Interactive listening evidence · Base & Medium

Vocal burst 10: Chewing Noises, Pleasure Moan

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 →

10. Chewing Noises, Pleasure Moan

EN_pSWJNePXD1g_W000005

emolia · en/real · 8.74 s · validation split

4 Gemini eventsBase count 1.6Medium count 1.4

Source key: EN_pSWJNePXD1g_W000005 · Audio SHA256: 7209a3be7964de2bf3fd72e31fa64d1ef03e09874744cd6a88e2f513d63ccdb7

Gemini annotation · selection aid

0.00–0.58 s: Pleasure Moan · group moan
3.73–4.19 s: Chewing Noises · group mouth
4.67–5.14 s: Pleasure Moan · group moan
6.78–7.23 s: Pleasure Moan · group moan

Base predictions

20 ms frame probability; dashed line = 0.5 threshold

0.00–0.64 s: Hum 69%, Affirmative Grunt 12%, Low Mumble 4% · onset 0.98
0.10–0.54 s: Hum 71%, Affirmative Grunt 10%, Low Mumble 7% · onset 0.50
3.98–4.50 s: Low Mumble 15%, Chuckle 13%, Lip Smack 7% · onset 0.60
4.64–5.06 s: Hum 46%, Affirmative Grunt 18%, Low Mumble 13% · onset 0.69
4.72–5.12 s: Hum 42%, Affirmative Grunt 24%, Low Mumble 11% · onset 0.69
6.38–6.90 s: Hum 26%, Affirmative Grunt 12%, Sharp Inhale 9% · onset 0.60
6.76–7.36 s: Hum 32%, Affirmative Grunt 30%, Displeased Grunt 9% · onset 0.53
6.84–7.38 s: Affirmative Grunt 32%, Hum 32%, Displeased Grunt 10% · onset 0.85
6.90–7.38 s: Affirmative Grunt 36%, Hum 30%, Displeased Grunt 10% · onset 0.83
7.00–7.52 s: Hum 43%, Affirmative Grunt 31%, Displeased Grunt 10% · onset 0.87
7.10–7.50 s: Hum 43%, Affirmative Grunt 35%, Displeased Grunt 8% · onset 0.75
7.18–7.62 s: Affirmative Grunt 49%, Hum 26%, Displeased Grunt 9% · onset 0.76
7.34–7.70 s: Affirmative Grunt 47%, Hum 12%, Displeased Grunt 10% · onset 0.54
7.50–7.80 s: Affirmative Grunt 26%, Sharp Inhale 16%, Lip Smack 9% · onset 0.56

Frame-positive regions: 4 · CPS 13.28 · Orange timbre cosine 0.870 · identity cosine 0.623

Medium predictions

20 ms frame probability; dashed line = 0.5 threshold

0.04–0.60 s: Hum 88%, Low Mumble 3%, Affirmative Grunt 2% · onset 0.99
3.70–4.22 s: Sharp Inhale 14%, Chuckle 14%, Low Mumble 11% · onset 0.55
4.48–5.10 s: Hum 46%, Affirmative Grunt 19%, Low Mumble 15% · onset 0.66
4.64–5.04 s: Hum 60%, Affirmative Grunt 16%, Low Mumble 10% · onset 0.74
4.72–5.18 s: Hum 63%, Affirmative Grunt 17%, Low Mumble 9% · onset 0.67
4.80–5.22 s: Hum 60%, Affirmative Grunt 18%, Low Mumble 9% · onset 0.82
6.76–7.16 s: Affirmative Grunt 19%, Chuckle 15%, Hum 10% · onset 0.64
6.88–7.56 s: Hum 43%, Affirmative Grunt 26%, Displeased Grunt 5% · onset 0.77
6.98–7.50 s: Hum 49%, Affirmative Grunt 24%, Displeased Grunt 4% · onset 0.67
7.04–7.42 s: Hum 44%, Affirmative Grunt 27%, Displeased Grunt 4% · onset 0.70
7.12–7.54 s: Hum 50%, Affirmative Grunt 28%, Low Mumble 3% · onset 0.70
7.18–7.60 s: Hum 39%, Affirmative Grunt 37%, Lip Smack 3% · onset 0.75
7.26–7.72 s: Affirmative Grunt 37%, Hum 34%, Displeased Grunt 4% · onset 0.70

Frame-positive regions: 5 · CPS 15.43 · Orange timbre cosine 0.927 · identity cosine 0.713

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

Target	Base raw	Base z	Medium raw	Medium z
`emo_Affection`	0.62	1.08	0.83	1.45
`emo_Amusement`	1.01	1.14	1.66	1.87
`emo_Anger`	0.05	0.07	0.07	0.11
`emo_Astonishment_Surprise`	0.05	0.08	0.10	0.16
`emo_Awe`	0.11	0.25	0.07	0.17
`emo_Bitterness`	0.05	0.10	0.03	0.04
`emo_Concentration`	1.95	1.77	1.72	1.47
`emo_Confusion`	0.29	0.54	0.13	0.24
`emo_Contemplation`	2.26	3.65	2.01	3.23
`emo_Contempt`	0.02	0.04	0.05	0.10
`emo_Contentment`	2.28	4.43	2.45	4.76
`emo_Disappointment`	0.15	0.22	0.12	0.17
`emo_Disgust`	-0.01	-0.03	0.00	-0.01
`emo_Distress`	0.18	0.22	0.08	0.10
`emo_Doubt`	0.91	1.94	0.79	1.69
`emo_Elation`	0.35	0.46	0.61	0.82
`emo_Embarrassment`	0.07	0.07	0.04	-0.02
`emo_Emotional_Numbness`	0.09	0.09	0.07	0.07
`emo_Fatigue_Exhaustion`	0.49	0.85	0.24	0.39
`emo_Fear`	-0.00	-0.03	-0.03	-0.07
`emo_Helplessness`	0.20	0.29	0.08	0.12
`emo_Hope_Enthusiasm_Optimism`	1.70	2.08	2.15	2.67
`emo_Impatience_and_Irritability`	0.20	0.07	0.20	0.07
`emo_Infatuation`	0.00	0.03	-0.01	0.01
`emo_Interest`	2.06	0.52	2.38	0.87
`emo_Intoxication_Altered_States_of_Consciousness`	0.04	0.12	0.00	0.05
`emo_Jealousy_and_Envy`	-0.02	-0.17	0.01	-0.10
`emo_Longing`	0.13	0.07	0.07	-0.02
`emo_Malevolence_Malice`	-0.00	-0.11	-0.00	-0.11
`emo_Pain`	0.07	0.12	0.00	0.01
`emo_Pleasure_Ecstasy`	0.27	0.41	0.35	0.55
`emo_Pride`	0.77	1.51	0.89	1.74
`emo_Relief`	0.50	0.69	0.75	1.05
`emo_Sadness`	0.14	0.18	-0.01	-0.02
`emo_Sexual_Lust`	-0.01	-0.08	-0.04	-0.14
`emo_Shame`	0.03	0.03	0.01	-0.01
`emo_Sourness`	0.09	0.21	0.06	0.16
`emo_Teasing`	0.25	0.46	0.65	1.19
`emo_Thankfulness_Gratitude`	0.26	0.31	0.27	0.33
`emo_Triumph`	0.13	0.26	0.20	0.39
`vn_AGEV_reg`	3.25	0.21	3.18	0.16
`vn_AROU_reg`	2.18	-0.15	2.31	-0.05
`vn_ARSH_reg`	2.76	0.21	2.99	0.47
`vn_ATCK_reg`	2.75	0.45	2.64	0.37
`vn_BKGN_reg`	3.07	0.48	3.13	0.56
`vn_BRGT_reg`	2.73	0.91	2.93	1.15
`vn_CHNK_reg`	2.58	0.59	2.22	0.30
`vn_CLRT_reg`	2.91	0.94	3.07	1.11
`vn_COGL_reg`	2.75	0.62	2.89	0.75
`vn_DARC_reg`	2.76	0.83	3.00	1.00
`vn_DFLU_reg`	3.03	0.46	3.00	0.44
`vn_EMPH_reg`	2.70	0.06	3.10	0.32
`vn_ESTH_reg`	3.14	0.94	3.36	1.22
`vn_EXPL_reg`	0.03	-0.18	0.05	-0.12
`vn_FOCS_reg`	3.52	1.07	3.78	1.31
`vn_FULL_reg`	3.32	1.73	3.05	1.43
`vn_GEND_reg`	5.15	0.69	4.96	0.57
`vn_HARM_reg`	3.18	0.84	3.36	1.05
`vn_METL_reg`	1.47	-0.15	1.32	-0.31
`vn_RANG_reg`	2.52	-0.44	2.69	-0.25
`vn_RCQL_reg`	2.92	0.19	3.10	0.39
`vn_REGS_reg`	0.99	-0.17	1.09	-0.08
`vn_RESP_reg`	2.29	-0.37	2.00	-0.64
`vn_ROUG_reg`	2.65	0.69	2.38	0.40
`vn_R_CHST_reg`	3.62	1.76	3.52	1.64
`vn_R_HEAD_reg`	1.26	-1.09	1.41	-0.90
`vn_R_MASK_reg`	2.18	0.27	2.35	0.44
`vn_R_MIXD_reg`	3.10	1.98	2.97	1.83
`vn_R_NASL_reg`	1.98	-0.78	1.91	-0.85
`vn_R_ORAL_reg`	3.13	1.27	3.04	1.16
`vn_R_THRT_reg`	3.12	1.31	2.74	0.84
`vn_SMTH_reg`	2.61	0.43	2.84	0.64
`vn_STNC_reg`	2.72	0.08	2.76	0.11
`vn_STRU_reg`	3.03	0.93	2.80	0.69
`vn_S_ASMR_reg`	0.33	-0.74	0.45	-0.65
`vn_S_AUTH_reg`	1.73	0.61	1.71	0.60
`vn_S_CART_reg`	0.51	-0.75	0.79	-0.55
`vn_S_CASU_reg`	4.68	0.69	4.94	0.90
`vn_S_CONV_reg`	4.47	1.42	4.95	1.79
`vn_S_DRAM_reg`	0.89	-1.59	0.72	-1.74
`vn_S_FORM_reg`	0.46	-0.72	0.49	-0.69
`vn_S_MONO_reg`	1.55	-0.99	1.08	-1.36
`vn_S_NARR_reg`	1.14	-0.12	1.34	0.02
`vn_S_NEWS_reg`	-0.06	-0.82	-0.09	-0.88
`vn_S_PLAY_reg`	1.84	-0.39	2.65	0.23
`vn_S_RANT_reg`	-0.29	-1.17	-0.41	-1.26
`vn_S_STRY_reg`	1.16	-0.97	1.28	-0.88
`vn_S_TECH_reg`	1.48	0.68	1.17	0.42
`vn_S_WHIS_reg`	0.21	-0.86	0.17	-0.88
`vn_TEMP_reg`	2.93	0.68	2.84	0.61
`vn_TENS_reg`	1.84	0.33	1.62	0.07
`vn_VALN_reg`	3.29	0.86	3.84	1.35
`vn_VALS_reg`	2.88	0.33	3.52	0.93
`vn_VFLX_reg`	3.15	0.74	2.90	0.53
`vn_VOLT_reg`	1.83	-0.85	1.94	-0.73
`vn_VULN_reg`	2.17	-0.49	2.45	-0.20
`vn_WARM_reg`	3.44	0.95	3.52	1.04
`genuineness_0_6`	4.95	1.61	4.96	1.62
`blend_0_10`	8.61	0.71	8.72	0.75
`R_quality`	1.05	-0.15	1.08	-0.03
`eiv_extra:Age`	2.90	-1.18	2.84	-1.42
`eiv_extra:Arousal`	1.61	0.74	1.87	1.32
`eiv_extra:Authenticity`	2.75	0.56	2.82	1.00
`eiv_extra:Background_Noise`	0.89	0.32	0.85	0.15
`eiv_extra:Confident_vs._Hesitant`	1.94	2.97	2.00	3.16
`eiv_extra:Gender`	-0.78	-0.15	-0.63	-0.01
`eiv_extra:High-Pitched_vs._Low-Pitched`	1.96	0.54	1.95	0.47
`eiv_extra:Monotone_vs._Expressive`	2.33	1.00	2.57	1.52
`eiv_extra:Recording_Quality`	1.94	-0.61	2.01	-0.39
`eiv_extra:Serious_vs._Humorous`	1.65	2.11	1.77	2.47
`eiv_extra:Soft_vs._Harsh`	0.56	0.88	0.62	1.07
`eiv_extra:Submissive_vs._Dominant`	0.28	-0.28	0.33	-0.13
`eiv_extra:Valence`	0.79	2.06	1.07	2.79
`eiv_extra:Vulnerable_vs._Emotionally_Detached`	1.34	-0.85	1.24	-1.09
`eiv_extra:Warm_vs._Cold`	0.77	2.40	0.93	2.93
`eiv_extra:score_background_quality`	3.66	0.51	3.59	0.41
`eiv_extra:score_content_enjoyment`	4.23	-0.91	4.27	-0.77
`eiv_extra:score_overall_quality`	2.90	0.49	2.80	0.29
`eiv_extra:score_speech_quality`	1.92	0.75	1.95	0.97
`audiobox:CE`	4.58	-0.22	4.30	-0.49
`audiobox:CU`	5.24	-0.41	4.84	-0.80
`audiobox:PC`	1.89	-0.27	1.86	-0.29
`audiobox:PQ`	6.62	-0.48	6.13	-1.04
`dnsmos:SIG_raw`	4.06	0.24	4.07	0.25
`dnsmos:BAK_raw`	4.24	0.92	4.10	0.80
`dnsmos:OVRL_raw`	3.79	0.87	3.70	0.75
`dnsmos:SIG`	3.58	0.17	3.59	0.19
`dnsmos:BAK`	4.08	0.74	3.99	0.65
`dnsmos:OVRL`	3.31	0.77	3.25	0.67
`dnsmos:P808_MOS`	3.85	0.87	3.83	0.83
`burst_count_log1p`	0.96	1.48	0.89	1.38
`voiceclap_attribute:Affection`	0.33	-1.12	1.04	0.17
`voiceclap_attribute:Age`	2.95	-0.51	3.09	-0.26
`voiceclap_attribute:Amusement`	0.72	0.58	1.27	1.54
`voiceclap_attribute:Anger`	-0.06	-2.08	-0.16	-2.27
`voiceclap_attribute:Arousal`	1.42	0.01	1.69	0.44
`voiceclap_attribute:Astonishment_Surprise`	0.15	-0.74	0.21	-0.62
`voiceclap_attribute:Authenticity`	2.69	-0.46	2.82	0.28
`voiceclap_attribute:Awe`	0.18	-1.39	0.34	-0.78
`voiceclap_attribute:Background_Noise`	0.61	0.15	0.61	0.16
`voiceclap_attribute:Bitterness`	-0.06	-2.78	-0.15	-3.17
`voiceclap_attribute:Concentration`	2.14	1.74	1.72	0.96
`voiceclap_attribute:Confident_vs._Hesitant`	2.12	2.24	1.93	1.84
`voiceclap_attribute:Confusion`	0.39	-0.76	0.10	-1.62
`voiceclap_attribute:Contemplation`	2.32	3.79	2.18	3.46
`voiceclap_attribute:Contempt`	-0.08	-2.32	-0.11	-2.43
`voiceclap_attribute:Contentment`	1.73	3.73	2.26	5.44
`voiceclap_attribute:Disappointment`	-0.05	-2.79	-0.26	-3.49
`voiceclap_attribute:Disgust`	-0.08	-3.40	-0.14	-3.69
`voiceclap_attribute:Distress`	-0.07	-2.85	-0.25	-3.36
`voiceclap_attribute:Doubt`	0.94	2.16	0.58	0.24
`voiceclap_attribute:Elation`	0.14	-1.00	0.68	0.35
`voiceclap_attribute:Embarrassment`	0.03	-0.90	0.04	-0.84
`voiceclap_attribute:Emotional_Numbness`	-0.02	-2.57	-0.02	-2.56
`voiceclap_attribute:Fatigue_Exhaustion`	0.34	-0.48	0.09	-1.42
`voiceclap_attribute:Fear`	-0.07	-3.23	-0.09	-3.32
`voiceclap_attribute:Gender`	-0.92	-0.77	-0.62	-0.46
`voiceclap_attribute:Helplessness`	0.10	-2.08	-0.06	-2.67
`voiceclap_attribute:High-Pitched_vs._Low-Pitched`	1.94	0.27	1.95	0.30
`voiceclap_attribute:Hope_Enthusiasm_Optimism`	1.10	1.00	1.64	2.35
`voiceclap_attribute:Impatience_and_Irritability`	0.13	-1.71	-0.07	-2.08
`voiceclap_attribute:Infatuation`	-0.04	-1.95	0.08	-1.58
`voiceclap_attribute:Interest`	2.31	1.62	2.45	1.93
`voiceclap_attribute:Intoxication_Altered_States_of_Consciousness`	0.11	-0.84	0.09	-0.89
`voiceclap_attribute:Jealousy_&_Envy`	-0.06	-2.39	-0.07	-2.42
`voiceclap_attribute:Longing`	0.06	-2.16	0.22	-1.45
`voiceclap_attribute:Malevolence_Malice`	-0.09	-2.67	-0.11	-2.73
`voiceclap_attribute:Monotone_vs._Expressive`	2.08	0.52	2.29	0.87
`voiceclap_attribute:Pain`	-0.00	-1.75	-0.10	-2.20
`voiceclap_attribute:Pleasure_Ecstasy`	0.08	-1.40	0.36	-0.49
`voiceclap_attribute:Pride`	0.47	-0.88	0.61	-0.50
`voiceclap_attribute:Recording_Quality`	2.03	-0.86	2.18	-0.40
`voiceclap_attribute:Relief`	0.26	-1.84	0.84	-0.43
`voiceclap_attribute:Sadness`	-0.10	-2.73	-0.12	-2.79
`voiceclap_attribute:Serious_vs._Humorous`	1.33	0.93	1.65	1.48
`voiceclap_attribute:Sexual_Lust`	-0.04	-1.60	-0.07	-1.69
`voiceclap_attribute:Shame`	0.08	-1.56	-0.00	-1.88
`voiceclap_attribute:Soft_vs._Harsh`	0.38	0.60	0.52	1.00
`voiceclap_attribute:Sourness`	-0.04	-2.58	-0.12	-2.83
`voiceclap_attribute:Submissive_vs._Dominant`	0.28	-0.96	0.33	-0.83
`voiceclap_attribute:Teasing`	0.20	-0.91	0.49	-0.14
`voiceclap_attribute:Thankfulness_Gratitude`	0.23	-2.17	0.39	-1.87
`voiceclap_attribute:Triumph`	0.05	-1.85	0.25	-1.28
`voiceclap_attribute:Valence`	0.12	0.20	0.42	0.68
`voiceclap_attribute:Vulnerable_vs._Emotionally_Detached`	1.55	-0.16	1.50	-0.25
`voiceclap_attribute:Warm_vs._Cold`	0.37	1.09	0.63	1.73
`voiceclap_attribute:duration`	9.63	-0.20	10.08	-0.13
`voiceclap_attribute:score_background_quality`	3.35	0.21	3.37	0.25
`voiceclap_attribute:score_content_enjoyment`	4.58	-0.51	4.61	-0.31
`voiceclap_attribute:score_overall_quality`	2.70	0.15	2.73	0.24
`voiceclap_attribute:score_speech_quality`	1.91	0.27	1.92	0.39
`voiceclap_attribute:talking_speed`	12.87	1.02	13.12	1.09

← All 50 examples ← Previous Next →