Interactive listening evidence · Base & Medium

Vocal burst 45: 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 →

45. Lip Smack

mediathek_0070Cgravelly-orc-warlord__en.c003.k0

vc_sidon · en/synth · 1.20 s · test split

1 Gemini eventsBase count 1.1Medium count 1.0

Source key: mediathek_0070__C__gravelly-orc-warlord__en.c003.k0 · Audio SHA256: 8310ea2ce11ad30b37dca72f11c4ffc8d9fce6b6aa2efbd006fed204b673900b

Gemini annotation · selection aid

0.05–0.98 s: Lip Smack · group mouth

Base predictions

20 ms frame probability; dashed line = 0.5 threshold

0.04–1.20 s: Exhausted Groan 38%, Other / rare burst 16%, Growl 11% · onset 0.99
0.14–1.20 s: Exhausted Groan 37%, Other / rare burst 15%, Growl 11% · onset 0.76
0.20–1.20 s: Exhausted Groan 37%, Other / rare burst 14%, Yawn 12% · onset 0.74
0.28–1.20 s: Exhausted Groan 38%, Other / rare burst 13%, Yawn 13% · onset 0.58
0.36–1.20 s: Exhausted Groan 39%, Yawn 12%, Other / rare burst 12% · onset 0.67
0.42–1.08 s: Exhausted Groan 35%, Yawn 12%, Frustrated Groan 11% · onset 0.57

Frame-positive regions: 1 · CPS 1.76 · Orange timbre cosine 0.497 · identity cosine 0.469

Medium predictions

20 ms frame probability; dashed line = 0.5 threshold

0.04–0.98 s: Exhausted Groan 32%, Frustrated Groan 14%, Growl 12% · onset 0.96
0.16–1.14 s: Exhausted Groan 40%, Frustrated Groan 15%, Growl 9% · onset 0.68
0.32–1.12 s: Exhausted Groan 39%, Frustrated Groan 14%, Yawn 10% · onset 0.75
0.40–1.20 s: Exhausted Groan 44%, Frustrated Groan 13%, Yawn 8% · onset 0.58
0.46–1.16 s: Exhausted Groan 40%, Frustrated Groan 11%, Yawn 8% · onset 0.69

Frame-positive regions: 1 · CPS 2.48 · Orange timbre cosine 0.644 · identity cosine 0.564

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

Target	Base raw	Base z	Medium raw	Medium z
`emo_Affection`	0.09	0.14	0.14	0.23
`emo_Amusement`	0.04	0.04	0.15	0.17
`emo_Anger`	0.47	0.75	0.06	0.10
`emo_Astonishment_Surprise`	0.14	0.23	0.11	0.18
`emo_Awe`	-0.03	-0.07	0.03	0.07
`emo_Bitterness`	0.17	0.37	0.00	-0.02
`emo_Concentration`	0.01	-0.84	0.15	-0.66
`emo_Confusion`	-0.02	-0.05	0.07	0.12
`emo_Contemplation`	0.22	0.23	0.41	0.54
`emo_Contempt`	0.01	0.03	-0.02	-0.04
`emo_Contentment`	0.18	0.35	0.22	0.43
`emo_Disappointment`	0.43	0.61	0.44	0.63
`emo_Disgust`	0.27	0.54	0.04	0.06
`emo_Distress`	1.24	1.51	0.69	0.84
`emo_Doubt`	0.03	0.04	0.15	0.31
`emo_Elation`	0.08	0.09	0.10	0.12
`emo_Embarrassment`	0.02	-0.06	0.03	-0.04
`emo_Emotional_Numbness`	0.25	0.27	0.35	0.38
`emo_Fatigue_Exhaustion`	2.50	4.58	2.61	4.80
`emo_Fear`	0.18	0.27	0.05	0.06
`emo_Helplessness`	1.22	1.75	1.47	2.12
`emo_Hope_Enthusiasm_Optimism`	0.17	0.07	0.11	-0.01
`emo_Impatience_and_Irritability`	0.64	0.70	0.20	0.07
`emo_Infatuation`	0.08	0.18	0.34	0.67
`emo_Interest`	0.20	-1.53	-0.05	-1.81
`emo_Intoxication_Altered_States_of_Consciousness`	0.07	0.17	0.14	0.29
`emo_Jealousy_and_Envy`	-0.03	-0.20	-0.01	-0.16
`emo_Longing`	0.32	0.37	0.38	0.47
`emo_Malevolence_Malice`	-0.08	-0.25	0.06	0.01
`emo_Pain`	1.44	2.49	1.20	2.08
`emo_Pleasure_Ecstasy`	0.15	0.21	0.27	0.41
`emo_Pride`	-0.05	-0.11	-0.06	-0.11
`emo_Relief`	0.36	0.48	0.27	0.34
`emo_Sadness`	0.44	0.59	0.63	0.83
`emo_Sexual_Lust`	0.22	0.39	0.45	0.85
`emo_Shame`	-0.07	-0.17	0.03	0.03
`emo_Sourness`	0.26	0.60	0.06	0.14
`emo_Teasing`	0.11	0.21	0.11	0.21
`emo_Thankfulness_Gratitude`	-0.06	-0.14	0.01	-0.05
`emo_Triumph`	-0.06	-0.10	-0.01	0.00
`vn_AGEV_reg`	3.01	0.02	3.09	0.08
`vn_AROU_reg`	2.14	-0.19	1.71	-0.56
`vn_ARSH_reg`	2.29	-0.34	2.00	-0.67
`vn_ATCK_reg`	2.07	-0.07	1.40	-0.59
`vn_BKGN_reg`	3.35	0.85	3.18	0.62
`vn_BRGT_reg`	2.13	0.17	1.65	-0.41
`vn_CHNK_reg`	1.07	-0.62	0.74	-0.89
`vn_CLRT_reg`	1.08	-1.00	1.01	-1.06
`vn_COGL_reg`	1.21	-0.84	1.81	-0.27
`vn_DARC_reg`	1.78	0.12	1.25	-0.26
`vn_DFLU_reg`	0.61	-1.59	0.61	-1.59
`vn_EMPH_reg`	2.20	-0.26	2.14	-0.30
`vn_ESTH_reg`	2.12	-0.36	2.39	-0.02
`vn_EXPL_reg`	0.05	-0.10	0.02	-0.19
`vn_FOCS_reg`	2.06	-0.26	1.91	-0.40
`vn_FULL_reg`	2.40	0.70	2.58	0.90
`vn_GEND_reg`	2.73	-0.83	3.53	-0.33
`vn_HARM_reg`	1.38	-1.32	1.35	-1.36
`vn_METL_reg`	1.08	-0.56	0.85	-0.80
`vn_RANG_reg`	1.87	-1.16	1.53	-1.55
`vn_RCQL_reg`	3.54	0.88	3.49	0.83
`vn_REGS_reg`	2.41	0.96	1.79	0.47
`vn_RESP_reg`	4.43	1.65	4.20	1.44
`vn_ROUG_reg`	3.31	1.44	3.11	1.22
`vn_R_CHST_reg`	2.10	-0.04	2.17	0.04
`vn_R_HEAD_reg`	1.59	-0.68	0.95	-1.46
`vn_R_MASK_reg`	1.28	-0.62	0.82	-1.08
`vn_R_MIXD_reg`	2.14	0.84	1.62	0.22
`vn_R_NASL_reg`	1.11	-1.61	1.17	-1.54
`vn_R_ORAL_reg`	2.10	-0.11	1.88	-0.40
`vn_R_THRT_reg`	3.36	1.60	3.25	1.47
`vn_SMTH_reg`	2.01	-0.12	2.35	0.19
`vn_STNC_reg`	1.54	-0.96	1.13	-1.32
`vn_STRU_reg`	0.72	-1.48	0.95	-1.23
`vn_S_ASMR_reg`	1.88	0.36	2.43	0.75
`vn_S_AUTH_reg`	-0.40	-1.43	-0.47	-1.49
`vn_S_CART_reg`	0.76	-0.57	0.37	-0.85
`vn_S_CASU_reg`	3.14	-0.51	3.02	-0.60
`vn_S_CONV_reg`	1.02	-1.19	0.89	-1.29
`vn_S_DRAM_reg`	2.75	0.03	2.49	-0.20
`vn_S_FORM_reg`	-0.12	-1.29	0.29	-0.88
`vn_S_MONO_reg`	3.66	0.65	3.72	0.70
`vn_S_NARR_reg`	-0.18	-1.03	0.16	-0.79
`vn_S_NEWS_reg`	-0.22	-1.11	-0.17	-1.02
`vn_S_PLAY_reg`	0.20	-1.64	0.42	-1.47
`vn_S_RANT_reg`	0.14	-0.83	0.18	-0.80
`vn_S_STRY_reg`	-0.03	-1.84	-0.24	-1.99
`vn_S_TECH_reg`	-0.74	-1.13	-0.47	-0.91
`vn_S_WHIS_reg`	2.14	0.33	2.12	0.32
`vn_TEMP_reg`	1.83	-0.24	1.47	-0.55
`vn_TENS_reg`	2.53	1.14	2.28	0.85
`vn_VALN_reg`	1.24	-0.98	1.01	-1.18
`vn_VALS_reg`	2.27	-0.23	2.25	-0.24
`vn_VFLX_reg`	3.22	0.80	2.87	0.51
`vn_VOLT_reg`	1.70	-1.00	1.56	-1.15
`vn_VULN_reg`	4.03	1.41	4.31	1.69
`vn_WARM_reg`	2.74	0.17	2.92	0.38
`genuineness_0_6`	4.27	1.19	4.24	1.18
`blend_0_10`	8.97	0.84	9.18	0.92
`R_quality`	0.94	-0.47	1.01	-0.26
`eiv_extra:Age`	3.01	-0.81	2.84	-1.39
`eiv_extra:Arousal`	1.45	0.38	1.49	0.45
`eiv_extra:Authenticity`	2.84	1.12	2.93	1.71
`eiv_extra:Background_Noise`	0.41	-1.50	0.28	-2.00
`eiv_extra:Confident_vs._Hesitant`	1.58	1.78	1.10	0.19
`eiv_extra:Gender`	0.29	0.91	0.33	0.95
`eiv_extra:High-Pitched_vs._Low-Pitched`	0.98	-3.39	0.82	-4.01
`eiv_extra:Monotone_vs._Expressive`	1.11	-1.60	0.89	-2.06
`eiv_extra:Recording_Quality`	1.88	-0.81	2.20	0.16
`eiv_extra:Serious_vs._Humorous`	0.27	-1.94	0.08	-2.51
`eiv_extra:Soft_vs._Harsh`	0.68	1.23	0.56	0.87
`eiv_extra:Submissive_vs._Dominant`	-0.03	-1.25	-0.03	-1.25
`eiv_extra:Valence`	-0.53	-1.41	0.31	0.79
`eiv_extra:Vulnerable_vs._Emotionally_Detached`	0.42	-2.96	0.50	-2.79
`eiv_extra:Warm_vs._Cold`	-0.34	-1.30	0.03	-0.06
`eiv_extra:score_background_quality`	2.76	-0.78	2.90	-0.59
`eiv_extra:score_content_enjoyment`	3.81	-2.31	3.77	-2.45
`eiv_extra:score_overall_quality`	1.89	-1.49	1.93	-1.43
`eiv_extra:score_speech_quality`	1.83	0.17	1.76	-0.35
`audiobox:CE`	3.76	-1.02	3.87	-0.91
`audiobox:CU`	5.45	-0.20	5.80	0.15
`audiobox:PC`	1.53	-0.50	1.62	-0.44
`audiobox:PQ`	6.52	-0.60	6.95	-0.11
`dnsmos:SIG_raw`	1.76	-3.20	2.34	-2.33
`dnsmos:BAK_raw`	1.93	-1.14	2.13	-0.96
`dnsmos:OVRL_raw`	1.40	-2.07	1.61	-1.82
`dnsmos:SIG`	1.92	-3.12	2.41	-2.15
`dnsmos:BAK`	2.20	-1.28	2.39	-1.07
`dnsmos:OVRL`	1.52	-2.18	1.70	-1.89
`dnsmos:P808_MOS`	2.59	-1.68	2.71	-1.43
`burst_count_log1p`	0.73	1.12	0.71	1.10
`voiceclap_attribute:Affection`	0.14	-1.46	-0.06	-1.82
`voiceclap_attribute:Age`	3.00	-0.42	2.50	-1.33
`voiceclap_attribute:Amusement`	-0.16	-0.96	0.02	-0.66
`voiceclap_attribute:Anger`	0.31	-1.35	0.21	-1.55
`voiceclap_attribute:Arousal`	0.91	-0.83	0.75	-1.08
`voiceclap_attribute:Astonishment_Surprise`	0.13	-0.79	0.12	-0.81
`voiceclap_attribute:Authenticity`	2.90	0.79	2.89	0.72
`voiceclap_attribute:Awe`	-0.05	-2.28	0.11	-1.66
`voiceclap_attribute:Background_Noise`	0.50	-0.26	0.44	-0.49
`voiceclap_attribute:Bitterness`	0.23	-1.54	0.22	-1.59
`voiceclap_attribute:Concentration`	0.31	-1.69	0.63	-1.10
`voiceclap_attribute:Confident_vs._Hesitant`	1.56	1.06	1.30	0.49
`voiceclap_attribute:Confusion`	0.11	-1.60	0.02	-1.87
`voiceclap_attribute:Contemplation`	0.75	-0.07	0.88	0.23
`voiceclap_attribute:Contempt`	0.04	-1.99	0.05	-1.96
`voiceclap_attribute:Contentment`	0.30	-0.94	0.58	-0.01
`voiceclap_attribute:Disappointment`	0.47	-0.98	0.57	-0.64
`voiceclap_attribute:Disgust`	0.15	-2.28	0.27	-1.71
`voiceclap_attribute:Distress`	1.25	0.92	1.10	0.49
`voiceclap_attribute:Doubt`	0.34	-1.03	0.20	-1.81
`voiceclap_attribute:Elation`	-0.20	-1.86	-0.04	-1.45
`voiceclap_attribute:Embarrassment`	-0.03	-1.07	-0.08	-1.22
`voiceclap_attribute:Emotional_Numbness`	0.27	-1.47	0.20	-1.74
`voiceclap_attribute:Fatigue_Exhaustion`	1.68	4.67	1.72	4.82
`voiceclap_attribute:Fear`	0.25	-1.73	0.31	-1.44
`voiceclap_attribute:Gender`	0.67	0.81	0.51	0.66
`voiceclap_attribute:Helplessness`	1.20	2.01	1.11	1.67
`voiceclap_attribute:High-Pitched_vs._Low-Pitched`	1.25	-1.57	0.91	-2.48
`voiceclap_attribute:Hope_Enthusiasm_Optimism`	-0.09	-2.01	-0.01	-1.82
`voiceclap_attribute:Impatience_and_Irritability`	0.32	-1.36	0.24	-1.50
`voiceclap_attribute:Infatuation`	0.12	-1.48	0.02	-1.77
`voiceclap_attribute:Interest`	-0.04	-3.71	0.27	-3.03
`voiceclap_attribute:Intoxication_Altered_States_of_Consciousness`	0.32	-0.39	-0.06	-1.22
`voiceclap_attribute:Jealousy_&_Envy`	0.11	-1.67	0.05	-1.93
`voiceclap_attribute:Longing`	0.37	-0.78	0.16	-1.72
`voiceclap_attribute:Malevolence_Malice`	0.09	-2.13	0.27	-1.63
`voiceclap_attribute:Monotone_vs._Expressive`	1.32	-0.77	0.79	-1.66
`voiceclap_attribute:Pain`	0.71	1.49	0.57	0.85
`voiceclap_attribute:Pleasure_Ecstasy`	0.08	-1.41	0.14	-1.22
`voiceclap_attribute:Pride`	-0.21	-2.84	-0.17	-2.71
`voiceclap_attribute:Recording_Quality`	1.95	-1.12	2.22	-0.30
`voiceclap_attribute:Relief`	0.48	-1.30	0.45	-1.38
`voiceclap_attribute:Sadness`	0.57	-0.59	0.50	-0.81
`voiceclap_attribute:Serious_vs._Humorous`	0.50	-0.53	0.42	-0.67
`voiceclap_attribute:Sexual_Lust`	0.25	-0.93	0.23	-0.96
`voiceclap_attribute:Shame`	-0.09	-2.19	0.00	-1.84
`voiceclap_attribute:Soft_vs._Harsh`	0.73	1.59	0.87	1.97
`voiceclap_attribute:Sourness`	0.24	-1.59	0.13	-1.99
`voiceclap_attribute:Submissive_vs._Dominant`	-0.02	-1.79	-0.22	-2.34
`voiceclap_attribute:Teasing`	0.00	-1.42	-0.06	-1.59
`voiceclap_attribute:Thankfulness_Gratitude`	-0.01	-2.64	0.23	-2.17
`voiceclap_attribute:Triumph`	-0.14	-2.38	-0.03	-2.08
`voiceclap_attribute:Valence`	-0.98	-1.53	0.08	0.14
`voiceclap_attribute:Vulnerable_vs._Emotionally_Detached`	0.59	-1.89	0.59	-1.89
`voiceclap_attribute:Warm_vs._Cold`	0.05	0.29	0.00	0.17
`voiceclap_attribute:duration`	4.11	-1.07	3.82	-1.12
`voiceclap_attribute:score_background_quality`	2.92	-0.65	3.15	-0.19
`voiceclap_attribute:score_content_enjoyment`	4.49	-1.12	4.50	-1.03
`voiceclap_attribute:score_overall_quality`	2.00	-1.54	2.02	-1.49
`voiceclap_attribute:score_speech_quality`	2.00	1.60	1.97	1.21
`voiceclap_attribute:talking_speed`	2.09	-1.85	2.09	-1.85

← All 50 examples ← Previous Next →