Interactive listening evidence · Base & Medium

Vocal burst 20: Resonant Hum, Sharp Inhale, Soft Hum

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 →

20. Resonant Hum, Sharp Inhale, Soft Hum

mediathek_0301VSTNC__moderately_high__en.c036.k0

vc_sidon · en/synth · 10.62 s · test split

3 Gemini eventsBase count 2.2Medium count 2.5

Source key: mediathek_0301__V__STNC__moderately_high__en.c036.k0 · Audio SHA256: 6c9b86ff1dff7b9dbf4407ba99fc46f90f59ab7a3f923feb7d7e1e422e7a41b0

Gemini annotation · selection aid

4.65–5.15 s: Sharp Inhale · group gasp
8.78–9.48 s: Resonant Hum · group hum
9.85–10.35 s: Soft Hum · group hum

Base predictions

20 ms frame probability; dashed line = 0.5 threshold

3.98–4.90 s: Breath 23%, Contented Sigh 12%, Sharp Inhale 12% · onset 0.77
4.16–5.08 s: Breath 34%, Sharp Inhale 14%, Contented Sigh 9% · onset 0.58
4.30–5.08 s: Breath 37%, Sharp Inhale 14%, Contented Sigh 10% · onset 0.76
4.36–5.16 s: Breath 37%, Sharp Inhale 16%, Contented Sigh 9% · onset 0.77
4.42–5.20 s: Breath 38%, Sharp Inhale 20%, Contented Sigh 8% · onset 0.74
4.50–5.18 s: Breath 37%, Sharp Inhale 23%, Contented Sigh 9% · onset 0.75
4.60–5.26 s: Breath 34%, Sharp Inhale 31%, Contented Sigh 7% · onset 0.69
4.70–5.30 s: Sharp Inhale 36%, Breath 29%, Contented Sigh 6% · onset 0.60
8.38–9.32 s: Hum 46%, Displeased Grunt 4%, Low Mumble 4% · onset 0.63
8.44–9.38 s: Hum 61%, Affirmative Grunt 4%, Low Mumble 3% · onset 0.74
8.50–9.58 s: Hum 83%, Affirmative Grunt 3%, Displeased Grunt 2% · onset 0.71
8.64–9.68 s: Hum 88%, Affirmative Grunt 2%, Displeased Grunt 1% · onset 0.79
8.76–9.68 s: Hum 90%, Affirmative Grunt 2%, Displeased Grunt 1% · onset 0.79
8.82–9.70 s: Hum 91%, Affirmative Grunt 2%, Displeased Grunt 1% · onset 0.80
9.06–9.66 s: Hum 94%, Affirmative Grunt 2%, Displeased Grunt 0% · onset 0.66
9.68–10.22 s: Hum 56%, Other / rare burst 5%, Chuckle 4% · onset 0.64
9.74–10.30 s: Hum 65%, Low Mumble 4%, Other / rare burst 4% · onset 0.66
9.88–10.44 s: Hum 79%, Affirmative Grunt 3%, Low Mumble 3% · onset 0.75
9.98–10.50 s: Hum 81%, Affirmative Grunt 4%, Low Mumble 2% · onset 0.59
10.06–10.60 s: Hum 75%, Affirmative Grunt 6%, Chuckle 2% · onset 0.61
10.14–10.60 s: Hum 75%, Affirmative Grunt 7%, Chuckle 2% · onset 0.67

Frame-positive regions: 2 · CPS 11.13 · Orange timbre cosine 0.903 · identity cosine 0.871

Medium predictions

20 ms frame probability; dashed line = 0.5 threshold

3.76–4.44 s: Breath 19%, Sharp Inhale 10%, Exasperated Sigh 8% · onset 0.57
4.04–4.90 s: Breath 38%, Sharp Inhale 13%, Contented Sigh 10% · onset 0.66
4.12–4.92 s: Breath 40%, Sharp Inhale 13%, Relief Sigh 9% · onset 0.67
4.22–4.92 s: Breath 40%, Sharp Inhale 15%, Relief Sigh 10% · onset 0.65
4.36–4.98 s: Breath 42%, Sharp Inhale 15%, Relief Sigh 11% · onset 0.77
4.44–5.14 s: Breath 40%, Sharp Inhale 17%, Relief Sigh 10% · onset 0.66
4.52–5.06 s: Breath 37%, Sharp Inhale 19%, Relief Sigh 11% · onset 0.70
4.60–5.18 s: Breath 36%, Sharp Inhale 25%, Relief Sigh 9% · onset 0.70
8.56–9.74 s: Hum 81%, Affirmative Grunt 4%, Contented Sigh 2% · onset 0.74
8.66–9.76 s: Hum 81%, Affirmative Grunt 4%, Contented Sigh 2% · onset 0.76
8.76–9.78 s: Hum 82%, Affirmative Grunt 4%, Contented Sigh 1% · onset 0.85
8.86–9.78 s: Hum 82%, Affirmative Grunt 4%, Ahem 1% · onset 0.86
9.04–9.96 s: Hum 81%, Affirmative Grunt 4%, Ahem 1% · onset 0.76
9.18–9.90 s: Hum 79%, Affirmative Grunt 5%, Other / rare burst 2% · onset 0.59
9.26–9.96 s: Hum 74%, Affirmative Grunt 5%, Other / rare burst 2% · onset 0.52
9.64–10.30 s: Hum 72%, Affirmative Grunt 4%, Snort 2% · onset 0.50
9.70–10.46 s: Hum 79%, Affirmative Grunt 5%, Low Mumble 1% · onset 0.53
9.78–10.62 s: Hum 75%, Affirmative Grunt 7%, Low Mumble 2% · onset 0.69
9.84–10.52 s: Hum 79%, Affirmative Grunt 6%, Low Mumble 1% · onset 0.59
9.92–10.60 s: Hum 76%, Affirmative Grunt 8%, Low Mumble 2% · onset 0.64
10.04–10.62 s: Hum 71%, Affirmative Grunt 12%, Ahem 2% · onset 0.60
10.12–10.62 s: Hum 68%, Affirmative Grunt 14%, Ahem 2% · onset 0.63
10.26–10.62 s: Hum 62%, Affirmative Grunt 16%, Ahem 2% · onset 0.60

Frame-positive regions: 2 · CPS 11.16 · Orange timbre cosine 0.907 · identity cosine 0.880

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

Target	Base raw	Base z	Medium raw	Medium z
`emo_Affection`	1.28	2.23	1.21	2.11
`emo_Amusement`	0.55	0.63	0.35	0.40
`emo_Anger`	-0.03	-0.05	0.09	0.13
`emo_Astonishment_Surprise`	0.11	0.18	0.05	0.07
`emo_Awe`	0.50	1.17	0.72	1.70
`emo_Bitterness`	0.02	0.02	0.10	0.21
`emo_Concentration`	2.02	1.87	2.06	1.92
`emo_Confusion`	0.06	0.11	0.06	0.12
`emo_Contemplation`	2.36	3.80	2.24	3.60
`emo_Contempt`	0.00	0.01	0.04	0.08
`emo_Contentment`	2.19	4.26	2.13	4.14
`emo_Disappointment`	0.07	0.10	0.23	0.33
`emo_Disgust`	0.04	0.06	0.04	0.07
`emo_Distress`	0.12	0.14	0.20	0.25
`emo_Doubt`	0.13	0.28	0.10	0.19
`emo_Elation`	0.04	0.04	0.08	0.09
`emo_Embarrassment`	0.07	0.06	0.03	-0.03
`emo_Emotional_Numbness`	0.27	0.29	0.31	0.34
`emo_Fatigue_Exhaustion`	0.45	0.78	1.10	1.99
`emo_Fear`	0.05	0.06	-0.03	-0.07
`emo_Helplessness`	0.12	0.18	0.25	0.37
`emo_Hope_Enthusiasm_Optimism`	1.63	1.99	1.14	1.35
`emo_Impatience_and_Irritability`	0.10	-0.07	0.11	-0.06
`emo_Infatuation`	0.13	0.27	0.07	0.15
`emo_Interest`	2.22	0.70	2.08	0.54
`emo_Intoxication_Altered_States_of_Consciousness`	0.02	0.09	0.03	0.11
`emo_Jealousy_and_Envy`	-0.02	-0.17	-0.04	-0.23
`emo_Longing`	0.81	1.15	0.44	0.57
`emo_Malevolence_Malice`	-0.02	-0.13	-0.01	-0.12
`emo_Pain`	0.04	0.07	0.06	0.11
`emo_Pleasure_Ecstasy`	0.30	0.46	0.26	0.39
`emo_Pride`	0.44	0.87	0.26	0.50
`emo_Relief`	0.53	0.73	0.40	0.54
`emo_Sadness`	0.19	0.25	0.21	0.27
`emo_Sexual_Lust`	0.07	0.09	0.06	0.07
`emo_Shame`	0.03	0.03	0.00	-0.02
`emo_Sourness`	0.04	0.09	0.10	0.23
`emo_Teasing`	0.16	0.29	0.10	0.18
`emo_Thankfulness_Gratitude`	0.17	0.18	0.16	0.17
`emo_Triumph`	0.06	0.13	0.05	0.11
`vn_AGEV_reg`	2.84	-0.12	2.72	-0.21
`vn_AROU_reg`	1.70	-0.57	1.76	-0.52
`vn_ARSH_reg`	2.61	0.04	2.60	0.03
`vn_ATCK_reg`	2.00	-0.12	1.78	-0.29
`vn_BKGN_reg`	4.04	1.75	4.09	1.83
`vn_BRGT_reg`	3.45	1.80	3.41	1.74
`vn_CHNK_reg`	2.53	0.55	2.56	0.58
`vn_CLRT_reg`	3.92	2.02	3.88	1.97
`vn_COGL_reg`	1.33	-0.72	1.35	-0.70
`vn_DARC_reg`	2.53	0.66	2.55	0.68
`vn_DFLU_reg`	0.83	-1.40	0.85	-1.38
`vn_EMPH_reg`	2.96	0.23	2.85	0.16
`vn_ESTH_reg`	4.19	2.28	4.14	2.22
`vn_EXPL_reg`	0.06	-0.07	0.02	-0.20
`vn_FOCS_reg`	3.52	1.06	3.92	1.43
`vn_FULL_reg`	2.91	1.27	2.85	1.20
`vn_GEND_reg`	0.98	-1.93	0.71	-2.11
`vn_HARM_reg`	3.67	1.42	3.72	1.48
`vn_METL_reg`	1.01	-0.63	0.95	-0.70
`vn_RANG_reg`	2.61	-0.34	2.42	-0.55
`vn_RCQL_reg`	4.20	1.63	4.11	1.53
`vn_REGS_reg`	3.80	2.05	3.77	2.03
`vn_RESP_reg`	2.57	-0.10	2.67	-0.01
`vn_ROUG_reg`	1.05	-1.11	1.33	-0.79
`vn_R_CHST_reg`	2.06	-0.09	2.15	0.01
`vn_R_HEAD_reg`	3.16	1.23	3.24	1.33
`vn_R_MASK_reg`	3.02	1.10	3.00	1.09
`vn_R_MIXD_reg`	3.72	2.71	3.73	2.73
`vn_R_NASL_reg`	1.79	-0.95	1.98	-0.78
`vn_R_ORAL_reg`	3.77	2.14	3.82	2.21
`vn_R_THRT_reg`	2.18	0.13	2.10	0.04
`vn_SMTH_reg`	3.50	1.24	3.57	1.31
`vn_STNC_reg`	2.62	-0.01	2.45	-0.17
`vn_STRU_reg`	3.95	1.90	3.97	1.91
`vn_S_ASMR_reg`	2.18	0.58	2.33	0.68
`vn_S_AUTH_reg`	1.63	0.52	1.54	0.44
`vn_S_CART_reg`	0.62	-0.67	0.57	-0.70
`vn_S_CASU_reg`	3.17	-0.49	3.41	-0.30
`vn_S_CONV_reg`	2.86	0.20	3.08	0.37
`vn_S_DRAM_reg`	2.13	-0.51	2.42	-0.26
`vn_S_FORM_reg`	1.56	0.36	1.59	0.39
`vn_S_MONO_reg`	3.30	0.37	3.57	0.58
`vn_S_NARR_reg`	3.03	1.19	3.12	1.26
`vn_S_NEWS_reg`	0.47	0.10	0.28	-0.23
`vn_S_PLAY_reg`	1.40	-0.72	1.57	-0.60
`vn_S_RANT_reg`	-0.02	-0.96	-0.12	-1.03
`vn_S_STRY_reg`	2.52	0.03	2.63	0.11
`vn_S_TECH_reg`	1.58	0.76	1.73	0.88
`vn_S_WHIS_reg`	1.17	-0.26	1.00	-0.37
`vn_TEMP_reg`	2.15	0.03	2.01	-0.09
`vn_TENS_reg`	1.52	-0.04	1.50	-0.07
`vn_VALN_reg`	3.07	0.67	3.28	0.85
`vn_VALS_reg`	2.91	0.37	2.96	0.41
`vn_VFLX_reg`	2.81	0.46	2.82	0.47
`vn_VOLT_reg`	1.55	-1.17	1.53	-1.19
`vn_VULN_reg`	3.04	0.40	3.11	0.46
`vn_WARM_reg`	3.59	1.12	3.67	1.20
`genuineness_0_6`	4.44	1.30	4.56	1.37
`blend_0_10`	7.40	0.27	7.44	0.28
`R_quality`	0.61	-1.43	0.60	-1.47
`eiv_extra:Age`	3.13	-0.41	3.25	-0.00
`eiv_extra:Arousal`	1.23	-0.13	1.35	0.14
`eiv_extra:Authenticity`	2.99	2.14	2.96	1.89
`eiv_extra:Background_Noise`	0.57	-0.90	0.58	-0.86
`eiv_extra:Confident_vs._Hesitant`	1.11	0.24	1.13	0.31
`eiv_extra:Gender`	1.23	1.85	1.11	1.73
`eiv_extra:High-Pitched_vs._Low-Pitched`	1.62	-0.84	1.67	-0.61
`eiv_extra:Monotone_vs._Expressive`	2.37	1.09	2.25	0.83
`eiv_extra:Recording_Quality`	2.67	1.57	2.49	1.04
`eiv_extra:Serious_vs._Humorous`	1.27	1.01	1.14	0.60
`eiv_extra:Soft_vs._Harsh`	0.96	2.12	0.90	1.93
`eiv_extra:Submissive_vs._Dominant`	0.19	-0.58	0.06	-0.99
`eiv_extra:Valence`	0.96	2.51	0.31	0.81
`eiv_extra:Vulnerable_vs._Emotionally_Detached`	1.40	-0.72	1.41	-0.69
`eiv_extra:Warm_vs._Cold`	0.95	3.00	0.62	1.90
`eiv_extra:score_background_quality`	3.85	0.79	3.69	0.57
`eiv_extra:score_content_enjoyment`	4.76	0.82	4.72	0.70
`eiv_extra:score_overall_quality`	3.16	1.00	3.05	0.78
`eiv_extra:score_speech_quality`	1.82	0.10	1.84	0.22
`audiobox:CE`	6.32	1.49	6.41	1.58
`audiobox:CU`	7.44	1.79	7.41	1.76
`audiobox:PC`	1.33	-0.62	1.48	-0.53
`audiobox:PQ`	7.88	0.96	7.82	0.89
`dnsmos:SIG_raw`	4.32	0.63	4.32	0.63
`dnsmos:BAK_raw`	4.57	1.21	4.53	1.17
`dnsmos:OVRL_raw`	4.14	1.30	4.10	1.25
`dnsmos:SIG`	3.72	0.47	3.72	0.46
`dnsmos:BAK`	4.23	0.90	4.18	0.86
`dnsmos:OVRL`	3.51	1.11	3.49	1.07
`dnsmos:P808_MOS`	4.13	1.43	4.10	1.36
`burst_count_log1p`	1.15	1.77	1.26	1.95
`voiceclap_attribute:Affection`	1.03	0.16	1.17	0.41
`voiceclap_attribute:Age`	3.20	-0.06	3.24	0.03
`voiceclap_attribute:Amusement`	0.78	0.67	0.79	0.69
`voiceclap_attribute:Anger`	-0.15	-2.26	-0.20	-2.35
`voiceclap_attribute:Arousal`	1.25	-0.27	1.08	-0.55
`voiceclap_attribute:Astonishment_Surprise`	0.07	-0.92	-0.07	-1.20
`voiceclap_attribute:Authenticity`	3.22	2.71	3.19	2.52
`voiceclap_attribute:Awe`	0.63	0.36	0.56	0.08
`voiceclap_attribute:Background_Noise`	0.23	-1.27	0.29	-1.05
`voiceclap_attribute:Bitterness`	0.05	-2.32	0.07	-2.22
`voiceclap_attribute:Concentration`	1.73	0.97	1.77	1.05
`voiceclap_attribute:Confident_vs._Hesitant`	1.29	0.47	1.44	0.78
`voiceclap_attribute:Confusion`	-0.04	-2.06	-0.08	-2.15
`voiceclap_attribute:Contemplation`	2.43	4.07	2.53	4.32
`voiceclap_attribute:Contempt`	-0.01	-2.13	-0.01	-2.11
`voiceclap_attribute:Contentment`	2.22	5.32	2.21	5.29
`voiceclap_attribute:Disappointment`	0.07	-2.37	0.09	-2.30
`voiceclap_attribute:Disgust`	-0.01	-3.04	-0.01	-3.06
`voiceclap_attribute:Distress`	0.19	-2.10	0.18	-2.14
`voiceclap_attribute:Doubt`	0.19	-1.85	0.29	-1.28
`voiceclap_attribute:Elation`	0.58	0.11	0.38	-0.41
`voiceclap_attribute:Embarrassment`	-0.09	-1.27	-0.07	-1.19
`voiceclap_attribute:Emotional_Numbness`	0.03	-2.37	0.05	-2.29
`voiceclap_attribute:Fatigue_Exhaustion`	0.74	1.05	0.67	0.80
`voiceclap_attribute:Fear`	-0.11	-3.42	-0.12	-3.47
`voiceclap_attribute:Gender`	1.68	1.82	1.49	1.63
`voiceclap_attribute:Helplessness`	0.15	-1.91	0.21	-1.68
`voiceclap_attribute:High-Pitched_vs._Low-Pitched`	1.39	-1.20	1.49	-0.93
`voiceclap_attribute:Hope_Enthusiasm_Optimism`	1.62	2.32	1.30	1.51
`voiceclap_attribute:Impatience_and_Irritability`	-0.01	-1.97	-0.06	-2.05
`voiceclap_attribute:Infatuation`	0.16	-1.34	0.16	-1.33
`voiceclap_attribute:Interest`	2.15	1.26	2.04	1.01
`voiceclap_attribute:Intoxication_Altered_States_of_Consciousness`	-0.05	-1.19	0.14	-0.79
`voiceclap_attribute:Jealousy_&_Envy`	0.04	-1.96	0.00	-2.13
`voiceclap_attribute:Longing`	0.50	-0.16	0.61	0.32
`voiceclap_attribute:Malevolence_Malice`	0.11	-2.10	0.01	-2.39
`voiceclap_attribute:Monotone_vs._Expressive`	1.86	0.14	1.87	0.16
`voiceclap_attribute:Pain`	-0.01	-1.79	0.01	-1.69
`voiceclap_attribute:Pleasure_Ecstasy`	0.50	0.00	0.44	-0.20
`voiceclap_attribute:Pride`	0.52	-0.74	0.26	-1.49
`voiceclap_attribute:Recording_Quality`	2.90	1.80	2.85	1.64
`voiceclap_attribute:Relief`	0.57	-1.11	0.49	-1.28
`voiceclap_attribute:Sadness`	0.14	-1.95	0.28	-1.51
`voiceclap_attribute:Serious_vs._Humorous`	0.77	-0.07	0.94	0.24
`voiceclap_attribute:Sexual_Lust`	0.16	-1.13	0.14	-1.19
`voiceclap_attribute:Shame`	-0.10	-2.20	-0.05	-2.03
`voiceclap_attribute:Soft_vs._Harsh`	0.91	2.08	1.00	2.34
`voiceclap_attribute:Sourness`	0.04	-2.30	0.07	-2.17
`voiceclap_attribute:Submissive_vs._Dominant`	0.22	-1.13	0.06	-1.56
`voiceclap_attribute:Teasing`	0.40	-0.37	0.30	-0.64
`voiceclap_attribute:Thankfulness_Gratitude`	0.48	-1.71	0.42	-1.83
`voiceclap_attribute:Triumph`	0.10	-1.72	-0.03	-2.06
`voiceclap_attribute:Valence`	0.66	1.05	0.47	0.75
`voiceclap_attribute:Vulnerable_vs._Emotionally_Detached`	1.18	-0.82	1.22	-0.76
`voiceclap_attribute:Warm_vs._Cold`	0.84	2.27	0.79	2.15
`voiceclap_attribute:duration`	11.34	0.07	10.81	-0.02
`voiceclap_attribute:score_background_quality`	3.64	0.79	3.58	0.68
`voiceclap_attribute:score_content_enjoyment`	4.78	0.82	4.70	0.32
`voiceclap_attribute:score_overall_quality`	2.95	0.77	2.93	0.71
`voiceclap_attribute:score_speech_quality`	1.89	-0.05	1.90	0.07
`voiceclap_attribute:talking_speed`	8.74	-0.08	9.83	0.21

← All 50 examples ← Previous Next →