Interactive listening evidence · Base & Medium

Vocal burst 01: Mournful Wail

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 Next →

01. Mournful Wail

mediathek_0486VS_FORM__extremely_low__en.c033

vprof_original · en/synth · 2.56 s · validation split

2 Gemini eventsBase count 1.2Medium count 1.4

Source key: mediathek_0486__V__S_FORM__extremely_low__en.c033 · Audio SHA256: 512779ee771afdee844c55b3863fec1a9891c0f5097cfb9da4687e3ac6820ffe

Gemini annotation · selection aid

0.00–1.25 s: Mournful Wail · group wail
1.48–2.56 s: Mournful Wail · group wail

Base predictions

20 ms frame probability; dashed line = 0.5 threshold

0.04–2.12 s: Mournful Wail 25%, Other / rare burst 19%, Scream 18% · onset 0.98
0.10–1.66 s: Mournful Wail 20%, Scream 19%, Other / rare burst 16% · onset 0.81

Frame-positive regions: 1 · CPS 1.15 · Orange timbre cosine 0.653 · identity cosine 0.504

Medium predictions

20 ms frame probability; dashed line = 0.5 threshold

0.04–1.52 s: Scream 57%, Other / rare burst 10%, Shriek 7% · onset 0.97

Frame-positive regions: 1 · CPS 0.91 · Orange timbre cosine 0.601 · identity cosine 0.503

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

Target	Base raw	Base z	Medium raw	Medium z
`emo_Affection`	0.05	0.08	0.05	0.08
`emo_Amusement`	0.15	0.17	0.02	0.03
`emo_Anger`	0.31	0.49	0.59	0.96
`emo_Astonishment_Surprise`	0.14	0.23	0.41	0.71
`emo_Awe`	0.04	0.10	0.05	0.11
`emo_Bitterness`	-0.03	-0.11	0.01	-0.01
`emo_Concentration`	0.24	-0.54	0.03	-0.81
`emo_Confusion`	-0.01	-0.02	0.15	0.28
`emo_Contemplation`	0.10	0.03	-0.01	-0.15
`emo_Contempt`	-0.01	-0.02	-0.06	-0.12
`emo_Contentment`	0.12	0.23	0.01	0.01
`emo_Disappointment`	0.25	0.36	0.12	0.17
`emo_Disgust`	0.02	0.02	0.03	0.04
`emo_Distress`	2.60	3.17	3.58	4.35
`emo_Doubt`	0.00	-0.00	-0.01	-0.04
`emo_Elation`	0.07	0.08	0.17	0.21
`emo_Embarrassment`	0.03	-0.02	-0.01	-0.12
`emo_Emotional_Numbness`	0.03	0.03	-0.07	-0.08
`emo_Fatigue_Exhaustion`	0.56	0.99	0.94	1.70
`emo_Fear`	1.24	2.01	2.20	3.59
`emo_Helplessness`	2.16	3.10	3.01	4.33
`emo_Hope_Enthusiasm_Optimism`	0.05	-0.09	0.06	-0.08
`emo_Impatience_and_Irritability`	0.03	-0.17	0.20	0.07
`emo_Infatuation`	0.03	0.09	-0.00	0.02
`emo_Interest`	0.26	-1.47	-0.12	-1.89
`emo_Intoxication_Altered_States_of_Consciousness`	0.03	0.10	0.07	0.17
`emo_Jealousy_and_Envy`	0.02	-0.09	-0.02	-0.18
`emo_Longing`	0.11	0.03	-0.04	-0.20
`emo_Malevolence_Malice`	0.23	0.32	0.22	0.31
`emo_Pain`	2.15	3.72	2.70	4.67
`emo_Pleasure_Ecstasy`	0.26	0.39	0.11	0.15
`emo_Pride`	0.01	0.01	-0.01	-0.03
`emo_Relief`	0.08	0.07	0.08	0.07
`emo_Sadness`	0.79	1.04	1.29	1.71
`emo_Sexual_Lust`	-0.02	-0.10	0.01	-0.04
`emo_Shame`	0.03	0.03	-0.00	-0.03
`emo_Sourness`	0.07	0.17	0.06	0.16
`emo_Teasing`	0.05	0.08	0.05	0.09
`emo_Thankfulness_Gratitude`	0.00	-0.06	-0.09	-0.19
`emo_Triumph`	-0.00	0.00	0.04	0.09
`vn_AGEV_reg`	2.82	-0.13	2.86	-0.10
`vn_AROU_reg`	4.66	2.01	5.02	2.32
`vn_ARSH_reg`	3.37	0.92	2.31	-0.31
`vn_ATCK_reg`	4.37	1.71	4.15	1.53
`vn_BKGN_reg`	3.78	1.41	3.39	0.90
`vn_BRGT_reg`	3.81	2.24	3.98	2.44
`vn_CHNK_reg`	1.65	-0.16	1.93	0.07
`vn_CLRT_reg`	1.59	-0.45	1.09	-0.98
`vn_COGL_reg`	0.29	-1.70	0.68	-1.33
`vn_DARC_reg`	4.07	1.78	3.27	1.20
`vn_DFLU_reg`	-0.61	-2.62	-0.31	-2.37
`vn_EMPH_reg`	3.99	0.91	4.50	1.24
`vn_ESTH_reg`	2.65	0.31	2.23	-0.22
`vn_EXPL_reg`	-0.06	-0.46	-0.02	-0.33
`vn_FOCS_reg`	3.16	0.74	3.18	0.76
`vn_FULL_reg`	3.38	1.80	2.59	0.92
`vn_GEND_reg`	2.40	-1.04	2.53	-0.96
`vn_HARM_reg`	3.64	1.39	2.52	0.05
`vn_METL_reg`	2.64	1.06	2.72	1.14
`vn_RANG_reg`	3.97	1.18	3.92	1.12
`vn_RCQL_reg`	3.82	1.20	3.67	1.03
`vn_REGS_reg`	3.84	2.08	3.33	1.68
`vn_RESP_reg`	3.69	0.95	4.22	1.46
`vn_ROUG_reg`	3.21	1.32	3.88	2.08
`vn_R_CHST_reg`	2.22	0.10	2.00	-0.16
`vn_R_HEAD_reg`	3.30	1.40	3.67	1.86
`vn_R_MASK_reg`	3.27	1.36	3.15	1.23
`vn_R_MIXD_reg`	3.09	1.97	2.34	1.08
`vn_R_NASL_reg`	1.68	-1.06	1.50	-1.23
`vn_R_ORAL_reg`	3.65	1.98	3.16	1.32
`vn_R_THRT_reg`	4.00	2.40	4.20	2.65
`vn_SMTH_reg`	2.52	0.35	2.17	0.02
`vn_STNC_reg`	3.52	0.78	2.74	0.09
`vn_STRU_reg`	1.56	-0.60	1.72	-0.43
`vn_S_ASMR_reg`	0.12	-0.88	0.20	-0.83
`vn_S_AUTH_reg`	1.22	0.13	0.47	-0.59
`vn_S_CART_reg`	2.39	0.59	2.62	0.76
`vn_S_CASU_reg`	1.68	-1.66	1.44	-1.84
`vn_S_CONV_reg`	0.20	-1.82	0.35	-1.70
`vn_S_DRAM_reg`	3.91	1.04	4.54	1.59
`vn_S_FORM_reg`	0.28	-0.89	-0.04	-1.21
`vn_S_MONO_reg`	2.86	0.03	3.38	0.43
`vn_S_NARR_reg`	-0.13	-0.99	-0.20	-1.04
`vn_S_NEWS_reg`	-0.02	-0.75	0.09	-0.56
`vn_S_PLAY_reg`	1.22	-0.86	0.34	-1.53
`vn_S_RANT_reg`	0.89	-0.25	1.33	0.09
`vn_S_STRY_reg`	-0.25	-2.00	-0.35	-2.07
`vn_S_TECH_reg`	-0.15	-0.65	-0.23	-0.71
`vn_S_WHIS_reg`	-0.21	-1.11	0.23	-0.84
`vn_TEMP_reg`	2.34	0.19	2.48	0.31
`vn_TENS_reg`	3.84	2.68	4.49	3.45
`vn_VALN_reg`	2.25	-0.07	1.29	-0.93
`vn_VALS_reg`	2.59	0.07	2.49	-0.03
`vn_VFLX_reg`	2.95	0.58	3.18	0.76
`vn_VOLT_reg`	2.54	-0.05	2.86	0.30
`vn_VULN_reg`	3.76	1.13	4.92	2.31
`vn_WARM_reg`	2.36	-0.24	1.99	-0.65
`genuineness_0_6`	3.82	0.92	3.97	1.01
`blend_0_10`	7.54	0.31	7.22	0.20
`R_quality`	0.44	-1.95	0.40	-2.07
`eiv_extra:Age`	1.01	-7.62	1.50	-5.96
`eiv_extra:Arousal`	2.54	2.87	2.71	3.26
`eiv_extra:Authenticity`	2.97	2.00	3.07	2.63
`eiv_extra:Background_Noise`	0.47	-1.28	0.55	-0.98
`eiv_extra:Confident_vs._Hesitant`	1.27	0.76	1.37	1.10
`eiv_extra:Gender`	0.28	0.90	0.19	0.81
`eiv_extra:High-Pitched_vs._Low-Pitched`	0.78	-4.20	0.90	-3.70
`eiv_extra:Monotone_vs._Expressive`	1.57	-0.62	1.66	-0.41
`eiv_extra:Recording_Quality`	2.01	-0.40	1.85	-0.88
`eiv_extra:Serious_vs._Humorous`	0.09	-2.47	0.01	-2.69
`eiv_extra:Soft_vs._Harsh`	0.54	0.82	0.32	0.12
`eiv_extra:Submissive_vs._Dominant`	-0.02	-1.21	0.01	-1.12
`eiv_extra:Valence`	-0.15	-0.40	-1.06	-2.81
`eiv_extra:Vulnerable_vs._Emotionally_Detached`	0.20	-3.47	0.32	-3.19
`eiv_extra:Warm_vs._Cold`	-0.26	-1.04	-0.51	-1.88
`eiv_extra:score_background_quality`	2.74	-0.82	2.93	-0.53
`eiv_extra:score_content_enjoyment`	3.88	-2.06	3.81	-2.31
`eiv_extra:score_overall_quality`	2.04	-1.20	1.96	-1.36
`eiv_extra:score_speech_quality`	1.74	-0.48	1.81	0.02
`audiobox:CE`	2.73	-2.04	2.65	-2.11
`audiobox:CU`	5.59	-0.06	5.39	-0.26
`audiobox:PC`	1.61	-0.44	1.64	-0.43
`audiobox:PQ`	6.34	-0.80	6.04	-1.14
`dnsmos:SIG_raw`	2.66	-1.86	2.40	-2.24
`dnsmos:BAK_raw`	2.79	-0.38	2.32	-0.79
`dnsmos:OVRL_raw`	2.20	-1.09	1.71	-1.70
`dnsmos:SIG`	2.61	-1.75	2.44	-2.10
`dnsmos:BAK`	3.00	-0.42	2.60	-0.85
`dnsmos:OVRL`	2.16	-1.12	1.79	-1.73
`dnsmos:P808_MOS`	2.71	-1.43	2.12	-2.63
`burst_count_log1p`	0.79	1.22	0.85	1.32
`voiceclap_attribute:Affection`	0.24	-1.28	-0.13	-1.94
`voiceclap_attribute:Age`	2.03	-2.19	1.31	-3.52
`voiceclap_attribute:Amusement`	0.47	0.13	0.21	-0.32
`voiceclap_attribute:Anger`	0.44	-1.10	0.37	-1.22
`voiceclap_attribute:Arousal`	2.04	1.00	2.68	2.03
`voiceclap_attribute:Astonishment_Surprise`	0.46	-0.11	0.61	0.21
`voiceclap_attribute:Authenticity`	2.90	0.77	2.94	1.00
`voiceclap_attribute:Awe`	0.18	-1.37	0.03	-1.94
`voiceclap_attribute:Background_Noise`	0.60	0.14	0.73	0.60
`voiceclap_attribute:Bitterness`	0.05	-2.29	0.24	-1.48
`voiceclap_attribute:Concentration`	0.19	-1.92	0.35	-1.63
`voiceclap_attribute:Confident_vs._Hesitant`	1.31	0.52	1.99	1.96
`voiceclap_attribute:Confusion`	-0.04	-2.06	-0.04	-2.06
`voiceclap_attribute:Contemplation`	0.19	-1.45	0.32	-1.14
`voiceclap_attribute:Contempt`	-0.00	-2.10	-0.11	-2.41
`voiceclap_attribute:Contentment`	0.11	-1.57	-0.01	-1.93
`voiceclap_attribute:Disappointment`	0.10	-2.26	0.63	-0.46
`voiceclap_attribute:Disgust`	-0.03	-3.16	0.01	-2.97
`voiceclap_attribute:Distress`	1.18	0.71	2.21	3.67
`voiceclap_attribute:Doubt`	-0.13	-3.53	-0.05	-3.09
`voiceclap_attribute:Elation`	0.26	-0.70	0.04	-1.26
`voiceclap_attribute:Embarrassment`	-0.09	-1.27	-0.10	-1.29
`voiceclap_attribute:Emotional_Numbness`	0.06	-2.28	-0.12	-2.96
`voiceclap_attribute:Fatigue_Exhaustion`	1.04	2.20	1.31	3.23
`voiceclap_attribute:Fear`	0.20	-1.95	0.56	-0.28
`voiceclap_attribute:Gender`	0.22	0.37	0.04	0.19
`voiceclap_attribute:Helplessness`	1.21	2.04	1.66	3.74
`voiceclap_attribute:High-Pitched_vs._Low-Pitched`	1.24	-1.60	1.35	-1.30
`voiceclap_attribute:Hope_Enthusiasm_Optimism`	0.19	-1.31	-0.00	-1.79
`voiceclap_attribute:Impatience_and_Irritability`	0.42	-1.17	0.24	-1.50
`voiceclap_attribute:Infatuation`	0.03	-1.75	-0.24	-2.55
`voiceclap_attribute:Interest`	0.26	-3.04	-0.09	-3.84
`voiceclap_attribute:Intoxication_Altered_States_of_Consciousness`	0.07	-0.92	0.06	-0.95
`voiceclap_attribute:Jealousy_&_Envy`	-0.09	-2.50	-0.08	-2.45
`voiceclap_attribute:Longing`	0.15	-1.77	0.15	-1.76
`voiceclap_attribute:Malevolence_Malice`	-0.14	-2.82	-0.08	-2.64
`voiceclap_attribute:Monotone_vs._Expressive`	1.60	-0.30	2.21	0.74
`voiceclap_attribute:Pain`	0.81	1.98	1.17	3.60
`voiceclap_attribute:Pleasure_Ecstasy`	0.30	-0.68	0.13	-1.26
`voiceclap_attribute:Pride`	0.04	-2.13	-0.04	-2.35
`voiceclap_attribute:Recording_Quality`	1.93	-1.18	1.52	-2.44
`voiceclap_attribute:Relief`	0.21	-1.98	-0.15	-2.84
`voiceclap_attribute:Sadness`	0.54	-0.66	1.12	1.17
`voiceclap_attribute:Serious_vs._Humorous`	0.62	-0.33	0.82	0.04
`voiceclap_attribute:Sexual_Lust`	-0.03	-1.59	-0.19	-1.96
`voiceclap_attribute:Shame`	-0.02	-1.92	0.03	-1.75
`voiceclap_attribute:Soft_vs._Harsh`	0.73	1.57	1.06	2.50
`voiceclap_attribute:Sourness`	0.05	-2.27	0.17	-1.84
`voiceclap_attribute:Submissive_vs._Dominant`	0.01	-1.70	-0.02	-1.81
`voiceclap_attribute:Teasing`	0.11	-1.14	0.11	-1.13
`voiceclap_attribute:Thankfulness_Gratitude`	0.23	-2.19	-0.12	-2.84
`voiceclap_attribute:Triumph`	0.10	-1.73	-0.06	-2.16
`voiceclap_attribute:Valence`	-0.50	-0.78	-0.82	-1.29
`voiceclap_attribute:Vulnerable_vs._Emotionally_Detached`	0.66	-1.76	0.52	-2.00
`voiceclap_attribute:Warm_vs._Cold`	0.32	0.96	0.32	0.96
`voiceclap_attribute:duration`	5.00	-0.93	3.62	-1.15
`voiceclap_attribute:score_background_quality`	3.08	-0.33	3.05	-0.39
`voiceclap_attribute:score_content_enjoyment`	4.38	-1.87	4.34	-2.13
`voiceclap_attribute:score_overall_quality`	2.11	-1.28	1.96	-1.64
`voiceclap_attribute:score_speech_quality`	1.97	1.10	1.95	0.82
`voiceclap_attribute:talking_speed`	-0.31	-2.49	1.27	-2.06

← All 50 examples Next →