	0.15	0.20	0.16	0.21
`emo_Sexual_Lust`	0.02	-0.02	0.01	-0.04
`emo_Shame`	0.01	-0.00	0.02	0.02
`emo_Sourness`	0.16	0.37	0.11	0.27
`emo_Teasing`	0.10	0.18	0.16	0.29
`emo_Thankfulness_Gratitude`	0.07	0.05	0.15	0.16
`emo_Triumph`	0.16	0.31	0.23	0.46
`vn_AGEV_reg`	2.93	-0.04	2.93	-0.04
`vn_AROU_reg`	2.78	0.37	2.82	0.40
`vn_ARSH_reg`	2.68	0.11	2.72	0.16
`vn_ATCK_reg`	2.89	0.56	2.82	0.51
`vn_BKGN_reg`	4.02	1.73	3.80	1.44
`vn_BRGT_reg`	3.30	1.61	3.44	1.78
`vn_CHNK_reg`	3.21	1.10	3.45	1.29
`vn_CLRT_reg`	4.33	2.44	4.31	2.43
`vn_COGL_reg`	1.41	-0.65	1.11	-0.93
`vn_DARC_reg`	3.07	1.05	3.09	1.07
`vn_DFLU_reg`	0.75	-1.47	0.66	-1.54
`vn_EMPH_reg`	3.49	0.58	3.54	0.61
`vn_ESTH_reg`	4.06	2.13	4.16	2.25
`vn_EXPL_reg`	-0.05	-0.43	-0.02	-0.33
`vn_FOCS_reg`	4.06	1.56	3.98	1.48
`vn_FULL_reg`	3.26	1.66	3.27	1.68
`vn_GEND_reg`	4.54	0.31	3.97	-0.05
`vn_HARM_reg`	3.62	1.36	3.71	1.47
`vn_METL_reg`	1.52	-0.10	1.50	-0.12
`vn_RANG_reg`	3.27	0.39	3.46	0.61
`vn_RCQL_reg`	3.95	1.34	4.16	1.58
`vn_REGS_reg`	1.95	0.59	2.09	0.70
`vn_RESP_reg`	2.38	-0.29	2.57	-0.11
`vn_ROUG_reg`	1.56	-0.53	1.45	-0.66
`vn_R_CHST_reg`	3.06	1.09	2.80	0.79
`vn_R_HEAD_reg`	2.37	0.27	2.59	0.54
`vn_R_MASK_reg`	2.99	1.08	3.18	1.26
`vn_R_MIXD_reg`	3.86	2.88	3.91	2.95
`vn_R_NASL_reg`	1.50	-1.24	1.55	-1.18
`vn_R_ORAL_reg`	3.43	1.68	3.51	1.79
`vn_R_THRT_reg`	2.45	0.47	2.30	0.29
`vn_SMTH_reg`	3.96	1.66	4.08	1.77
`vn_STNC_reg`	3.53	0.79	3.44	0.71
`vn_STRU_reg`	4.16	2.11	4.16	2.11
`vn_S_ASMR_reg`	0.21	-0.82	0.50	-0.61
`vn_S_AUTH_reg`	2.70	1.55	2.58	1.43
`vn_S_CART_reg`	0.71	-0.61	0.86	-0.50
`vn_S_CASU_reg`	3.04	-0.59	3.46	-0.26
`vn_S_CONV_reg`	3.61	0.77	3.77	0.89
`vn_S_DRAM_reg`	2.29	-0.38	2.34	-0.33
`vn_S_FORM_reg`	2.06	0.85	1.98	0.77
`vn_S_MONO_reg`	2.40	-0.33	2.39	-0.34
`vn_S_NARR_reg`	3.63	1.61	3.56	1.56
`vn_S_NEWS_reg`	0.92	0.90	0.94	0.94
`vn_S_PLAY_reg`	2.17	-0.14	2.29	-0.05
`vn_S_RANT_reg`	0.63	-0.45	0.51	-0.55
`vn_S_STRY_reg`	2.48	0.00	2.60	0.09
`vn_S_TECH_reg`	2.60	1.59	2.23	1.29
`vn_S_WHIS_reg`	0.27	-0.82	0.35	-0.77
`vn_TEMP_reg`	3.43	1.10	3.63	1.27
`vn_TENS_reg`	2.43	1.02	2.35	0.93
`vn_VALN_reg`	3.16	0.74	3.42	0.98
`vn_VALS_reg`	2.84	0.30	2.90	0.35
`vn_VFLX_reg`	2.90	0.53	2.98	0.60
`vn_VOLT_reg`	1.86	-0.82	1.99	-0.68
`vn_VULN_reg`	1.88	-0.78	1.88	-0.78
`vn_WARM_reg`	3.40	0.91	3.28	0.77
`genuineness_0_6`	4.46	1.31	4.32	1.23
`blend_0_10`	7.54	0.32	7.45	0.28
`R_quality`	0.60	-1.45	0.59	-1.51
`eiv_extra:Age`	3.31	0.21	3.38	0.44
`eiv_extra:Arousal`	1.94	1.49	1.96	1.55
`eiv_extra:Authenticity`	3.12	2.96	3.12	2.93
`eiv_extra:Background_Noise`	0.27	-2.02	0.31	-1.88
`eiv_extra:Confident_vs._Hesitant`	0.97	-0.22	0.90	-0.45
`eiv_extra:Gender`	0.16	0.79	0.19	0.81
`eiv_extra:High-Pitched_vs._Low-Pitched`	1.29	-2.16	1.36	-1.86
`eiv_extra:Monotone_vs._Expressive`	1.67	-0.41	1.70	-0.34
`eiv_extra:Recording_Quality`	2.64	1.49	2.67	1.58
`eiv_extra:Serious_vs._Humorous`	0.83	-0.29	1.00	0.20
`eiv_extra:Soft_vs._Harsh`	0.15	-0.40	0.23	-0.14
`eiv_extra:Submissive_vs._Dominant`	0.34	-0.11	0.34	-0.12
`eiv_extra:Valence`	0.26	0.68	0.39	1.00
`eiv_extra:Vulnerable_vs._Emotionally_Detached`	1.17	-1.25	1.24	-1.07
`eiv_extra:Warm_vs._Cold`	-0.03	-0.26	0.09	0.13
`eiv_extra:score_background_quality`	3.84	0.78	3.78	0.69
`eiv_extra:score_content_enjoyment`	5.02	1.69	5.00	1.62
`eiv_extra:score_overall_quality`	3.17	1.02	3.15	0.99
`eiv_extra:score_speech_quality`	1.98	1.15	2.01	1.36
`audiobox:CE`	6.44	1.62	6.43	1.60
`audiobox:CU`	6.98	1.33	7.09	1.44
`audiobox:PC`	1.45	-0.54	1.61	-0.45
`audiobox:PQ`	7.95	1.03	7.98	1.07
`dnsmos:SIG_raw`	4.23	0.50	4.29	0.58
`dnsmos:BAK_raw`	4.48	1.13	4.60	1.23
`dnsmos:OVRL_raw`	4.04	1.17	4.12	1.27
`dnsmos:SIG`	3.67	0.37	3.70	0.42
`dnsmos:BAK`	4.19	0.86	4.23	0.91
`dnsmos:OVRL`	3.45	1.00	3.50	1.08
`dnsmos:P808_MOS`	3.88	0.93	3.94	1.05
`burst_count_log1p`	0.97	1.50	1.06	1.64
`voiceclap_attribute:Affection`	0.13	-1.48	0.29	-1.18
`voiceclap_attribute:Age`	3.30	0.13	3.37	0.27
`voiceclap_attribute:Amusement`	0.55	0.27	0.76	0.64
`voiceclap_attribute:Anger`	0.06	-1.84	-0.19	-2.33
`voiceclap_attribute:Arousal`	1.85	0.69	1.91	0.79
`voiceclap_attribute:Astonishment_Surprise`	0.50	-0.02	0.61	0.21
`voiceclap_attribute:Authenticity`	3.03	1.58	3.01	1.42
`voiceclap_attribute:Awe`	0.13	-1.59	0.26	-1.09
`voiceclap_attribute:Background_Noise`	0.38	-0.72	0.47	-0.38
`voiceclap_attribute:Bitterness`	0.04	-2.35	-0.16	-3.18
`voiceclap_attribute:Concentration`	1.96	1.41	2.06	1.60
`voiceclap_attribute:Confident_vs._Hesitant`	1.49	0.90	1.34	0.57
`voiceclap_attribute:Confusion`	0.25	-1.18	0.10	-1.62
`voiceclap_attribute:Contemplation`	1.84	2.60	1.65	2.13
`voiceclap_attribute:Contempt`	-0.07	-2.30	-0.18	-2.62
`voiceclap_attribute:Contentment`	1.35	2.49	1.57	3.19
`voiceclap_attribute:Disappointment`	0.27	-1.67	0.17	-2.04
`voiceclap_attribute:Disgust`	-0.01	-3.04	-0.09	-3.44
`voiceclap_attribute:Distress`	0.35	-1.66	0.24	-1.96
`voiceclap_attribute:Doubt`	0.57	0.21	0.40	-0.74
`voiceclap_attribute:Elation`	0.12	-1.05	0.33	-0.53
`voiceclap_attribute:Embarrassment`	-0.01	-1.01	-0.02	-1.04
`voiceclap_attribute:Emotional_Numbness`	-0.11	-2.90	-0.03	-2.62
`voiceclap_attribute:Fatigue_Exhaustion`	0.56	0.39	0.45	-0.03
`voiceclap_attribute:Fear`	0.09	-2.48	-0.03	-3.05
`voiceclap_attribute:Gender`	0.04	0.19	-0.00	0.15
`voiceclap_attribute:Helplessness`	0.36	-1.12	0.22	-1.64
`voiceclap_attribute:High-Pitched_vs._Low-Pitched`	1.50	-0.90	1.63	-0.56
`voiceclap_attribute:Hope_Enthusiasm_Optimism`	1.03	0.83	1.29	1.48
`voiceclap_attribute:Impatience_and_Irritability`	0.30	-1.39	0.21	-1.55
`voiceclap_attribute:Infatuation`	-0.08	-2.09	-0.09	-2.10
`voiceclap_attribute:Interest`	2.20	1.36	2.46	1.97
`voiceclap_attribute:Intoxication_Altered_States_of_Consciousness`	-0.10	-1.30	-0.02	-1.13
`voiceclap_attribute:Jealousy_&_Envy`	-0.08	-2.45	-0.07	-2.44
`voiceclap_attribute:Longing`	0.05	-2.21	0.14	-1.80
`voiceclap_attribute:Malevolence_Malice`	-0.11	-2.73	-0.27	-3.20
`voiceclap_attribute:Monotone_vs._Expressive`	2.10	0.55	2.19	0.71
`voiceclap_attribute:Pain`	0.12	-1.20	0.06	-1.45
`voiceclap_attribute:Pleasure_Ecstasy`	-0.09	-1.96	0.04	-1.53
`voiceclap_attribute:Pride`	0.40	-1.09	0.52	-0.74
`voiceclap_attribute:Recording_Quality`	2.54	0.68	2.61	0.91
`voiceclap_attribute:Relief`	0.36	-1.61	0.44	-1.41
`voiceclap_attribute:Sadness`	0.01	-2.36	-0.05	-2.57
`voiceclap_attribute:Serious_vs._Humorous`	0.94	0.24	1.05	0.43
`voiceclap_attribute:Sexual_Lust`	-0.08	-1.71	-0.07	-1.69
`voiceclap_attribute:Shame`	-0.12	-2.30	-0.12	-2.30
`voiceclap_attribute:Soft_vs._Harsh`	0.25	0.25	0.16	0.01
`voiceclap_attribute:Sourness`	0.06	-2.22	-0.03	-2.55
`voiceclap_attribute:Submissive_vs._Dominant`	0.50	-0.34	0.59	-0.10
`voiceclap_attribute:Teasing`	0.26	-0.73	0.26	-0.74
`voiceclap_attribute:Thankfulness_Gratitude`	0.04	-2.55	0.08	-2.47
`voiceclap_attribute:Triumph`	0.02	-1.95	0.18	-1.49
`voiceclap_attribute:Valence`	-0.10	-0.15	-0.04	-0.06
`voiceclap_attribute:Vulnerable_vs._Emotionally_Detached`	1.35	-0.51	1.42	-0.38
`voiceclap_attribute:Warm_vs._Cold`	-0.01	0.14	0.04	0.27
`voiceclap_attribute:duration`	9.73	-0.19	11.52	0.10
`voiceclap_attribute:score_background_quality`	3.78	1.07	3.70	0.91
`voiceclap_attribute:score_content_enjoyment`	4.91	1.73	4.93	1.89
`voiceclap_attribute:score_overall_quality`	3.14	1.24	3.14	1.21
`voiceclap_attribute:score_speech_quality`	1.93	0.53	1.88	-0.09
`voiceclap_attribute:talking_speed`	16.02	1.86	15.87	1.82

← All 50 examples ← Previous Next →