Interactive listening evidence · Base & Medium

Vocal burst 16: Humming, 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 →

16. Humming, Soft Hum

mediathek_0096VFOCS__moderately_low__de.c013

vprof_original · de/synth · 6.48 s · test split

4 Gemini eventsBase count 3.8Medium count 3.8

Source key: mediathek_0096__V__FOCS__moderately_low__de.c013 · Audio SHA256: 136362229ee5be867c539e1201e3708f0daaa891df0f6708ab33387699d07c47

Gemini annotation · selection aid

0.00–0.88 s: Soft Hum · group hum
1.76–2.85 s: Humming · group hum
3.42–4.19 s: Soft Hum · group hum
4.88–6.32 s: Humming · group hum

Base predictions

20 ms frame probability; dashed line = 0.5 threshold

0.00–0.78 s: Hum 92%, Affirmative Grunt 3%, Other / rare burst 1% · onset 0.97
1.22–1.86 s: Hum 31%, Breath 12%, Low Mumble 11% · onset 0.68
1.48–2.36 s: Hum 63%, Low Mumble 8%, Breath 4% · onset 0.85
1.56–2.36 s: Hum 67%, Low Mumble 7%, Breath 3% · onset 0.63
1.62–2.50 s: Hum 71%, Low Mumble 6%, Other / rare burst 3% · onset 0.71
1.72–2.58 s: Hum 72%, Low Mumble 5%, Affirmative Grunt 3% · onset 0.92
1.88–2.64 s: Hum 76%, Low Mumble 4%, Affirmative Grunt 3% · onset 0.74
1.98–2.72 s: Hum 77%, Low Mumble 4%, Affirmative Grunt 3% · onset 0.92
2.06–2.86 s: Hum 81%, Affirmative Grunt 4%, Low Mumble 3% · onset 0.72
2.24–3.08 s: Hum 89%, Affirmative Grunt 3%, Other / rare burst 1% · onset 0.61
2.48–3.02 s: Hum 84%, Affirmative Grunt 5%, Low Mumble 2% · onset 0.83
2.72–3.30 s: Hum 90%, Affirmative Grunt 5%, Other / rare burst 1% · onset 0.86
3.22–3.90 s: Hum 44%, Other / rare burst 7%, Affirmative Grunt 6% · onset 0.67
3.46–4.02 s: Hum 45%, Other / rare burst 7%, Low Mumble 6% · onset 0.70
3.68–4.36 s: Hum 58%, Effort Grunt 5%, Other / rare burst 5% · onset 0.73
3.74–4.48 s: Hum 72%, Affirmative Grunt 3%, Other / rare burst 3% · onset 0.83
3.84–4.60 s: Hum 84%, Affirmative Grunt 2%, Other / rare burst 2% · onset 0.62
3.90–4.68 s: Hum 89%, Affirmative Grunt 2%, Other / rare burst 2% · onset 0.63
3.98–4.60 s: Hum 88%, Affirmative Grunt 2%, Other / rare burst 1% · onset 0.89
4.08–4.62 s: Hum 90%, Affirmative Grunt 2%, Other / rare burst 1% · onset 0.63
4.22–4.82 s: Hum 93%, Affirmative Grunt 2%, Other / rare burst 1% · onset 0.69
4.30–4.98 s: Hum 91%, Affirmative Grunt 2%, Other / rare burst 2% · onset 0.66
4.90–5.46 s: Hum 49%, Other / rare burst 11%, Effort Grunt 9% · onset 0.67
4.98–5.54 s: Hum 62%, Other / rare burst 8%, Effort Grunt 5% · onset 0.74
5.04–5.62 s: Hum 74%, Other / rare burst 5%, Affirmative Grunt 5% · onset 0.62
5.10–5.70 s: Hum 83%, Affirmative Grunt 4%, Other / rare burst 3% · onset 0.74
5.20–5.84 s: Hum 89%, Affirmative Grunt 3%, Other / rare burst 2% · onset 0.66
5.34–6.00 s: Hum 93%, Affirmative Grunt 3%, Other / rare burst 1% · onset 0.64
5.42–6.08 s: Hum 93%, Affirmative Grunt 3%, Other / rare burst 1% · onset 0.74
5.48–6.04 s: Hum 93%, Affirmative Grunt 3%, Other / rare burst 1% · onset 0.72
5.86–6.32 s: Hum 88%, Affirmative Grunt 6%, Other / rare burst 1% · onset 0.62
5.98–6.36 s: Hum 85%, Affirmative Grunt 7%, Other / rare burst 1% · onset 0.78

Frame-positive regions: 1 · CPS 0.91 · Orange timbre cosine 0.745 · identity cosine 0.565

Medium predictions

20 ms frame probability; dashed line = 0.5 threshold

0.00–0.76 s: Hum 92%, Other / rare burst 2%, Affirmative Grunt 1% · onset 0.99
0.94–1.60 s: Hum 32%, Breath 9%, Sharp Inhale 6% · onset 0.57
1.16–2.04 s: Hum 41%, Breath 5%, Affirmative Grunt 5% · onset 0.60
1.22–1.94 s: Hum 36%, Breath 6%, Affirmative Grunt 5% · onset 0.70
1.30–2.22 s: Hum 63%, Affirmative Grunt 5%, Low Mumble 4% · onset 0.60
1.44–2.24 s: Hum 65%, Affirmative Grunt 6%, Low Mumble 3% · onset 0.71
1.50–2.26 s: Hum 69%, Affirmative Grunt 6%, Low Mumble 3% · onset 0.78
1.56–2.40 s: Hum 81%, Affirmative Grunt 3%, Low Mumble 3% · onset 0.71
1.62–2.42 s: Hum 83%, Affirmative Grunt 3%, Low Mumble 3% · onset 0.77
1.70–2.44 s: Hum 85%, Affirmative Grunt 3%, Low Mumble 2% · onset 0.76
1.82–2.60 s: Hum 85%, Affirmative Grunt 3%, Low Mumble 2% · onset 0.75
1.94–2.62 s: Hum 87%, Affirmative Grunt 2%, Low Mumble 2% · onset 0.82
2.12–2.78 s: Hum 87%, Affirmative Grunt 2%, Low Mumble 2% · onset 0.67
2.50–3.18 s: Hum 90%, Affirmative Grunt 2%, Other / rare burst 2% · onset 0.77
2.62–3.30 s: Hum 91%, Affirmative Grunt 2%, Other / rare burst 2% · onset 0.68
2.76–3.40 s: Hum 89%, Other / rare burst 2%, Affirmative Grunt 2% · onset 0.83
3.24–4.00 s: Hum 43%, Other / rare burst 7%, Breath 5% · onset 0.68
3.42–4.26 s: Hum 51%, Purr 6%, Other / rare burst 5% · onset 0.78
3.70–4.58 s: Hum 82%, Affirmative Grunt 2%, Other / rare burst 2% · onset 0.81
3.98–4.74 s: Hum 92%, Other / rare burst 2%, Low Mumble 1% · onset 0.70
4.10–4.90 s: Hum 92%, Other / rare burst 2%, Low Mumble 1% · onset 0.72
4.16–4.94 s: Hum 92%, Other / rare burst 2%, Low Mumble 1% · onset 0.69
4.30–5.06 s: Hum 91%, Other / rare burst 3%, Low Mumble 1% · onset 0.78
4.96–5.64 s: Hum 89%, Affirmative Grunt 2%, Effort Grunt 2% · onset 0.64
5.02–5.90 s: Hum 95%, Other / rare burst 1%, Affirmative Grunt 1% · onset 0.67
5.08–5.90 s: Hum 95%, Other / rare burst 1%, Affirmative Grunt 1% · onset 0.88
5.14–6.02 s: Hum 95%, Other / rare burst 1%, Affirmative Grunt 1% · onset 0.79
5.20–5.94 s: Hum 96%, Other / rare burst 1%, Affirmative Grunt 1% · onset 0.78
5.32–6.12 s: Hum 95%, Affirmative Grunt 1%, Other / rare burst 1% · onset 0.67
5.44–6.32 s: Hum 95%, Affirmative Grunt 1%, Other / rare burst 1% · onset 0.79
5.98–6.48 s: Hum 91%, Affirmative Grunt 3%, Other / rare burst 1% · onset 0.65
6.10–6.48 s: Hum 90%, Affirmative Grunt 3%, Other / rare burst 1% · onset 0.64

Frame-positive regions: 1 · CPS 1.51 · Orange timbre cosine 0.703 · identity cosine 0.495

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

Target	Base raw	Base z	Medium raw	Medium z
`emo_Affection`	0.72	1.26	0.43	0.74
`emo_Amusement`	0.51	0.58	0.56	0.63
`emo_Anger`	0.06	0.09	-0.03	-0.06
`emo_Astonishment_Surprise`	0.04	0.07	0.09	0.15
`emo_Awe`	0.13	0.31	0.05	0.12
`emo_Bitterness`	-0.04	-0.12	-0.04	-0.13
`emo_Concentration`	1.15	0.70	1.36	0.98
`emo_Confusion`	0.06	0.10	0.06	0.10
`emo_Contemplation`	2.62	4.25	2.18	3.51
`emo_Contempt`	-0.02	-0.03	-0.00	-0.01
`emo_Contentment`	2.48	4.82	2.29	4.46
`emo_Disappointment`	0.23	0.33	0.10	0.15
`emo_Disgust`	-0.03	-0.08	0.00	-0.01
`emo_Distress`	0.24	0.29	0.25	0.30
`emo_Doubt`	0.22	0.45	0.40	0.85
`emo_Elation`	0.06	0.07	0.11	0.13
`emo_Embarrassment`	0.10	0.14	0.05	0.02
`emo_Emotional_Numbness`	0.26	0.27	0.08	0.09
`emo_Fatigue_Exhaustion`	1.12	2.03	0.93	1.67
`emo_Fear`	-0.02	-0.05	-0.02	-0.05
`emo_Helplessness`	0.22	0.32	0.28	0.41
`emo_Hope_Enthusiasm_Optimism`	1.26	1.51	0.57	0.59
`emo_Impatience_and_Irritability`	0.00	-0.21	-0.01	-0.23
`emo_Infatuation`	0.06	0.14	0.02	0.06
`emo_Interest`	0.81	-0.86	0.98	-0.67
`emo_Intoxication_Altered_States_of_Consciousness`	0.04	0.11	-0.01	0.03
`emo_Jealousy_and_Envy`	-0.03	-0.19	-0.01	-0.15
`emo_Longing`	0.43	0.54	0.09	0.01
`emo_Malevolence_Malice`	-0.06	-0.21	-0.01	-0.13
`emo_Pain`	0.10	0.18	0.11	0.19
`emo_Pleasure_Ecstasy`	0.88	1.40	0.31	0.48
`emo_Pride`	0.07	0.14	0.04	0.07
`emo_Relief`	0.78	1.09	0.53	0.73
`emo_Sadness`	0.06	0.08	0.20	0.26
`emo_Sexual_Lust`	0.03	-0.00	-0.01	-0.08
`emo_Shame`	0.03	0.03	-0.02	-0.05
`emo_Sourness`	-0.02	-0.04	0.00	0.01
`emo_Teasing`	0.12	0.21	0.16	0.30
`emo_Thankfulness_Gratitude`	0.14	0.15	0.05	0.02
`emo_Triumph`	-0.01	-0.01	-0.06	-0.09
`vn_AGEV_reg`	3.29	0.25	2.42	-0.46
`vn_AROU_reg`	1.79	-0.49	1.63	-0.64
`vn_ARSH_reg`	2.82	0.28	3.01	0.50
`vn_ATCK_reg`	2.04	-0.10	1.58	-0.45
`vn_BKGN_reg`	3.49	1.04	3.59	1.17
`vn_BRGT_reg`	3.08	1.34	2.96	1.20
`vn_CHNK_reg`	1.71	-0.11	1.55	-0.24
`vn_CLRT_reg`	1.83	-0.20	1.82	-0.21
`vn_COGL_reg`	1.52	-0.54	1.53	-0.53
`vn_DARC_reg`	2.31	0.51	2.96	0.98
`vn_DFLU_reg`	0.30	-1.85	0.50	-1.68
`vn_EMPH_reg`	2.18	-0.28	1.96	-0.42
`vn_ESTH_reg`	3.15	0.96	3.49	1.39
`vn_EXPL_reg`	0.02	-0.21	0.16	0.22
`vn_FOCS_reg`	2.31	-0.03	2.30	-0.04
`vn_FULL_reg`	2.71	1.05	2.74	1.09
`vn_GEND_reg`	1.72	-1.47	1.29	-1.74
`vn_HARM_reg`	3.67	1.42	3.51	1.23
`vn_METL_reg`	0.74	-0.92	0.73	-0.93
`vn_RANG_reg`	2.22	-0.77	2.20	-0.79
`vn_RCQL_reg`	3.67	1.03	3.55	0.90
`vn_REGS_reg`	3.11	1.51	3.64	1.93
`vn_RESP_reg`	2.10	-0.55	2.12	-0.53
`vn_ROUG_reg`	1.55	-0.54	1.93	-0.12
`vn_R_CHST_reg`	2.10	-0.04	2.07	-0.07
`vn_R_HEAD_reg`	2.54	0.48	3.01	1.04
`vn_R_MASK_reg`	2.68	0.77	2.26	0.35
`vn_R_MIXD_reg`	3.01	1.87	3.03	1.90
`vn_R_NASL_reg`	3.10	0.30	2.81	0.02
`vn_R_ORAL_reg`	2.93	1.01	2.97	1.07
`vn_R_THRT_reg`	2.76	0.86	2.46	0.49
`vn_SMTH_reg`	2.58	0.40	3.08	0.86
`vn_STNC_reg`	1.51	-0.99	1.74	-0.78
`vn_STRU_reg`	1.90	-0.25	1.61	-0.55
`vn_S_ASMR_reg`	2.29	0.65	2.32	0.67
`vn_S_AUTH_reg`	0.26	-0.79	0.09	-0.96
`vn_S_CART_reg`	1.12	-0.31	0.96	-0.43
`vn_S_CASU_reg`	3.57	-0.17	3.95	0.12
`vn_S_CONV_reg`	1.60	-0.76	2.37	-0.17
`vn_S_DRAM_reg`	1.56	-1.01	1.35	-1.20
`vn_S_FORM_reg`	0.31	-0.87	0.32	-0.85
`vn_S_MONO_reg`	3.16	0.26	2.98	0.12
`vn_S_NARR_reg`	0.06	-0.86	0.14	-0.81
`vn_S_NEWS_reg`	-0.05	-0.81	-0.09	-0.87
`vn_S_PLAY_reg`	2.05	-0.23	2.09	-0.20
`vn_S_RANT_reg`	-0.26	-1.14	-0.38	-1.24
`vn_S_STRY_reg`	0.24	-1.64	0.14	-1.71
`vn_S_TECH_reg`	0.41	-0.19	0.57	-0.07
`vn_S_WHIS_reg`	0.69	-0.56	1.06	-0.33
`vn_TEMP_reg`	2.16	0.04	1.86	-0.22
`vn_TENS_reg`	1.30	-0.30	1.40	-0.18
`vn_VALN_reg`	2.87	0.48	3.40	0.96
`vn_VALS_reg`	3.34	0.77	3.60	1.00
`vn_VFLX_reg`	2.93	0.56	3.17	0.76
`vn_VOLT_reg`	1.21	-1.55	1.28	-1.47
`vn_VULN_reg`	3.27	0.64	3.12	0.48
`vn_WARM_reg`	3.48	0.99	3.35	0.85
`genuineness_0_6`	4.76	1.50	4.39	1.27
`blend_0_10`	8.40	0.63	8.63	0.71
`R_quality`	0.78	-0.93	0.75	-1.02
`eiv_extra:Age`	2.12	-3.85	2.32	-3.16
`eiv_extra:Arousal`	0.78	-1.18	0.71	-1.33
`eiv_extra:Authenticity`	2.72	0.34	2.57	-0.62
`eiv_extra:Background_Noise`	0.72	-0.32	0.74	-0.26
`eiv_extra:Confident_vs._Hesitant`	2.04	3.30	2.19	3.78
`eiv_extra:Gender`	0.23	0.85	0.41	1.03
`eiv_extra:High-Pitched_vs._Low-Pitched`	1.41	-1.65	1.35	-1.91
`eiv_extra:Monotone_vs._Expressive`	1.30	-1.18	1.40	-0.97
`eiv_extra:Recording_Quality`	1.77	-1.12	1.52	-1.89
`eiv_extra:Serious_vs._Humorous`	0.85	-0.23	0.95	0.07
`eiv_extra:Soft_vs._Harsh`	1.29	3.16	1.36	3.36
`eiv_extra:Submissive_vs._Dominant`	-0.30	-2.08	-0.35	-2.25
`eiv_extra:Valence`	0.60	1.57	-0.07	-0.19
`eiv_extra:Vulnerable_vs._Emotionally_Detached`	0.75	-2.20	0.76	-2.18
`eiv_extra:Warm_vs._Cold`	0.69	2.14	0.65	2.00
`eiv_extra:score_background_quality`	3.39	0.13	3.43	0.18
`eiv_extra:score_content_enjoyment`	3.51	-3.29	3.62	-2.93
`eiv_extra:score_overall_quality`	2.22	-0.86	2.38	-0.53
`eiv_extra:score_speech_quality`	1.88	0.52	1.90	0.65
`audiobox:CE`	2.86	-1.90	2.89	-1.88
`audiobox:CU`	5.06	-0.59	5.11	-0.54
`audiobox:PC`	1.61	-0.45	1.84	-0.30
`audiobox:PQ`	5.96	-1.23	5.78	-1.44
`dnsmos:SIG_raw`	2.19	-2.56	2.53	-2.05
`dnsmos:BAK_raw`	3.52	0.28	3.80	0.53
`dnsmos:OVRL_raw`	1.94	-1.41	2.36	-0.89
`dnsmos:SIG`	2.36	-2.25	2.58	-1.82
`dnsmos:BAK`	3.47	0.09	3.76	0.40
`dnsmos:OVRL`	1.98	-1.41	2.29	-0.90
`dnsmos:P808_MOS`	2.49	-1.88	2.31	-2.24
`burst_count_log1p`	1.57	2.43	1.56	2.42
`voiceclap_attribute:Affection`	0.87	-0.13	0.77	-0.32
`voiceclap_attribute:Age`	1.86	-2.51	1.53	-3.11
`voiceclap_attribute:Amusement`	0.55	0.27	0.85	0.80
`voiceclap_attribute:Anger`	-0.20	-2.36	-0.01	-1.97
`voiceclap_attribute:Arousal`	0.68	-1.19	1.15	-0.44
`voiceclap_attribute:Astonishment_Surprise`	-0.12	-1.30	-0.12	-1.31
`voiceclap_attribute:Authenticity`	2.75	-0.10	2.83	0.37
`voiceclap_attribute:Awe`	0.19	-1.34	0.20	-1.30
`voiceclap_attribute:Background_Noise`	0.42	-0.55	0.57	0.02
`voiceclap_attribute:Bitterness`	-0.11	-2.98	-0.14	-3.12
`voiceclap_attribute:Concentration`	0.75	-0.88	0.92	-0.55
`voiceclap_attribute:Confident_vs._Hesitant`	1.68	1.30	1.87	1.72
`voiceclap_attribute:Confusion`	0.03	-1.84	0.04	-1.81
`voiceclap_attribute:Contemplation`	1.45	1.66	1.25	1.15
`voiceclap_attribute:Contempt`	-0.03	-2.19	-0.07	-2.29
`voiceclap_attribute:Contentment`	1.64	3.41	1.58	3.23
`voiceclap_attribute:Disappointment`	-0.41	-4.02	-0.19	-3.27
`voiceclap_attribute:Disgust`	-0.15	-3.72	-0.07	-3.35
`voiceclap_attribute:Distress`	0.04	-2.53	0.28	-1.86
`voiceclap_attribute:Doubt`	0.23	-1.62	0.31	-1.19
`voiceclap_attribute:Elation`	0.16	-0.97	0.11	-1.08
`voiceclap_attribute:Embarrassment`	-0.16	-1.50	-0.12	-1.35
`voiceclap_attribute:Emotional_Numbness`	0.15	-1.94	0.20	-1.73
`voiceclap_attribute:Fatigue_Exhaustion`	0.62	0.59	0.80	1.28
`voiceclap_attribute:Fear`	-0.06	-3.21	-0.05	-3.16
`voiceclap_attribute:Gender`	0.74	0.89	0.78	0.93
`voiceclap_attribute:Helplessness`	0.29	-1.38	0.29	-1.38
`voiceclap_attribute:High-Pitched_vs._Low-Pitched`	1.32	-1.39	1.20	-1.71
`voiceclap_attribute:Hope_Enthusiasm_Optimism`	0.83	0.31	0.52	-0.46
`voiceclap_attribute:Impatience_and_Irritability`	-0.26	-2.43	-0.04	-2.02
`voiceclap_attribute:Infatuation`	0.26	-1.05	0.13	-1.45
`voiceclap_attribute:Interest`	0.94	-1.50	1.13	-1.06
`voiceclap_attribute:Intoxication_Altered_States_of_Consciousness`	0.20	-0.65	0.13	-0.80
`voiceclap_attribute:Jealousy_&_Envy`	-0.02	-2.20	-0.02	-2.20
`voiceclap_attribute:Longing`	0.27	-1.20	0.23	-1.39
`voiceclap_attribute:Malevolence_Malice`	0.02	-2.34	-0.02	-2.48
`voiceclap_attribute:Monotone_vs._Expressive`	1.08	-1.17	1.50	-0.46
`voiceclap_attribute:Pain`	0.20	-0.82	0.11	-1.24
`voiceclap_attribute:Pleasure_Ecstasy`	0.48	-0.06	0.31	-0.64
`voiceclap_attribute:Pride`	0.19	-1.68	0.04	-2.11
`voiceclap_attribute:Recording_Quality`	2.13	-0.56	2.00	-0.97
`voiceclap_attribute:Relief`	0.74	-0.70	0.20	-1.99
`voiceclap_attribute:Sadness`	-0.16	-2.92	-0.06	-2.59
`voiceclap_attribute:Serious_vs._Humorous`	0.99	0.33	1.04	0.42
`voiceclap_attribute:Sexual_Lust`	0.02	-1.46	-0.00	-1.52
`voiceclap_attribute:Shame`	0.03	-1.75	0.05	-1.69
`voiceclap_attribute:Soft_vs._Harsh`	1.35	3.30	1.28	3.11
`voiceclap_attribute:Sourness`	-0.08	-2.69	-0.11	-2.80
`voiceclap_attribute:Submissive_vs._Dominant`	-0.32	-2.64	-0.26	-2.46
`voiceclap_attribute:Teasing`	0.25	-0.78	0.39	-0.40
`voiceclap_attribute:Thankfulness_Gratitude`	0.21	-2.22	0.06	-2.50
`voiceclap_attribute:Triumph`	0.00	-1.99	-0.13	-2.35
`voiceclap_attribute:Valence`	0.45	0.72	0.68	1.08
`voiceclap_attribute:Vulnerable_vs._Emotionally_Detached`	0.74	-1.61	0.48	-2.08
`voiceclap_attribute:Warm_vs._Cold`	0.74	2.00	0.87	2.33
`voiceclap_attribute:duration`	7.70	-0.51	6.89	-0.63
`voiceclap_attribute:score_background_quality`	3.35	0.22	3.35	0.20
`voiceclap_attribute:score_content_enjoyment`	4.38	-1.89	4.39	-1.82
`voiceclap_attribute:score_overall_quality`	2.35	-0.70	2.24	-0.96
`voiceclap_attribute:score_speech_quality`	2.03	1.93	2.00	1.53
`voiceclap_attribute:talking_speed`	0.57	-2.25	1.57	-1.99

← All 50 examples ← Previous Next →