Interactive listening evidence · Base & Medium

Vocal burst 25: Exasperated Sigh, Lip Smack

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 →

25. Exasperated Sigh, Lip Smack

k132_age2_bg1VEMPH__very_high__en.c011.k1

vc_sidon · en/synth · 10.06 s · test split

2 Gemini eventsBase count 2.0Medium count 2.4

Source key: k132_age2_bg1__V__EMPH__very_high__en.c011.k1 · Audio SHA256: 5a331d4d185a925428948882cc43adea37cb4429541c776920acf573b68a24c0

Gemini annotation · selection aid

0.00–0.35 s: Lip Smack · group mouth
6.82–7.78 s: Exasperated Sigh · group sigh_neg

Base predictions

20 ms frame probability; dashed line = 0.5 threshold

0.00–0.52 s: Sharp Inhale 41%, Exasperated Sigh 18%, Breath 13% · onset 0.98
0.10–0.70 s: Sharp Inhale 36%, Breath 19%, Exasperated Sigh 17% · onset 0.60
5.92–7.06 s: Breath 42%, Exasperated Sigh 24%, Relief Sigh 8% · onset 0.57
6.12–7.34 s: Exasperated Sigh 36%, Breath 25%, Relief Sigh 10% · onset 0.60
6.20–7.34 s: Exasperated Sigh 38%, Breath 22%, Relief Sigh 11% · onset 0.63
6.36–7.34 s: Exasperated Sigh 42%, Breath 19%, Relief Sigh 10% · onset 0.78
6.46–7.54 s: Exasperated Sigh 49%, Breath 18%, Relief Sigh 8% · onset 0.85
6.60–7.52 s: Exasperated Sigh 52%, Breath 15%, Relief Sigh 8% · onset 0.69
6.68–7.60 s: Exasperated Sigh 55%, Breath 14%, Relief Sigh 7% · onset 0.64
6.76–7.70 s: Exasperated Sigh 55%, Breath 14%, Relief Sigh 7% · onset 0.63
6.84–7.70 s: Exasperated Sigh 55%, Breath 13%, Relief Sigh 8% · onset 0.83
6.90–7.70 s: Exasperated Sigh 55%, Breath 13%, Relief Sigh 8% · onset 0.85
6.98–7.82 s: Exasperated Sigh 51%, Breath 17%, Relief Sigh 7% · onset 0.79
7.06–7.72 s: Exasperated Sigh 55%, Breath 13%, Relief Sigh 8% · onset 0.67
7.18–7.94 s: Exasperated Sigh 42%, Breath 25%, Relief Sigh 8% · onset 0.51

Frame-positive regions: 2 · CPS 11.74 · Orange timbre cosine 0.925 · identity cosine 0.866

Medium predictions

20 ms frame probability; dashed line = 0.5 threshold

0.00–0.48 s: Sharp Inhale 24%, Exasperated Sigh 24%, Breath 8% · onset 0.96
0.10–0.62 s: Exasperated Sigh 21%, Sharp Inhale 21%, Breath 13% · onset 0.62
6.02–6.90 s: Breath 51%, Exasperated Sigh 14%, Wistful Sigh 9% · onset 0.76
6.14–7.32 s: Breath 34%, Exasperated Sigh 24%, Wistful Sigh 10% · onset 0.79
6.20–7.46 s: Breath 30%, Exasperated Sigh 29%, Wistful Sigh 8% · onset 0.57
6.26–7.48 s: Exasperated Sigh 31%, Breath 29%, Exhausted Groan 8% · onset 0.59
6.34–7.42 s: Exasperated Sigh 32%, Breath 26%, Wistful Sigh 9% · onset 0.74
6.42–7.50 s: Exasperated Sigh 36%, Breath 25%, Relief Sigh 8% · onset 0.71
6.52–7.58 s: Exasperated Sigh 44%, Breath 23%, Relief Sigh 7% · onset 0.66
6.60–7.64 s: Exasperated Sigh 48%, Breath 20%, Exhausted Groan 6% · onset 0.68
6.66–7.74 s: Exasperated Sigh 50%, Breath 21%, Exhausted Groan 6% · onset 0.55
6.76–7.52 s: Exasperated Sigh 49%, Breath 16%, Relief Sigh 10% · onset 0.64
6.88–7.78 s: Exasperated Sigh 54%, Breath 19%, Relief Sigh 6% · onset 0.67
7.00–7.66 s: Exasperated Sigh 59%, Breath 13%, Relief Sigh 8% · onset 0.66
7.18–7.78 s: Exasperated Sigh 53%, Breath 15%, Relief Sigh 8% · onset 0.67

Frame-positive regions: 2 · CPS 11.34 · Orange timbre cosine 0.943 · identity cosine 0.905

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

Target	Base raw	Base z	Medium raw	Medium z
`emo_Affection`	1.94	3.40	2.66	4.65
`emo_Amusement`	-0.01	-0.01	0.07	0.08
`emo_Anger`	0.75	1.21	0.20	0.32
`emo_Astonishment_Surprise`	0.08	0.12	-0.01	-0.02
`emo_Awe`	0.21	0.48	0.32	0.75
`emo_Bitterness`	1.41	3.37	0.75	1.78
`emo_Concentration`	2.03	1.88	1.76	1.52
`emo_Confusion`	0.04	0.07	0.08	0.15
`emo_Contemplation`	2.74	4.45	3.05	4.96
`emo_Contempt`	0.20	0.43	0.04	0.09
`emo_Contentment`	0.61	1.19	0.97	1.88
`emo_Disappointment`	1.76	2.51	1.56	2.23
`emo_Disgust`	0.17	0.33	0.02	0.02
`emo_Distress`	1.67	2.04	1.10	1.34
`emo_Doubt`	0.64	1.37	0.41	0.87
`emo_Elation`	-0.04	-0.07	-0.02	-0.04
`emo_Embarrassment`	0.01	-0.08	-0.03	-0.17
`emo_Emotional_Numbness`	0.51	0.55	0.25	0.27
`emo_Fatigue_Exhaustion`	0.92	1.66	0.69	1.23
`emo_Fear`	0.11	0.16	0.15	0.23
`emo_Helplessness`	1.52	2.18	1.39	2.00
`emo_Hope_Enthusiasm_Optimism`	0.62	0.66	1.26	1.50
`emo_Impatience_and_Irritability`	0.59	0.62	0.08	-0.10
`emo_Infatuation`	0.58	1.12	0.96	1.84
`emo_Interest`	0.95	-0.70	1.22	-0.40
`emo_Intoxication_Altered_States_of_Consciousness`	0.06	0.15	0.02	0.08
`emo_Jealousy_and_Envy`	0.00	-0.13	0.05	-0.02
`emo_Longing`	1.65	2.47	2.51	3.84
`emo_Malevolence_Malice`	-0.01	-0.13	0.00	-0.10
`emo_Pain`	0.62	1.08	1.05	1.81
`emo_Pleasure_Ecstasy`	0.07	0.08	0.13	0.19
`emo_Pride`	0.30	0.59	0.45	0.87
`emo_Relief`	0.29	0.38	0.30	0.40
`emo_Sadness`	1.81	2.39	1.96	2.59
`emo_Sexual_Lust`	0.05	0.05	0.17	0.28
`emo_Shame`	0.12	0.22	-0.03	-0.09
`emo_Sourness`	0.53	1.21	0.11	0.27
`emo_Teasing`	0.08	0.15	0.06	0.11
`emo_Thankfulness_Gratitude`	0.16	0.16	0.40	0.51
`emo_Triumph`	-0.00	0.00	0.02	0.05
`vn_AGEV_reg`	3.57	0.47	3.52	0.44
`vn_AROU_reg`	1.96	-0.35	1.80	-0.48
`vn_ARSH_reg`	2.68	0.11	2.43	-0.17
`vn_ATCK_reg`	2.56	0.30	2.44	0.22
`vn_BKGN_reg`	3.88	1.54	3.85	1.51
`vn_BRGT_reg`	2.76	0.94	2.75	0.94
`vn_CHNK_reg`	2.40	0.44	2.26	0.34
`vn_CLRT_reg`	3.83	1.92	3.94	2.03
`vn_COGL_reg`	1.24	-0.81	1.16	-0.88
`vn_DARC_reg`	2.70	0.79	2.55	0.68
`vn_DFLU_reg`	0.59	-1.60	0.55	-1.63
`vn_EMPH_reg`	2.96	0.23	2.94	0.22
`vn_ESTH_reg`	3.79	1.77	3.96	1.99
`vn_EXPL_reg`	0.04	-0.14	0.05	-0.12
`vn_FOCS_reg`	3.92	1.43	4.08	1.58
`vn_FULL_reg`	4.08	2.59	4.18	2.70
`vn_GEND_reg`	5.30	0.78	5.50	0.91
`vn_HARM_reg`	2.79	0.36	2.70	0.27
`vn_METL_reg`	1.32	-0.31	1.18	-0.46
`vn_RANG_reg`	1.91	-1.12	1.95	-1.07
`vn_RCQL_reg`	3.90	1.30	4.10	1.52
`vn_REGS_reg`	0.77	-0.34	0.90	-0.23
`vn_RESP_reg`	3.10	0.40	3.18	0.47
`vn_ROUG_reg`	3.05	1.15	2.96	1.04
`vn_R_CHST_reg`	4.34	2.62	4.52	2.82
`vn_R_HEAD_reg`	0.95	-1.45	0.90	-1.52
`vn_R_MASK_reg`	1.91	0.00	2.06	0.16
`vn_R_MIXD_reg`	3.30	2.22	3.66	2.65
`vn_R_NASL_reg`	1.09	-1.62	0.91	-1.80
`vn_R_ORAL_reg`	3.16	1.32	2.98	1.08
`vn_R_THRT_reg`	3.58	1.89	3.53	1.82
`vn_SMTH_reg`	3.37	1.12	3.59	1.33
`vn_STNC_reg`	3.12	0.43	3.13	0.43
`vn_STRU_reg`	3.92	1.87	3.82	1.75
`vn_S_ASMR_reg`	1.24	-0.09	1.59	0.16
`vn_S_AUTH_reg`	2.72	1.57	2.75	1.60
`vn_S_CART_reg`	0.39	-0.84	0.35	-0.86
`vn_S_CASU_reg`	2.47	-1.03	2.29	-1.18
`vn_S_CONV_reg`	3.11	0.39	3.45	0.65
`vn_S_DRAM_reg`	3.46	0.64	3.49	0.67
`vn_S_FORM_reg`	1.79	0.58	1.92	0.71
`vn_S_MONO_reg`	3.52	0.54	3.20	0.29
`vn_S_NARR_reg`	2.09	0.54	2.12	0.56
`vn_S_NEWS_reg`	0.26	-0.26	0.48	0.12
`vn_S_PLAY_reg`	0.20	-1.64	0.29	-1.57
`vn_S_RANT_reg`	0.71	-0.39	0.39	-0.64
`vn_S_STRY_reg`	2.35	-0.09	2.34	-0.10
`vn_S_TECH_reg`	0.76	0.09	0.50	-0.12
`vn_S_WHIS_reg`	1.12	-0.30	1.20	-0.24
`vn_TEMP_reg`	2.14	0.02	2.05	-0.05
`vn_TENS_reg`	2.78	1.43	2.66	1.29
`vn_VALN_reg`	1.97	-0.32	2.28	-0.04
`vn_VALS_reg`	2.67	0.14	2.65	0.13
`vn_VFLX_reg`	2.57	0.26	2.70	0.37
`vn_VOLT_reg`	1.49	-1.24	1.46	-1.27
`vn_VULN_reg`	2.61	-0.04	2.88	0.24
`vn_WARM_reg`	3.63	1.16	3.84	1.38
`genuineness_0_6`	4.56	1.37	4.68	1.45
`blend_0_10`	7.64	0.35	7.57	0.33
`R_quality`	0.68	-1.22	0.66	-1.30
`eiv_extra:Age`	3.33	0.27	3.32	0.25
`eiv_extra:Arousal`	1.66	0.85	1.58	0.66
`eiv_extra:Authenticity`	3.31	4.19	3.53	5.62
`eiv_extra:Background_Noise`	-0.05	-3.25	-0.17	-3.70
`eiv_extra:Confident_vs._Hesitant`	1.42	1.26	1.36	1.07
`eiv_extra:Gender`	-0.74	-0.12	-0.57	0.05
`eiv_extra:High-Pitched_vs._Low-Pitched`	1.94	0.43	2.05	0.89
`eiv_extra:Monotone_vs._Expressive`	2.22	0.76	2.16	0.64
`eiv_extra:Recording_Quality`	2.89	2.25	3.08	2.81
`eiv_extra:Serious_vs._Humorous`	0.59	-1.00	0.39	-1.58
`eiv_extra:Soft_vs._Harsh`	0.52	0.74	0.54	0.82
`eiv_extra:Submissive_vs._Dominant`	0.96	1.80	0.92	1.68
`eiv_extra:Valence`	-0.35	-0.93	0.43	1.13
`eiv_extra:Vulnerable_vs._Emotionally_Detached`	1.20	-1.17	1.14	-1.32
`eiv_extra:Warm_vs._Cold`	-0.00	-0.18	0.22	0.55
`eiv_extra:score_background_quality`	3.90	0.87	4.04	1.06
`eiv_extra:score_content_enjoyment`	4.82	1.02	4.83	1.08
`eiv_extra:score_overall_quality`	3.15	0.98	3.21	1.11
`eiv_extra:score_speech_quality`	1.85	0.31	1.82	0.06
`audiobox:CE`	6.16	1.33	6.31	1.48
`audiobox:CU`	7.34	1.69	7.46	1.81
`audiobox:PC`	1.56	-0.48	1.51	-0.51
`audiobox:PQ`	8.15	1.25	8.24	1.36
`dnsmos:SIG_raw`	4.22	0.48	4.23	0.50
`dnsmos:BAK_raw`	4.51	1.15	4.53	1.17
`dnsmos:OVRL_raw`	4.03	1.16	4.03	1.16
`dnsmos:SIG`	3.66	0.34	3.67	0.35
`dnsmos:BAK`	4.18	0.85	4.22	0.90
`dnsmos:OVRL`	3.44	0.99	3.44	0.99
`dnsmos:P808_MOS`	3.93	1.03	4.00	1.18
`burst_count_log1p`	1.11	1.72	1.23	1.90
`voiceclap_attribute:Affection`	0.21	-1.32	0.73	-0.39
`voiceclap_attribute:Age`	3.45	0.41	3.44	0.38
`voiceclap_attribute:Amusement`	-0.24	-1.10	-0.43	-1.43
`voiceclap_attribute:Anger`	0.60	-0.78	0.59	-0.79
`voiceclap_attribute:Arousal`	1.46	0.07	1.67	0.41
`voiceclap_attribute:Astonishment_Surprise`	-0.19	-1.45	-0.58	-2.26
`voiceclap_attribute:Authenticity`	3.03	1.54	3.15	2.26
`voiceclap_attribute:Awe`	0.16	-1.47	0.06	-1.86
`voiceclap_attribute:Background_Noise`	0.25	-1.21	0.21	-1.36
`voiceclap_attribute:Bitterness`	0.53	-0.28	0.70	0.47
`voiceclap_attribute:Concentration`	1.78	1.07	1.59	0.70
`voiceclap_attribute:Confident_vs._Hesitant`	1.11	0.09	1.16	0.19
`voiceclap_attribute:Confusion`	0.07	-1.71	-0.04	-2.04
`voiceclap_attribute:Contemplation`	2.21	3.52	2.25	3.62
`voiceclap_attribute:Contempt`	0.37	-0.99	0.43	-0.82
`voiceclap_attribute:Contentment`	0.66	0.22	0.73	0.46
`voiceclap_attribute:Disappointment`	0.99	0.78	1.33	1.97
`voiceclap_attribute:Disgust`	0.15	-2.31	0.03	-2.86
`voiceclap_attribute:Distress`	1.01	0.25	1.53	1.72
`voiceclap_attribute:Doubt`	0.76	1.19	0.64	0.53
`voiceclap_attribute:Elation`	-0.36	-2.27	0.01	-1.33
`voiceclap_attribute:Embarrassment`	-0.08	-1.24	0.07	-0.74
`voiceclap_attribute:Emotional_Numbness`	0.07	-2.24	0.38	-1.06
`voiceclap_attribute:Fatigue_Exhaustion`	1.34	3.36	1.92	5.60
`voiceclap_attribute:Fear`	0.10	-2.42	0.19	-2.01
`voiceclap_attribute:Gender`	-0.72	-0.57	-0.96	-0.80
`voiceclap_attribute:Helplessness`	0.98	1.20	1.41	2.79
`voiceclap_attribute:High-Pitched_vs._Low-Pitched`	1.78	-0.16	1.99	0.39
`voiceclap_attribute:Hope_Enthusiasm_Optimism`	0.13	-1.46	0.24	-1.18
`voiceclap_attribute:Impatience_and_Irritability`	0.61	-0.82	0.97	-0.16
`voiceclap_attribute:Infatuation`	0.03	-1.73	0.02	-1.76
`voiceclap_attribute:Interest`	1.00	-1.36	0.56	-2.37
`voiceclap_attribute:Intoxication_Altered_States_of_Consciousness`	-0.18	-1.47	-0.26	-1.64
`voiceclap_attribute:Jealousy_&_Envy`	0.10	-1.73	-0.19	-2.92
`voiceclap_attribute:Longing`	0.44	-0.47	0.78	1.10
`voiceclap_attribute:Malevolence_Malice`	0.06	-2.24	0.12	-2.06
`voiceclap_attribute:Monotone_vs._Expressive`	1.75	-0.04	1.83	0.09
`voiceclap_attribute:Pain`	0.35	-0.15	0.60	1.00
`voiceclap_attribute:Pleasure_Ecstasy`	-0.09	-1.97	0.09	-1.36
`voiceclap_attribute:Pride`	0.38	-1.16	0.58	-0.56
`voiceclap_attribute:Recording_Quality`	2.59	0.84	2.65	1.02
`voiceclap_attribute:Relief`	0.15	-2.12	0.46	-1.37
`voiceclap_attribute:Sadness`	0.64	-0.37	1.13	1.21
`voiceclap_attribute:Serious_vs._Humorous`	0.44	-0.64	0.32	-0.85
`voiceclap_attribute:Sexual_Lust`	-0.11	-1.77	-0.07	-1.68
`voiceclap_attribute:Shame`	0.02	-1.77	0.25	-0.97
`voiceclap_attribute:Soft_vs._Harsh`	0.19	0.07	0.28	0.34
`voiceclap_attribute:Sourness`	0.58	-0.44	0.70	-0.01
`voiceclap_attribute:Submissive_vs._Dominant`	0.80	0.49	1.09	1.31
`voiceclap_attribute:Teasing`	-0.06	-1.57	-0.04	-1.53
`voiceclap_attribute:Thankfulness_Gratitude`	0.09	-2.44	0.44	-1.79
`voiceclap_attribute:Triumph`	-0.10	-2.28	0.06	-1.83
`voiceclap_attribute:Valence`	-0.71	-1.11	-0.88	-1.38
`voiceclap_attribute:Vulnerable_vs._Emotionally_Detached`	1.49	-0.26	1.31	-0.58
`voiceclap_attribute:Warm_vs._Cold`	-0.32	-0.62	-0.35	-0.71
`voiceclap_attribute:duration`	9.82	-0.17	9.85	-0.17
`voiceclap_attribute:score_background_quality`	3.69	0.90	3.63	0.78
`voiceclap_attribute:score_content_enjoyment`	4.74	0.58	4.73	0.53
`voiceclap_attribute:score_overall_quality`	2.96	0.78	2.84	0.50
`voiceclap_attribute:score_speech_quality`	1.89	0.01	1.86	-0.46
`voiceclap_attribute:talking_speed`	9.83	0.21	11.93	0.77

← All 50 examples ← Previous Next →