Interactive listening evidence · Base & Medium

Vocal burst 48: 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 →

48. Yawn

mediathek_0243VS_CASU__moderately_high__de.c001

vprof_original · de/synth · 12.72 s · test split

1 Gemini eventsBase count 1.3Medium count 1.1

Source key: mediathek_0243__V__S_CASU__moderately_high__de.c001 · Audio SHA256: 780dc03c43dc1f051204b4b062ec68fd57c4557ddca79c33c96bfc2c5feab283

Gemini annotation · selection aid

10.45–12.38 s: Yawn · group yawn

Base predictions

20 ms frame probability; dashed line = 0.5 threshold

10.12–11.74 s: Exhausted Groan 32%, Yawn 28%, Frustrated Groan 7% · onset 0.71
10.28–11.66 s: Exhausted Groan 33%, Yawn 24%, Frustrated Groan 7% · onset 0.75
10.44–11.92 s: Yawn 38%, Exhausted Groan 31%, Frustrated Groan 9% · onset 0.80
10.52–11.94 s: Yawn 40%, Exhausted Groan 31%, Frustrated Groan 9% · onset 0.61
10.62–12.14 s: Yawn 46%, Exhausted Groan 25%, Frustrated Groan 11% · onset 0.65
10.68–12.30 s: Yawn 51%, Exhausted Groan 20%, Frustrated Groan 13% · onset 0.67
10.74–12.22 s: Yawn 49%, Exhausted Groan 20%, Frustrated Groan 14% · onset 0.67
10.86–12.34 s: Yawn 52%, Exhausted Groan 17%, Frustrated Groan 15% · onset 0.63
11.02–12.50 s: Yawn 51%, Frustrated Groan 18%, Exhausted Groan 15% · onset 0.52
11.10–12.28 s: Yawn 50%, Frustrated Groan 19%, Exhausted Groan 14% · onset 0.52

Frame-positive regions: 3 · CPS 11.95 · Orange timbre cosine 0.960 · identity cosine 0.924

Medium predictions

20 ms frame probability; dashed line = 0.5 threshold

0.00–0.34 s: Sharp Inhale 26%, Chuckle 9%, Wistful Sigh 8% · onset 0.58
9.96–10.88 s: Breath 29%, Exasperated Sigh 12%, Exhausted Groan 11% · onset 0.57
10.12–11.64 s: Exhausted Groan 28%, Yawn 26%, Frustrated Groan 18% · onset 0.55
10.20–11.98 s: Yawn 35%, Exhausted Groan 25%, Frustrated Groan 22% · onset 0.69
10.28–12.50 s: Yawn 29%, Frustrated Groan 26%, Exhausted Groan 24% · onset 0.80
10.46–12.72 s: Frustrated Groan 28%, Yawn 26%, Exhausted Groan 24% · onset 0.73
10.54–12.62 s: Frustrated Groan 30%, Yawn 26%, Exhausted Groan 22% · onset 0.72
10.62–12.64 s: Frustrated Groan 31%, Yawn 26%, Exhausted Groan 21% · onset 0.77
10.68–12.46 s: Frustrated Groan 33%, Yawn 28%, Exhausted Groan 20% · onset 0.73
10.74–12.58 s: Frustrated Groan 34%, Yawn 26%, Exhausted Groan 20% · onset 0.72
10.80–12.64 s: Frustrated Groan 35%, Yawn 25%, Exhausted Groan 19% · onset 0.71
10.86–12.48 s: Frustrated Groan 38%, Yawn 25%, Exhausted Groan 17% · onset 0.57
10.96–12.38 s: Frustrated Groan 43%, Yawn 24%, Exhausted Groan 15% · onset 0.63
11.12–12.20 s: Frustrated Groan 48%, Yawn 23%, Exhausted Groan 11% · onset 0.57

Frame-positive regions: 1 · CPS 11.83 · Orange timbre cosine 0.946 · identity cosine 0.937

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

Target	Base raw	Base z	Medium raw	Medium z
`emo_Affection`	0.04	0.06	0.04	0.05
`emo_Amusement`	0.09	0.11	0.04	0.05
`emo_Anger`	0.08	0.12	0.09	0.14
`emo_Astonishment_Surprise`	0.31	0.52	0.21	0.36
`emo_Awe`	0.27	0.62	0.04	0.10
`emo_Bitterness`	0.48	1.11	0.28	0.65
`emo_Concentration`	1.81	1.59	1.95	1.77
`emo_Confusion`	0.22	0.40	0.13	0.23
`emo_Contemplation`	2.34	3.77	2.37	3.83
`emo_Contempt`	0.08	0.17	0.11	0.24
`emo_Contentment`	0.44	0.85	0.51	1.00
`emo_Disappointment`	1.31	1.87	1.07	1.53
`emo_Disgust`	0.06	0.11	0.06	0.10
`emo_Distress`	0.97	1.18	0.55	0.67
`emo_Doubt`	0.79	1.68	0.90	1.92
`emo_Elation`	0.04	0.04	0.01	-0.00
`emo_Embarrassment`	0.05	0.01	0.05	0.01
`emo_Emotional_Numbness`	0.54	0.59	0.61	0.66
`emo_Fatigue_Exhaustion`	0.70	1.25	0.56	0.99
`emo_Fear`	0.16	0.23	0.06	0.07
`emo_Helplessness`	0.61	0.89	0.32	0.46
`emo_Hope_Enthusiasm_Optimism`	0.26	0.19	0.30	0.24
`emo_Impatience_and_Irritability`	0.29	0.20	0.21	0.09
`emo_Infatuation`	-0.01	0.01	0.01	0.04
`emo_Interest`	1.90	0.34	1.92	0.36
`emo_Intoxication_Altered_States_of_Consciousness`	0.03	0.09	0.03	0.10
`emo_Jealousy_and_Envy`	0.03	-0.08	0.04	-0.04
`emo_Longing`	0.57	0.77	0.56	0.75
`emo_Malevolence_Malice`	0.01	-0.08	0.05	-0.02
`emo_Pain`	0.24	0.41	0.07	0.12
`emo_Pleasure_Ecstasy`	0.01	-0.01	0.03	0.02
`emo_Pride`	0.23	0.44	0.19	0.37
`emo_Relief`	0.04	0.01	0.16	0.19
`emo_Sadness`	1.04	1.38	0.80	1.06
`emo_Sexual_Lust`	0.02	-0.01	0.02	-0.02
`emo_Shame`	0.08	0.13	0.08	0.13
`emo_Sourness`	0.33	0.76	0.22	0.52
`emo_Teasing`	0.07	0.12	0.07	0.13
`emo_Thankfulness_Gratitude`	-0.03	-0.11	-0.00	-0.06
`emo_Triumph`	0.03	0.06	0.04	0.09
`vn_AGEV_reg`	3.30	0.26	3.19	0.17
`vn_AROU_reg`	1.78	-0.51	1.85	-0.45
`vn_ARSH_reg`	2.58	0.00	2.55	-0.03
`vn_ATCK_reg`	2.57	0.32	2.75	0.45
`vn_BKGN_reg`	3.91	1.58	3.72	1.34
`vn_BRGT_reg`	3.05	1.31	2.99	1.23
`vn_CHNK_reg`	3.02	0.95	2.91	0.86
`vn_CLRT_reg`	4.22	2.33	4.43	2.56
`vn_COGL_reg`	1.08	-0.96	0.93	-1.09
`vn_DARC_reg`	2.47	0.62	2.60	0.71
`vn_DFLU_reg`	0.52	-1.66	0.33	-1.82
`vn_EMPH_reg`	3.41	0.52	3.42	0.53
`vn_ESTH_reg`	4.00	2.05	3.98	2.02
`vn_EXPL_reg`	0.00	-0.26	0.09	0.01
`vn_FOCS_reg`	3.62	1.16	3.58	1.12
`vn_FULL_reg`	3.45	1.88	3.73	2.19
`vn_GEND_reg`	4.98	0.58	4.68	0.39
`vn_HARM_reg`	3.38	1.07	3.61	1.35
`vn_METL_reg`	1.19	-0.45	1.20	-0.44
`vn_RANG_reg`	2.27	-0.72	2.37	-0.61
`vn_RCQL_reg`	4.14	1.57	4.03	1.44
`vn_REGS_reg`	1.41	0.17	1.48	0.22
`vn_RESP_reg`	2.36	-0.31	2.15	-0.50
`vn_ROUG_reg`	1.94	-0.10	1.69	-0.38
`vn_R_CHST_reg`	3.79	1.96	3.54	1.67
`vn_R_HEAD_reg`	1.70	-0.55	1.76	-0.48
`vn_R_MASK_reg`	2.53	0.62	2.73	0.82
`vn_R_MIXD_reg`	3.39	2.32	3.51	2.46
`vn_R_NASL_reg`	1.52	-1.21	1.36	-1.36
`vn_R_ORAL_reg`	3.11	1.26	3.10	1.24
`vn_R_THRT_reg`	2.85	0.98	2.74	0.83
`vn_SMTH_reg`	3.73	1.45	3.87	1.58
`vn_STNC_reg`	3.27	0.56	3.22	0.52
`vn_STRU_reg`	4.11	2.06	4.17	2.12
`vn_S_ASMR_reg`	1.12	-0.18	0.90	-0.33
`vn_S_AUTH_reg`	2.78	1.62	2.96	1.79
`vn_S_CART_reg`	0.16	-1.00	-0.12	-1.20
`vn_S_CASU_reg`	2.21	-1.24	2.02	-1.39
`vn_S_CONV_reg`	2.56	-0.02	2.43	-0.13
`vn_S_DRAM_reg`	2.59	-0.11	2.45	-0.23
`vn_S_FORM_reg`	2.63	1.41	2.83	1.60
`vn_S_MONO_reg`	3.58	0.59	3.57	0.58
`vn_S_NARR_reg`	4.04	1.89	4.12	1.95
`vn_S_NEWS_reg`	1.28	1.54	1.51	1.94
`vn_S_PLAY_reg`	0.41	-1.48	0.46	-1.44
`vn_S_RANT_reg`	0.67	-0.42	0.34	-0.67
`vn_S_STRY_reg`	3.21	0.54	2.94	0.34
`vn_S_TECH_reg`	2.11	1.19	2.28	1.33
`vn_S_WHIS_reg`	0.86	-0.46	0.34	-0.78
`vn_TEMP_reg`	2.42	0.25	2.50	0.32
`vn_TENS_reg`	2.16	0.71	2.07	0.60
`vn_VALN_reg`	2.24	-0.08	2.46	0.12
`vn_VALS_reg`	2.78	0.24	2.62	0.09
`vn_VFLX_reg`	2.57	0.26	2.47	0.17
`vn_VOLT_reg`	1.65	-1.05	1.71	-0.98
`vn_VULN_reg`	2.36	-0.29	2.05	-0.61
`vn_WARM_reg`	3.47	0.99	3.55	1.06
`genuineness_0_6`	4.22	1.16	4.29	1.21
`blend_0_10`	7.46	0.29	7.24	0.21
`R_quality`	0.59	-1.49	0.58	-1.53
`eiv_extra:Age`	3.36	0.37	3.39	0.49
`eiv_extra:Arousal`	1.34	0.12	1.18	-0.25
`eiv_extra:Authenticity`	2.93	1.73	2.86	1.26
`eiv_extra:Background_Noise`	0.52	-1.09	0.53	-1.05
`eiv_extra:Confident_vs._Hesitant`	0.98	-0.21	1.06	0.05
`eiv_extra:Gender`	-0.41	0.21	-0.58	0.04
`eiv_extra:High-Pitched_vs._Low-Pitched`	1.78	-0.18	1.84	0.04
`eiv_extra:Monotone_vs._Expressive`	1.70	-0.34	1.72	-0.30
`eiv_extra:Recording_Quality`	2.30	0.46	2.28	0.42
`eiv_extra:Serious_vs._Humorous`	0.80	-0.37	0.91	-0.04
`eiv_extra:Soft_vs._Harsh`	0.15	-0.40	0.15	-0.41
`eiv_extra:Submissive_vs._Dominant`	0.41	0.12	0.33	-0.15
`eiv_extra:Valence`	-0.09	-0.26	-0.02	-0.06
`eiv_extra:Vulnerable_vs._Emotionally_Detached`	1.61	-0.24	1.64	-0.17
`eiv_extra:Warm_vs._Cold`	-0.01	-0.19	0.05	-0.00
`eiv_extra:score_background_quality`	3.85	0.80	3.89	0.84
`eiv_extra:score_content_enjoyment`	4.92	1.36	4.90	1.31
`eiv_extra:score_overall_quality`	3.17	1.02	3.17	1.02
`eiv_extra:score_speech_quality`	1.95	0.98	1.95	0.99
`audiobox:CE`	6.10	1.28	5.96	1.14
`audiobox:CU`	6.67	1.02	6.76	1.11
`audiobox:PC`	1.44	-0.55	1.42	-0.57
`audiobox:PQ`	7.71	0.76	7.77	0.83
`dnsmos:SIG_raw`	4.21	0.46	4.23	0.49
`dnsmos:BAK_raw`	4.51	1.15	4.53	1.17
`dnsmos:OVRL_raw`	4.06	1.20	4.06	1.20
`dnsmos:SIG`	3.65	0.33	3.67	0.36
`dnsmos:BAK`	4.18	0.85	4.18	0.85
`dnsmos:OVRL`	3.45	1.00	3.46	1.02
`dnsmos:P808_MOS`	4.17	1.52	4.21	1.59
`burst_count_log1p`	0.84	1.30	0.72	1.12
`voiceclap_attribute:Affection`	0.05	-1.63	-0.02	-1.75
`voiceclap_attribute:Age`	3.50	0.49	3.36	0.24
`voiceclap_attribute:Amusement`	-0.28	-1.18	-0.04	-0.76
`voiceclap_attribute:Anger`	0.22	-1.53	0.09	-1.78
`voiceclap_attribute:Arousal`	1.34	-0.13	1.30	-0.19
`voiceclap_attribute:Astonishment_Surprise`	0.26	-0.53	0.18	-0.69
`voiceclap_attribute:Authenticity`	3.01	1.42	2.96	1.12
`voiceclap_attribute:Awe`	0.27	-1.04	0.28	-0.99
`voiceclap_attribute:Background_Noise`	0.31	-0.97	0.36	-0.78
`voiceclap_attribute:Bitterness`	0.39	-0.88	0.30	-1.25
`voiceclap_attribute:Concentration`	2.04	1.55	2.29	2.02
`voiceclap_attribute:Confident_vs._Hesitant`	1.02	-0.10	1.07	-0.01
`voiceclap_attribute:Confusion`	0.29	-1.05	0.23	-1.23
`voiceclap_attribute:Contemplation`	2.42	4.04	2.62	4.54
`voiceclap_attribute:Contempt`	0.08	-1.85	0.04	-1.99
`voiceclap_attribute:Contentment`	0.90	1.00	1.11	1.69
`voiceclap_attribute:Disappointment`	0.78	0.07	0.58	-0.61
`voiceclap_attribute:Disgust`	0.08	-2.65	0.03	-2.86
`voiceclap_attribute:Distress`	0.96	0.09	0.67	-0.75
`voiceclap_attribute:Doubt`	0.70	0.88	0.74	1.08
`voiceclap_attribute:Elation`	-0.30	-2.11	-0.16	-1.77
`voiceclap_attribute:Embarrassment`	-0.08	-1.24	-0.00	-0.98
`voiceclap_attribute:Emotional_Numbness`	0.15	-1.93	0.07	-2.24
`voiceclap_attribute:Fatigue_Exhaustion`	0.99	2.02	0.87	1.56
`voiceclap_attribute:Fear`	0.25	-1.72	0.10	-2.42
`voiceclap_attribute:Gender`	-0.10	0.05	-0.44	-0.29
`voiceclap_attribute:Helplessness`	0.88	0.82	0.70	0.14
`voiceclap_attribute:High-Pitched_vs._Low-Pitched`	1.72	-0.33	1.75	-0.25
`voiceclap_attribute:Hope_Enthusiasm_Optimism`	0.21	-1.26	0.51	-0.48
`voiceclap_attribute:Impatience_and_Irritability`	0.35	-1.30	0.21	-1.55
`voiceclap_attribute:Infatuation`	0.02	-1.76	0.00	-1.82
`voiceclap_attribute:Interest`	1.59	-0.02	1.92	0.73
`voiceclap_attribute:Intoxication_Altered_States_of_Consciousness`	-0.03	-1.14	-0.03	-1.14
`voiceclap_attribute:Jealousy_&_Envy`	-0.00	-2.15	-0.09	-2.52
`voiceclap_attribute:Longing`	0.38	-0.70	0.39	-0.66
`voiceclap_attribute:Malevolence_Malice`	-0.06	-2.59	-0.06	-2.57
`voiceclap_attribute:Monotone_vs._Expressive`	1.54	-0.39	1.69	-0.14
`voiceclap_attribute:Pain`	0.35	-0.13	0.27	-0.51
`voiceclap_attribute:Pleasure_Ecstasy`	-0.10	-1.99	-0.02	-1.75
`voiceclap_attribute:Pride`	0.16	-1.78	0.19	-1.68
`voiceclap_attribute:Recording_Quality`	2.65	1.04	2.68	1.12
`voiceclap_attribute:Relief`	0.40	-1.50	0.25	-1.87
`voiceclap_attribute:Sadness`	0.64	-0.36	0.52	-0.75
`voiceclap_attribute:Serious_vs._Humorous`	0.42	-0.67	0.70	-0.18
`voiceclap_attribute:Sexual_Lust`	0.01	-1.49	0.00	-1.51
`voiceclap_attribute:Shame`	0.07	-1.63	0.01	-1.83
`voiceclap_attribute:Soft_vs._Harsh`	0.18	0.05	0.17	0.02
`voiceclap_attribute:Sourness`	0.35	-1.24	0.26	-1.54
`voiceclap_attribute:Submissive_vs._Dominant`	0.52	-0.29	0.53	-0.26
`voiceclap_attribute:Teasing`	-0.11	-1.73	0.02	-1.37
`voiceclap_attribute:Thankfulness_Gratitude`	-0.01	-2.63	-0.06	-2.72
`voiceclap_attribute:Triumph`	-0.05	-2.13	-0.08	-2.22
`voiceclap_attribute:Valence`	-0.44	-0.68	-0.09	-0.14
`voiceclap_attribute:Vulnerable_vs._Emotionally_Detached`	1.66	0.04	1.67	0.06
`voiceclap_attribute:Warm_vs._Cold`	-0.28	-0.55	0.02	0.22
`voiceclap_attribute:duration`	11.91	0.16	12.07	0.18
`voiceclap_attribute:score_background_quality`	3.76	1.03	3.89	1.29
`voiceclap_attribute:score_content_enjoyment`	4.87	1.46	4.97	2.11
`voiceclap_attribute:score_overall_quality`	3.12	1.17	3.26	1.51
`voiceclap_attribute:score_speech_quality`	1.88	-0.14	1.89	-0.08
`voiceclap_attribute:talking_speed`	12.27	0.86	11.34	0.62

← All 50 examples ← Previous Next →