Interactive listening evidence · Base & Medium

Vocal burst 09: Scream

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 →

09. Scream

k498_age2_bg1VROUG__moderately_highdec000

vprof_repair · de/synth · 10.32 s · test split

2 Gemini eventsBase count 1.5Medium count 1.5

Source key: k498_age2_bg1__V__ROUG__moderately_high__de__c000 · Audio SHA256: 7d92d4a8a2e1e0e2b6ac52c414eec119e05d53d6475f7952c49809a39415d7df

Gemini annotation · selection aid

0.05–1.48 s: Scream · group scream
5.95–7.42 s: Scream · group scream

Base predictions

20 ms frame probability; dashed line = 0.5 threshold

0.00–0.98 s: Scream 59%, Shriek 23%, Other / rare burst 3% · onset 0.99
5.94–7.08 s: Scream 62%, Shriek 18%, Other / rare burst 3% · onset 0.68
6.12–7.26 s: Scream 76%, Shriek 14%, Other / rare burst 2% · onset 0.78
6.24–7.50 s: Scream 84%, Shriek 9%, Other / rare burst 1% · onset 0.83
6.32–7.36 s: Scream 81%, Shriek 10%, Other / rare burst 2% · onset 0.69

Frame-positive regions: 3 · CPS 13.07 · Orange timbre cosine 0.862 · identity cosine 0.801

Medium predictions

20 ms frame probability; dashed line = 0.5 threshold

0.00–1.14 s: Scream 69%, Shriek 19%, Growl 1% · onset 0.97
5.98–6.96 s: Scream 54%, Shriek 17%, Surprised Gasp 4% · onset 0.70
6.10–6.98 s: Scream 55%, Shriek 19%, Surprised Gasp 3% · onset 0.65
6.24–7.62 s: Scream 83%, Shriek 11%, Growl 1% · onset 0.62
6.32–7.46 s: Scream 81%, Shriek 11%, Growl 1% · onset 0.66

Frame-positive regions: 3 · CPS 11.55 · Orange timbre cosine 0.892 · identity cosine 0.839

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	0.12	0.19
`emo_Amusement`	0.63	0.71	0.88	0.99
`emo_Anger`	0.27	0.44	0.10	0.16
`emo_Astonishment_Surprise`	0.82	1.42	0.56	0.97
`emo_Awe`	0.09	0.20	0.07	0.17
`emo_Bitterness`	0.07	0.13	0.10	0.21
`emo_Concentration`	1.54	1.22	1.68	1.40
`emo_Confusion`	0.28	0.51	0.07	0.12
`emo_Contemplation`	1.07	1.65	0.97	1.48
`emo_Contempt`	0.03	0.06	0.11	0.24
`emo_Contentment`	0.51	0.98	0.71	1.38
`emo_Disappointment`	0.07	0.10	0.10	0.14
`emo_Disgust`	0.10	0.19	0.08	0.15
`emo_Distress`	1.71	2.08	0.90	1.10
`emo_Doubt`	0.45	0.95	0.24	0.51
`emo_Elation`	0.16	0.20	0.35	0.46
`emo_Embarrassment`	0.01	-0.07	0.04	0.00
`emo_Emotional_Numbness`	0.07	0.07	0.08	0.08
`emo_Fatigue_Exhaustion`	0.52	0.92	0.36	0.62
`emo_Fear`	1.38	2.24	0.94	1.52
`emo_Helplessness`	1.12	1.61	0.76	1.10
`emo_Hope_Enthusiasm_Optimism`	0.47	0.46	0.80	0.89
`emo_Impatience_and_Irritability`	0.55	0.57	0.21	0.09
`emo_Infatuation`	-0.02	-0.01	0.02	0.07
`emo_Interest`	1.73	0.15	1.96	0.41
`emo_Intoxication_Altered_States_of_Consciousness`	0.08	0.20	0.03	0.10
`emo_Jealousy_and_Envy`	0.02	-0.08	0.05	-0.02
`emo_Longing`	0.03	-0.09	0.08	-0.01
`emo_Malevolence_Malice`	0.09	0.07	0.03	-0.04
`emo_Pain`	0.66	1.14	0.16	0.28
`emo_Pleasure_Ecstasy`	0.10	0.13	0.04	0.04
`emo_Pride`	0.46	0.90	0.50	0.99
`emo_Relief`	0.07	0.06	0.18	0.22
`emo_Sadness`	0.39	0.51	-0.04	-0.05
`emo_Sexual_Lust`	0.01	-0.03	-0.01	-0.08
`emo_Shame`	0.00	-0.02	0.05	0.08
`emo_Sourness`	0.12	0.30	0.11	0.25
`emo_Teasing`	0.33	0.61	0.32	0.59
`emo_Thankfulness_Gratitude`	0.04	0.00	0.03	-0.02
`emo_Triumph`	0.14	0.28	0.18	0.36
`vn_AGEV_reg`	2.60	-0.31	2.83	-0.12
`vn_AROU_reg`	2.65	0.26	3.08	0.63
`vn_ARSH_reg`	2.70	0.14	2.66	0.09
`vn_ATCK_reg`	2.85	0.53	3.43	0.98
`vn_BKGN_reg`	3.63	1.21	3.66	1.25
`vn_BRGT_reg`	3.05	1.31	3.56	1.93
`vn_CHNK_reg`	2.84	0.80	3.27	1.15
`vn_CLRT_reg`	3.41	1.47	3.73	1.81
`vn_COGL_reg`	0.90	-1.12	0.39	-1.61
`vn_DARC_reg`	2.87	0.91	3.05	1.04
`vn_DFLU_reg`	0.26	-1.88	-0.02	-2.12
`vn_EMPH_reg`	3.90	0.85	3.79	0.77
`vn_ESTH_reg`	3.54	1.46	3.43	1.32
`vn_EXPL_reg`	0.13	0.13	0.11	0.06
`vn_FOCS_reg`	4.32	1.80	4.24	1.72
`vn_FULL_reg`	2.99	1.37	2.73	1.07
`vn_GEND_reg`	2.59	-0.92	2.45	-1.01
`vn_HARM_reg`	2.54	0.07	2.90	0.50
`vn_METL_reg`	1.77	0.16	2.05	0.44
`vn_RANG_reg`	3.41	0.55	3.50	0.65
`vn_RCQL_reg`	3.74	1.11	4.01	1.41
`vn_REGS_reg`	2.89	1.33	2.97	1.40
`vn_RESP_reg`	3.18	0.47	2.65	-0.03
`vn_ROUG_reg`	2.36	0.37	2.15	0.14
`vn_R_CHST_reg`	2.27	0.16	2.30	0.20
`vn_R_HEAD_reg`	2.80	0.79	3.07	1.12
`vn_R_MASK_reg`	2.95	1.04	3.29	1.37
`vn_R_MIXD_reg`	3.27	2.18	3.00	1.86
`vn_R_NASL_reg`	1.27	-1.45	1.82	-0.93
`vn_R_ORAL_reg`	3.32	1.53	3.45	1.71
`vn_R_THRT_reg`	2.48	0.51	2.57	0.62
`vn_SMTH_reg`	3.51	1.25	3.70	1.42
`vn_STNC_reg`	3.27	0.56	3.53	0.79
`vn_STRU_reg`	3.54	1.46	4.03	1.98
`vn_S_ASMR_reg`	1.00	-0.26	0.80	-0.41
`vn_S_AUTH_reg`	2.33	1.19	2.92	1.75
`vn_S_CART_reg`	1.43	-0.09	1.30	-0.19
`vn_S_CASU_reg`	2.87	-0.72	2.14	-1.30
`vn_S_CONV_reg`	2.80	0.16	2.20	-0.30
`vn_S_DRAM_reg`	3.70	0.85	3.72	0.87
`vn_S_FORM_reg`	1.57	0.37	1.85	0.64
`vn_S_MONO_reg`	2.97	0.11	3.38	0.43
`vn_S_NARR_reg`	2.98	1.16	3.70	1.65
`vn_S_NEWS_reg`	0.15	-0.46	0.40	-0.01
`vn_S_PLAY_reg`	1.80	-0.42	1.67	-0.51
`vn_S_RANT_reg`	0.84	-0.29	0.58	-0.49
`vn_S_STRY_reg`	2.60	0.09	2.88	0.29
`vn_S_TECH_reg`	1.03	0.31	1.68	0.84
`vn_S_WHIS_reg`	1.64	0.03	0.90	-0.43
`vn_TEMP_reg`	2.72	0.51	3.02	0.75
`vn_TENS_reg`	2.62	1.25	2.75	1.39
`vn_VALN_reg`	2.73	0.36	2.92	0.53
`vn_VALS_reg`	2.87	0.32	2.74	0.21
`vn_VFLX_reg`	2.84	0.48	3.20	0.78
`vn_VOLT_reg`	2.36	-0.25	2.33	-0.29
`vn_VULN_reg`	2.07	-0.58	1.81	-0.85
`vn_WARM_reg`	2.79	0.23	2.87	0.33
`genuineness_0_6`	3.89	0.96	3.55	0.75
`blend_0_10`	6.33	-0.13	6.03	-0.24
`R_quality`	0.46	-1.88	0.41	-2.04
`eiv_extra:Age`	1.36	-6.46	0.67	-8.79
`eiv_extra:Arousal`	2.65	3.12	2.66	3.16
`eiv_extra:Authenticity`	2.86	1.25	2.79	0.79
`eiv_extra:Background_Noise`	0.96	0.56	0.94	0.51
`eiv_extra:Confident_vs._Hesitant`	1.76	2.39	1.63	1.94
`eiv_extra:Gender`	0.24	0.86	-0.13	0.49
`eiv_extra:High-Pitched_vs._Low-Pitched`	1.48	-1.39	1.64	-0.76
`eiv_extra:Monotone_vs._Expressive`	2.75	1.90	2.65	1.67
`eiv_extra:Recording_Quality`	1.79	-1.07	1.82	-0.99
`eiv_extra:Serious_vs._Humorous`	1.44	1.51	1.37	1.29
`eiv_extra:Soft_vs._Harsh`	0.73	1.40	0.60	1.01
`eiv_extra:Submissive_vs._Dominant`	0.17	-0.64	0.35	-0.09
`eiv_extra:Valence`	-0.48	-1.28	-0.25	-0.67
`eiv_extra:Vulnerable_vs._Emotionally_Detached`	0.93	-1.79	1.05	-1.53
`eiv_extra:Warm_vs._Cold`	-0.01	-0.21	-0.08	-0.44
`eiv_extra:score_background_quality`	3.04	-0.38	3.10	-0.29
`eiv_extra:score_content_enjoyment`	4.27	-0.80	4.40	-0.34
`eiv_extra:score_overall_quality`	2.47	-0.37	2.58	-0.13
`eiv_extra:score_speech_quality`	1.69	-0.82	1.69	-0.84
`audiobox:CE`	4.50	-0.29	4.84	0.04
`audiobox:CU`	6.36	0.71	6.52	0.87
`audiobox:PC`	2.19	-0.09	2.45	0.07
`audiobox:PQ`	6.90	-0.17	7.26	0.25
`dnsmos:SIG_raw`	3.56	-0.51	3.55	-0.52
`dnsmos:BAK_raw`	2.08	-1.01	2.36	-0.75
`dnsmos:OVRL_raw`	2.36	-0.90	2.44	-0.79
`dnsmos:SIG`	3.23	-0.52	3.26	-0.46
`dnsmos:BAK`	2.40	-1.07	2.66	-0.78
`dnsmos:OVRL`	2.28	-0.92	2.37	-0.77
`dnsmos:P808_MOS`	2.97	-0.91	3.07	-0.72
`burst_count_log1p`	0.91	1.41	0.92	1.42
`voiceclap_attribute:Affection`	0.08	-1.56	0.11	-1.50
`voiceclap_attribute:Age`	1.65	-2.88	1.85	-2.52
`voiceclap_attribute:Amusement`	0.84	0.78	0.99	1.05
`voiceclap_attribute:Anger`	0.42	-1.13	-0.16	-2.27
`voiceclap_attribute:Arousal`	2.49	1.71	2.16	1.18
`voiceclap_attribute:Astonishment_Surprise`	0.54	0.07	0.35	-0.33
`voiceclap_attribute:Authenticity`	2.97	1.19	2.92	0.92
`voiceclap_attribute:Awe`	0.19	-1.36	0.07	-1.82
`voiceclap_attribute:Background_Noise`	0.79	0.85	0.83	1.00
`voiceclap_attribute:Bitterness`	0.12	-2.02	-0.05	-2.72
`voiceclap_attribute:Concentration`	1.44	0.43	1.44	0.42
`voiceclap_attribute:Confident_vs._Hesitant`	1.72	1.40	1.50	0.91
`voiceclap_attribute:Confusion`	0.11	-1.60	-0.04	-2.04
`voiceclap_attribute:Contemplation`	0.97	0.48	0.75	-0.07
`voiceclap_attribute:Contempt`	0.10	-1.80	-0.14	-2.51
`voiceclap_attribute:Contentment`	0.83	0.79	1.13	1.78
`voiceclap_attribute:Disappointment`	0.51	-0.84	0.03	-2.51
`voiceclap_attribute:Disgust`	0.10	-2.55	-0.06	-3.33
`voiceclap_attribute:Distress`	0.97	0.13	0.73	-0.55
`voiceclap_attribute:Doubt`	0.32	-1.15	0.09	-2.35
`voiceclap_attribute:Elation`	0.41	-0.33	0.49	-0.13
`voiceclap_attribute:Embarrassment`	-0.04	-1.11	-0.03	-1.07
`voiceclap_attribute:Emotional_Numbness`	0.16	-1.90	0.32	-1.31
`voiceclap_attribute:Fatigue_Exhaustion`	1.14	2.61	0.97	1.94
`voiceclap_attribute:Fear`	0.27	-1.65	0.35	-1.26
`voiceclap_attribute:Gender`	0.40	0.55	0.58	0.72
`voiceclap_attribute:Helplessness`	0.72	0.21	0.57	-0.32
`voiceclap_attribute:High-Pitched_vs._Low-Pitched`	1.60	-0.64	1.51	-0.88
`voiceclap_attribute:Hope_Enthusiasm_Optimism`	0.66	-0.12	0.92	0.54
`voiceclap_attribute:Impatience_and_Irritability`	0.45	-1.11	0.09	-1.78
`voiceclap_attribute:Infatuation`	0.08	-1.59	0.15	-1.39
`voiceclap_attribute:Interest`	1.59	-0.02	1.72	0.27
`voiceclap_attribute:Intoxication_Altered_States_of_Consciousness`	-0.06	-1.21	-0.08	-1.26
`voiceclap_attribute:Jealousy_&_Envy`	0.02	-2.07	0.04	-1.96
`voiceclap_attribute:Longing`	0.14	-1.82	0.08	-2.08
`voiceclap_attribute:Malevolence_Malice`	0.13	-2.04	0.17	-1.92
`voiceclap_attribute:Monotone_vs._Expressive`	2.70	1.56	2.70	1.56
`voiceclap_attribute:Pain`	0.44	0.26	0.45	0.31
`voiceclap_attribute:Pleasure_Ecstasy`	0.14	-1.19	0.18	-1.08
`voiceclap_attribute:Pride`	0.53	-0.72	0.58	-0.58
`voiceclap_attribute:Recording_Quality`	2.08	-0.73	2.05	-0.79
`voiceclap_attribute:Relief`	0.45	-1.40	0.46	-1.37
`voiceclap_attribute:Sadness`	0.25	-1.61	0.09	-2.11
`voiceclap_attribute:Serious_vs._Humorous`	1.27	0.82	1.56	1.33
`voiceclap_attribute:Sexual_Lust`	0.05	-1.41	0.32	-0.76
`voiceclap_attribute:Shame`	0.01	-1.81	0.00	-1.85
`voiceclap_attribute:Soft_vs._Harsh`	0.55	1.09	0.57	1.13
`voiceclap_attribute:Sourness`	0.35	-1.24	0.05	-2.25
`voiceclap_attribute:Submissive_vs._Dominant`	0.40	-0.61	0.47	-0.44
`voiceclap_attribute:Teasing`	0.50	-0.10	0.52	-0.06
`voiceclap_attribute:Thankfulness_Gratitude`	-0.25	-3.09	-0.04	-2.69
`voiceclap_attribute:Triumph`	0.40	-0.87	0.41	-0.84
`voiceclap_attribute:Valence`	-0.19	-0.29	-0.15	-0.23
`voiceclap_attribute:Vulnerable_vs._Emotionally_Detached`	0.95	-1.24	1.13	-0.92
`voiceclap_attribute:Warm_vs._Cold`	0.13	0.48	0.37	1.08
`voiceclap_attribute:duration`	10.40	-0.08	10.93	0.00
`voiceclap_attribute:score_background_quality`	3.07	-0.35	2.93	-0.63
`voiceclap_attribute:score_content_enjoyment`	4.63	-0.18	4.73	0.48
`voiceclap_attribute:score_overall_quality`	2.49	-0.35	2.50	-0.32
`voiceclap_attribute:score_speech_quality`	1.79	-1.42	1.82	-1.02
`voiceclap_attribute:talking_speed`	7.05	-0.53	8.58	-0.12

← All 50 examples ← Previous Next →