Rule.VN1 — VoiceNet: one of 57 voice-descriptor dimensions sweeps by >=T, each consecutive step <=C Source. trajectories_v5.parquet | Family. one corpus in isolation Sampled from 288,000 matching rows, without replacement across the family, so no two tiers reuse a chain.
How to read a Script. Each chunk is one line:
a short tag of what the models heard in that clip, then the words spoken.
(underlined, plain ·
delivery, style) — the tag before the words. Emotions first, then how
it is delivered. Underlined descriptors are the ones that change across this chain
— anything identical on every clip is pulled out and stated once above, because a
value that never moves says nothing about a trajectory.
(ahem) — brackets inside the words
are a different thing: a real non-speech sound, printed where it happens. Most clips have
none; about a quarter do.
The full generated caption for any clip is still there, under
“full caption & clip details”. Its perceived-gender and background-noise
clauses were re-rendered from the numeric buckets, because the versions stored in the
corpus index had those two ladders running backwards.
The emotion clause has been re-derived, and it used to be wrong. The 40 emotion heads are not on a common scale — Interest has a median of 2.08 and is never zero, while Infatuation is zero on 87.7 % of clips — and the caption named an emotion whenever its raw score cleared an absolute 1.0. Interest therefore appeared in 94.8 % of captions and Sadness in almost none: the clause was reporting the scale of the head, not the emotion of the clip. An emotion is now named only when it lands in the top 10 % for that emotion, against a pooled tie-aware mid-rank ECDF over 132,833,726 utterances spanning every dataset and language. Interest now appears in 6.2 %, all 40 emotions occur, and a clip that is ordinary on all 40 says “no dominant emotion” rather than being forced to pick one (21.8 % of clips). This is the same scale the trajectory miner selects on, so the caption and the mining now refer to the same quantity: the mined target emotion is named in the final clip's caption on 73 % of chains, up from 46 %.
COGL — cognitive load ↓c-eurospeech-VN1 · #1
This is a VoiceNet dimension, not an emotion: cognitive load (COGL) describes the voice or the recording itself — how it sounds — rather than what the speaker feels. The rule asked it to sweep by at least 0.50.
The chain starts with cognitive load (COGL) above average — 0.72, higher than 72 % of clips in this corpus — and works its way down to low at 0.21, lower than 79 % of clips in this corpus. That is a total fall of 0.51.
It takes 4 clips to get there. Clip to clip the moves are -0.22, then -0.05, then -0.25 — a slow start, with most of the change arriving in the final step.
No single step is larger than the 0.25 cap, which is exactly what stops this being a jump cut: the change has to be spread across the clips instead of landing all at once.
Same speaker? No similarity score is available here — the eurospeech clips in this chain are not covered by either speaker-embedding store. The chain therefore rests on the corpus's own speaker/track labelling, which is not the same as a measured check.
Voice consistency: these clips are separate recordings joined together, and no voice-similarity check could be run for this sample, so there is no measurement of how closely the voices match. You may hear the voice shift between segments. Voice conversion has not been applied yet in this build. A planned pass will re-render every segment onto the first segment's voice, which removes this effect entirely.
4 clips · 55 s · fr · eurospeech
hear it un-normalised (raw levels, max seam 1.6 dB)
k 4d_a -0.510d_b -0.510step_a 0.249step_b 0.249min_cos_consec —min_cos_anchor —dataset eurospeechlang frspeaker france_france_senate_26835track france_france_senate_26835total 54.8slevel spread 2.0 dBmax seam 1.6 dB
Script — 4 chunks, 2 with a non-speech sound
Unchanged across all 4 clips: an adult masculine voice · average recording, quiet background, energised, neutral tension, moderately variable, some disfluency, wide pitch range
(disappointment, relief, concentration · normal-paced, average clarity, light breath, monologue)Non seulement la situation ne s'est pas améliorée, mais elle s'est fortement détériorée. Mon collègue Sébastien Meurant propose depuis de longs mois la création d'une mission d'information sur le coût de l'immigration. Ma question est simple,
full caption & clip details
An adult masculine voice; delivery is energised, normal-paced, neutral tension, moderately variable; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; average clarity, some disfluency, wide pitch range, light breath; affect is mildly negative, slightly dominant, slightly guarded; reads as disappointment, relief, concentration; style: monologue, cartoonish; average recording, quiet background; genuineness 2.4/6; vocal-burst blend 9.5/10; 13.7s, FR.
france_france_senate_2683524_61d43f5fde858_10332096_10345808 · in -26.6 dBFS · gain +6.6 dB · eurospeech-01148
(relief, thankfulness gratitude, triumph·measured, somewhat unclear, audible breath, storytelling)à combien estimez-vous le coût global réel de l'immigration pour la France ? Allez-vous enfin lever ce tabou ? Bravo ! La parole est
full caption & clip details
A child masculine voice; delivery is energised, measured, neutral tension, moderately variable; timbre is neutral-toned, neutral-bright, slightly rough, slightly thin; somewhat unclear, some disfluency, wide pitch range, audible breath; affect is positive, slightly dominant, slightly guarded; reads as relief, thankfulness gratitude, triumph; style: storytelling, narration; average recording, quiet background; genuineness 1.6/6; vocal-burst blend 2.2/10; 11.6s, FR.
france_france_senate_2683524_61d43f5fde858_10345808_10357441 · in -28.1 dBFS · gain +8.1 dB · eurospeech-01148
(pride, thankfulness gratitude ·brisk, average clarity, normal breath, dramatic)est à Mme la (ahem) ministre déléguée. En matière de politique d'immigration et d'intégration, le budget de l'État fait l'objet chaque année d'un document de politique transversale, qui est adossé au projet de loi de finances.
full caption & clip details
A young adult feminine voice; delivery is energised, brisk, neutral tension, moderately variable; timbre is slightly cool, slightly bright, fairly smooth, slightly thin; average clarity, some disfluency, wide pitch range, normal breath; affect is neutral, slightly dominant, slightly guarded; reads as pride, thankfulness gratitude; style: dramatic, casual; average recording, quiet background; genuineness 2.9/6; vocal-burst blend 3.2/10; 11.8s, FR.
france_france_senate_2683524_61d43f5fde858_10357441_10369279 · in -27.7 dBFS · gain +7.7 dB · eurospeech-01148
(concentration, disappointment, emotional numbness· brisk, clear, heavy breath, dramatic)pour l'année 2021. Cette somme englobe, à la fois, des dépenses engagées directement au titre de la politique publique d'immigration, d'asile et d'intégration des primo-arrivants, les coûts engagés par les forces de sécurité pour (ahem) lutter contre l'immigration irrégulière, mais aussi les dépenses supportées par les ministères de l'éducation nationale,
full caption & clip details
A young adult feminine voice; delivery is energised, brisk, neutral tension, moderately variable; timbre is slightly cool, slightly bright, fairly smooth, thin; clear, some disfluency, wide pitch range, heavy breath; affect is positive, slightly dominant, fairly guarded; reads as concentration, disappointment, emotional numbness; style: dramatic, ranting; average recording, quiet background; genuineness 2.5/6; vocal-burst blend 6.5/10; 17.1s, FR.
france_france_senate_2683524_61d43f5fde858_10380224_10397344 · in -26.1 dBFS · gain +6.1 dB · eurospeech-01148
S_ASMR — style: asmr ↓c-eurospeech-VN1 · #2
This is a VoiceNet dimension, not an emotion: style: asmr (S_ASMR) describes the voice or the recording itself — how it sounds — rather than what the speaker feels. The rule asked it to sweep by at least 0.20.
The chain starts with style: asmr (S_ASMR) above average — 0.68, higher than 68 % of clips in this corpus — and works its way down to below average at 0.39, lower than 61 % of clips in this corpus. That is a total fall of 0.29.
It takes 3 clips to get there. Clip to clip the moves are -0.08, then -0.21 — a slow start, with most of the change arriving in the final step.
No single step is larger than the 0.25 cap, which is exactly what stops this being a jump cut: the change has to be spread across the clips instead of landing all at once.
Same speaker? No similarity score is available here — the eurospeech clips in this chain are not covered by either speaker-embedding store. The chain therefore rests on the corpus's own speaker/track labelling, which is not the same as a measured check.
Voice consistency: these clips are separate recordings joined together, and no voice-similarity check could be run for this sample, so there is no measurement of how closely the voices match. You may hear the voice shift between segments. Voice conversion has not been applied yet in this build. A planned pass will re-render every segment onto the first segment's voice, which removes this effect entirely.
3 clips · 46 s · hr · eurospeech
hear it un-normalised (raw levels, max seam 1.9 dB)
k 3d_a -0.291d_b -0.291step_a 0.213step_b 0.213min_cos_consec —min_cos_anchor —dataset eurospeechlang hrspeaker croatia_20191024090803-209track croatia_20191024090803-209total 45.6slevel spread 1.9 dBmax seam 1.9 dB
Script — 3 chunks, 2 with a non-speech sound
Unchanged across all 3 clips: a middle-aged masculine voice · neutral-toned, quiet background, fairly steady, somewhat unclear
(contentment, thankfulness gratitude, infatuation · measured, very low-energy, slightly relaxed, monologue)kada će ti biti rasprava s obzirom na situaciju u Hrvatskom saboru odnosno da se iznenada može desiti da desetak ljudi nema u sabornici. I sada ja koji sam planirao da će to biti
full caption & clip details
A middle-aged masculine voice; delivery is very low-energy, measured, slightly relaxed, fairly steady; timbre is neutral-toned, slightly dark, slightly rough, balanced body; somewhat unclear, frequent disfluency, fairly narrow pitch, audible breath; affect is neutral, neutral stance, slightly guarded; reads as contentment, thankfulness gratitude, infatuation; style: monologue, whispered; average recording, quiet background; genuineness 3.6/6; vocal-burst blend 3.2/10; 14.9s, HR.
croatia_20191024090803-20954_7358848_7373728 · in -24.6 dBFS · gain +4.6 dB · eurospeech-01510
(thankfulness gratitude, pleasure ecstasy, contemplation· measured, very low-energy, relaxed, monologue)možda za pola sata, 45 minuta došao sam ono u zadnju stotinku. Tako da sa te strane možda ne bi bilo loše da imamo određene stvari regulirane tako da se zastupnici bolje obavijeste. (low mumble) Kada govorimo o
full caption & clip details
A middle-aged masculine voice; delivery is very low-energy, measured, relaxed, fairly steady; timbre is neutral-toned, slightly dark, slightly rough, slightly thin; somewhat unclear, frequent disfluency, fairly narrow pitch, normal breath; affect is mildly negative, neutral stance, slightly guarded; reads as thankfulness gratitude, pleasure ecstasy, contemplation; style: monologue, casual; below-average recording, quiet background; genuineness 4.3/6; vocal-burst blend 3.4/10; 17.9s, HR.
croatia_20191024090803-20954_7373728_7391616 · in -25.0 dBFS · gain +5.0 dB · eurospeech-01510
An adult masculine voice; delivery is normally alert, normal-paced, neutral tension, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; somewhat unclear, some disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as thankfulness gratitude, pride; style: monologue, casual; average recording, quiet background; genuineness 5.0/6; vocal-burst blend 4.2/10; 12.6s, HR.
croatia_20191024090803-20954_7404224_7416800 · in -23.1 dBFS · gain +3.1 dB · eurospeech-01510
STRU — structuredness of delivery ↓c-eurospeech-VN1 · #3
This is a VoiceNet dimension, not an emotion: structuredness of delivery (STRU) describes the voice or the recording itself — how it sounds — rather than what the speaker feels. The rule asked it to sweep by at least 0.20.
The chain starts with structuredness of delivery (STRU) above average — 0.67, higher than 67 % of clips in this corpus — and works its way down to low at 0.23, lower than 77 % of clips in this corpus. That is a total fall of 0.45.
It takes 3 clips to get there. Clip to clip the moves are -0.25, then -0.20 — an even, steady climb — each clip carries about the same share.
No single step is larger than the 0.25 cap, which is exactly what stops this being a jump cut: the change has to be spread across the clips instead of landing all at once.
Same speaker? No similarity score is available here — the eurospeech clips in this chain are not covered by either speaker-embedding store. The chain therefore rests on the corpus's own speaker/track labelling, which is not the same as a measured check.
Voice consistency: these clips are separate recordings joined together, and no voice-similarity check could be run for this sample, so there is no measurement of how closely the voices match. You may hear the voice shift between segments. Voice conversion has not been applied yet in this build. A planned pass will re-render every segment onto the first segment's voice, which removes this effect entirely.
3 clips · 46 s · lt · eurospeech
hear it un-normalised (raw levels, max seam 8.5 dB)
k 3d_a -0.447d_b -0.447step_a 0.248step_b 0.248min_cos_consec —min_cos_anchor —dataset eurospeechlang ltspeaker lithuania_lithuania_3_0811track lithuania_lithuania_3_0811total 45.9slevel spread 9.1 dBmax seam 8.5 dB
Script — 3 chunks, 1 with a non-speech sound
Unchanged across all 3 clips: a young adult feminine voice · quiet background, normally alert, slightly relaxed
(sexual lust, concentration · normal-paced, fairly steady, some disfluency, formal)ar suvaržančius kai kurių teises. Noriu jūsų paklausti, ar tiesa, kad įstojote į M.Valančiaus blaivybės sąjūdį, ir jeigu įstojote, tai reikia tik sveikinti, kad, atstovaudamas tokiai organizacijai, teikiate atitinkamus įstatymus.
full caption & clip details
A young adult feminine voice; delivery is normally alert, normal-paced, slightly relaxed, fairly steady; timbre is slightly cool, slightly dark, fairly smooth, thin; somewhat unclear, some disfluency, fairly narrow pitch, light breath; affect is neutral, neutral stance, slightly guarded; reads as sexual lust, concentration; style: formal; average recording, quiet background; genuineness 2.5/6; vocal-burst blend 1.8/10; 17.0s, LT.
lithuania_lithuania_3_08112007_12417072_12434047 · in -27.2 dBFS · gain +7.2 dB · eurospeech-01934
(measured, steady, frequent disfluency, monologue)kad blaivininkas nereiškia žmogaus, kuris visiškai negeria, bet blaivininkas yra žmogus, nevartojantis stiprių alkoholinių gėrimų ir saikingai vartojantis silpnus, o abstinentas yra visai negeriantis.
lithuania_lithuania_3_08112007_12446528_12459072 · in -26.6 dBFS · gain +6.6 dB · eurospeech-01934
(relief, triumph, pride·normal-paced, fairly steady, some disfluency, monologue)draudžiama vežti automobilių salonuose ir panašiai… Tačiau kaip jūs suvokiate ir kaip paaiškintumėte, aš asmeniškai įžvelgiu tam tikrą dviprasmybę, (low mumble) kai kalbama apie vienatūrius automobilius, mikroautobusus, visureigius,
full caption & clip details
An adult masculine voice; delivery is normally alert, normal-paced, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; somewhat unclear, some disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as relief, triumph, pride; style: monologue; average recording, quiet background; genuineness 4.4/6; vocal-burst blend 3.2/10; 16.0s, LT.
lithuania_lithuania_3_08112007_12518128_12534176 · in -18.1 dBFS · gain -1.9 dB · eurospeech-01934
TEMP — tempo ↑c-eurospeech-VN1 · #4
This is a VoiceNet dimension, not an emotion: tempo (TEMP) describes the voice or the recording itself — how it sounds — rather than what the speaker feels. The rule asked it to sweep by at least 0.20.
The chain starts with tempo (TEMP) above average — 0.66, higher than 66 % of clips in this corpus — and ends with it at the very top of the range at 0.96, higher than 96 % of clips in this corpus. That is a total rise of 0.30.
It takes 4 clips to get there. Clip to clip the moves are +0.23, then -0.18, then +0.24 — not a clean run: step 2 moves back the other way by 0.18 before the chain recovers.
No single step is larger than the 0.25 cap, which is exactly what stops this being a jump cut: the change has to be spread across the clips instead of landing all at once.
Same speaker? No similarity score is available here — the eurospeech clips in this chain are not covered by either speaker-embedding store. The chain therefore rests on the corpus's own speaker/track labelling, which is not the same as a measured check.
Voice consistency: these clips are separate recordings joined together, and no voice-similarity check could be run for this sample, so there is no measurement of how closely the voices match. You may hear the voice shift between segments. Voice conversion has not been applied yet in this build. A planned pass will re-render every segment onto the first segment's voice, which removes this effect entirely.
4 clips · 62 s · no · eurospeech
hear it un-normalised (raw levels, max seam 1.7 dB)
k 4d_a 0.301d_b 0.301step_a 0.243step_b 0.243min_cos_consec —min_cos_anchor —dataset eurospeechlang nospeaker norway_9605-1track norway_9605-1total 62.2slevel spread 1.7 dBmax seam 1.7 dB
Script — 4 chunks, 1 with a non-speech sound
Unchanged across all 4 clips: a middle-aged masculine voice · slightly cool, neutral-bright, balanced body, average recording, energised, neutral tension, moderately variable, wide pitch range
(disgust, malevolence malice, contempt · measured, frequent disfluency, average clarity, cartoonish)spissede tiltak knyttet til lønnstilskudd, varige lønnstilskudd for dem som står i fare for å havne på uføretrygd. Det er bedre og lettere å ta i bruk for næringslivet når det gjelder det midlertidige. Vi
full caption & clip details
A middle-aged masculine voice; delivery is energised, measured, neutral tension, moderately variable; timbre is slightly cool, neutral-bright, slightly rough, balanced body; average clarity, frequent disfluency, wide pitch range, normal breath; affect is neutral, slightly dominant, fairly guarded; reads as disgust, malevolence malice, contempt; style: cartoonish, authoritative; average recording, some background noise; genuineness 4.1/6; vocal-burst blend 2.0/10; 13.5s, NO.
norway_9605-1_6586880_6600368 · in -24.7 dBFS · gain +4.7 dB · eurospeech-02351
(sourness, disgust, thankfulness gratitude·brisk, some disfluency, average clarity, authoritative)Det er tiltak som vil hjelpe folk som står utenfor arbeidslivet, inn i arbeidslivet. Jeg er også glad for at vi har fått på plass et (ahem) SUA-kontor i Bergen, som også betyr at man vil være positiv til å rekruttere riktig og kvalifisert
full caption & clip details
An adult masculine voice; delivery is energised, brisk, neutral tension, moderately variable; timbre is slightly cool, neutral-bright, slightly rough, balanced body; average clarity, some disfluency, wide pitch range, normal breath; affect is neutral, slightly dominant, fairly guarded; reads as sourness, disgust, thankfulness gratitude; style: authoritative, cartoonish; average recording, some background noise; genuineness 3.0/6; vocal-burst blend 3.6/10; 18.3s, NO.
norway_9605-1_6616448_6634704 · in -23.1 dBFS · gain +3.0 dB · eurospeech-02351
(contempt, malevolence malice, impatience and irritability· brisk, some disfluency, very clear, cartoonish)arbeidskraft fra utlandet på en raskere og bedre måte, samtidig som det er et viktig instrument i kampen mot sosial dumping.
full caption & clip details
A middle-aged masculine voice; delivery is energised, brisk, neutral tension, moderately variable; timbre is slightly cool, neutral-bright, slightly rough, balanced body; very clear, some disfluency, wide pitch range, normal breath; affect is negative, slightly dominant, guarded; reads as contempt, malevolence malice, impatience and irritability; style: cartoonish, ranting; average recording, quiet background; genuineness 2.5/6; vocal-burst blend 2.7/10; 10.5s, NO.
norway_9605-1_6634704_6645216 · in -24.8 dBFS · gain +4.8 dB · eurospeech-02351
(triumph, jealousy and envy, pride· brisk, some disfluency, average clarity, cartoonish)våre velferdsordninger, er det også viktig at vi har bærekraftige, gode og trygge velferdsordninger for fremtiden. Jeg er derfor glad for at man nå har fått på plass en uføretrygd med et barnetillegg som setter et tak på 95 pst. Det oppretter også det som regjeringen har vært opptatt av, nemlig at man skal ha arbeidsincentiver,
full caption & clip details
An adult masculine voice; delivery is energised, brisk, neutral tension, moderately variable; timbre is slightly cool, neutral-bright, fairly smooth, balanced body; average clarity, some disfluency, wide pitch range, normal breath; affect is neutral, slightly dominant, fairly guarded; reads as triumph, jealousy and envy, pride; style: cartoonish, ranting; average recording, some background noise; genuineness 2.3/6; vocal-burst blend 5.0/10; 19.5s, NO.
norway_9605-1_6645216_6664704 · in -23.7 dBFS · gain +3.7 dB · eurospeech-02351
S_ASMR — style: asmr ↑c-eurospeech-VN1 · #5
This is a VoiceNet dimension, not an emotion: style: asmr (S_ASMR) describes the voice or the recording itself — how it sounds — rather than what the speaker feels. The rule asked it to sweep by at least 0.50.
The chain starts with style: asmr (S_ASMR) low — 0.13, lower than 87 % of clips in this corpus — and ends with it above average at 0.64, higher than 64 % of clips in this corpus. That is a total rise of 0.51.
It takes 5 clips to get there. Clip to clip the moves are -0.00, then +0.17, then +0.24, then +0.11 — not a clean run: step 1 moves back the other way by 0.00 before the chain recovers.
No single step is larger than the 0.25 cap, which is exactly what stops this being a jump cut: the change has to be spread across the clips instead of landing all at once.
Same speaker? No similarity score is available here — the eurospeech clips in this chain are not covered by either speaker-embedding store. The chain therefore rests on the corpus's own speaker/track labelling, which is not the same as a measured check.
Voice consistency: these clips are separate recordings joined together, and no voice-similarity check could be run for this sample, so there is no measurement of how closely the voices match. You may hear the voice shift between segments. Voice conversion has not been applied yet in this build. A planned pass will re-render every segment onto the first segment's voice, which removes this effect entirely.
5 clips · 82 s · de · eurospeech
hear it un-normalised (raw levels, max seam 6.1 dB)
k 5d_a 0.515d_b 0.515step_a 0.237step_b 0.237min_cos_consec —min_cos_anchor —dataset eurospeechlang despeaker germany_7532534track germany_7532534total 82.2slevel spread 8.3 dBmax seam 6.1 dB
Script — 5 chunks, 0 with a non-speech sound
Unchanged across all 5 clips: a young adult masculine voice · neutral-bright, fairly smooth
(concentration, disgust, bitterness · brisk, highly aroused, slightly tense, dramatic)durch flächendeckende 2-G-Maßnahmen, Kontaktreduktion, Absage von Veranstaltungen, Schließung von Gastronomie, Klubs und Bars auf den Weg bringen, mittelfristig durch das Boostern und Ausweiten, Schutz bieten und langfristig durch so scharfe Instrumente wie einrichtungsspezifische Impfflicht und eine Debatte, die wir auf den Weg gebracht haben,
full caption & clip details
A young adult masculine voice; delivery is highly aroused, brisk, slightly tense, moderately variable; timbre is slightly cool, neutral-bright, fairly smooth, thin; very clear, almost no disfluency, wide pitch range, light breath; affect is neutral, very dominant, fairly guarded; reads as concentration, disgust, bitterness; style: dramatic, authoritative; average recording, quiet background; genuineness 1.3/6; vocal-burst blend 1.7/10; 19.4s, DE.
germany_7532534_3833120_3852496 · in -24.7 dBFS · gain +4.7 dB · eurospeech-00535
(anger, concentration, interest· brisk, energised, neutral tension, ranting)über eine allgemeine Impfpflicht, auch einen besseren Schutz, einen Weg aus dieser Pandemie hieraus ebnen. Und ich möchte an die Länder gerichtet appellieren: Wir brauchen jetzt die Durchsetzung, die Umsetzung der Maßnahmen, die wir in voller Fülle ermöglichen. Nur so wird Schutz auch möglich und auf den Weg gebracht,
full caption & clip details
A young adult masculine voice; delivery is energised, brisk, neutral tension, moderately variable; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; very clear, some disfluency, wide pitch range, light breath; affect is positive, slightly dominant, fairly guarded; reads as anger, concentration, interest; style: ranting, authoritative; average recording, quiet background; genuineness 2.3/6; vocal-burst blend 2.6/10; 17.7s, DE.
germany_7532534_3852496_3870176 · in -23.6 dBFS · gain +3.6 dB · eurospeech-00535
(concentration, impatience and irritability, interest · brisk, energised, neutral tension, authoritative)nur so verhindern wir, dass Omikron, das längst im Land ist, nicht weiter die Hütte anzündet, sondern Schutz der Menschen wirklich wirkungsvoll auf den Weg gebracht ist. In diesem Sinne: Lassen Sie uns gemeinsam einen Kollaps verhindern! Vielen Dank.
full caption & clip details
An adult masculine voice; delivery is energised, brisk, neutral tension, moderately variable; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; very clear, some disfluency, wide pitch range, light breath; affect is neutral, slightly dominant, fairly guarded; reads as concentration, impatience and irritability, interest; style: authoritative, dramatic; average recording, no background noise; genuineness 2.3/6; vocal-burst blend 0.0/10; 16.0s, DE.
germany_7532534_3870176_3886207 · in -25.8 dBFS · gain +5.8 dB · eurospeech-00535
(normal-paced, normally alert, slightly relaxed, formal)Nächste Rednerin: für die FDP-Fraktion Katrin Helling-Plahr.
full caption & clip details
An adult masculine voice; delivery is normally alert, normal-paced, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; clear, no disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; no dominant emotion; style: formal, authoritative; good recording, no background noise; genuineness 1.3/6; vocal-burst blend 0.8/10; 12.0s, DE.
germany_7532534_3905058_3917034 · in -31.9 dBFS · gain +11.9 dB · eurospeech-00535
(malevolence malice, pride, infatuation·measured, normally alert, slightly relaxed, dramatic)Sehr geehrte Frau Präsidentin! Meine Damen und Herren! Die schärfste Waffe gegen das Virus sind Impfungen; deshalb: Boostern wir die Impfkampagne! Wer sich impfen lassen möchte, muss umgehend ein Angebot erhalten.
full caption & clip details
A middle-aged feminine voice; delivery is normally alert, measured, slightly relaxed, moderately variable; timbre is slightly cool, neutral-bright, fairly smooth, balanced body; clear, almost no disfluency, wide pitch range, normal breath; affect is mildly positive, neutral stance, neutral openness; reads as malevolence malice, pride, infatuation; style: dramatic, didactic; average recording, quiet background; genuineness 1.3/6; vocal-burst blend 0.5/10; 16.6s, DE.
germany_7532534_3917034_3933600 · in -29.1 dBFS · gain +9.1 dB · eurospeech-00535
This is a VoiceNet dimension, not an emotion: audible breath / respiration (RESP) describes the voice or the recording itself — how it sounds — rather than what the speaker feels. The rule asked it to sweep by at least 0.20.
The chain starts with audible breath / respiration (RESP) below average — 0.41, lower than 59 % of clips in this corpus — and ends with it high at 0.86, higher than 86 % of clips in this corpus. That is a total rise of 0.45.
It takes 5 clips to get there. Clip to clip the moves are +0.23, then +0.12, then +0.22, then -0.12 — not a clean run: step 4 moves back the other way by 0.12 before the chain recovers.
No single step is larger than the 0.25 cap, which is exactly what stops this being a jump cut: the change has to be spread across the clips instead of landing all at once.
Same speaker? No similarity score is available here — the eurospeech clips in this chain are not covered by either speaker-embedding store. The chain therefore rests on the corpus's own speaker/track labelling, which is not the same as a measured check.
Voice consistency: these clips are separate recordings joined together, and no voice-similarity check could be run for this sample, so there is no measurement of how closely the voices match. You may hear the voice shift between segments. Voice conversion has not been applied yet in this build. A planned pass will re-render every segment onto the first segment's voice, which removes this effect entirely.
5 clips · 75 s · lt · eurospeech
k 5d_a 0.449d_b 0.449step_a 0.225step_b 0.225min_cos_consec —min_cos_anchor —dataset eurospeechlang ltspeaker lithuania_lithuania_13_181track lithuania_lithuania_13_181total 75.4slevel spread 3.7 dBmax seam 3.7 dB
Script — 5 chunks, 4 with a non-speech sound
Unchanged across all 5 clips: an adult masculine voice · fairly smooth, normally alert, light breath
(disgust, interest · brisk, slightly relaxed, fairly steady, monologue)Tik tiek, kad mes dar neturime naujų bylų, kai veikos yra padarytos po tos pataisos, praktika iš esmės dar nesulaukė įstatyminio pokyčio ir teisėjai dar neturėjo galimybės pasisakyti dėl to pokyčio.
full caption & clip details
An adult masculine voice; delivery is normally alert, brisk, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; somewhat unclear, some disfluency, moderate pitch range, light breath; affect is neutral, slightly dominant, slightly guarded; reads as disgust, interest; style: monologue, authoritative; average recording, quiet background; genuineness 1.5/6; vocal-burst blend 1.5/10; 14.9s, LT.
lithuania_lithuania_13_18122018_12936864_12951776 · in -22.4 dBFS · gain +2.4 dB · eurospeech-01860
(pride·measured, neutral tension, fairly steady, casual)Aš manau, (low mumble) nors teismų praktika iš tiesų kartais yra inertiška, bet ji, manau, tikrai keisis reaguojant į tas pataisas. Negaliu spėti kaip, bet jinai keisis. (low mumble) PIRMININKĖ.
full caption & clip details
An adult masculine voice; delivery is normally alert, measured, neutral tension, fairly steady; timbre is neutral-toned, slightly dark, fairly smooth, balanced body; somewhat unclear, frequent disfluency, fairly narrow pitch, light breath; affect is neutral, neutral stance, slightly guarded; reads as pride; style: casual, monologue; average recording, quiet background; genuineness 4.9/6; vocal-burst blend 2.7/10; 16.0s, LT.
lithuania_lithuania_13_18122018_12951776_12967808 · in -21.7 dBFS · gain +1.7 dB · eurospeech-01860
(normal-paced, slightly relaxed, fairly steady, casual)Taip, (low mumble) jos didelės ir mums patiems, teisėjams, kartais ir gėda, kad mes (low mumble) tiek laiko esame priversti nagrinėti tokias bylas,
full caption & clip details
A young adult masculine voice; delivery is normally alert, normal-paced, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; somewhat unclear, frequent disfluency, moderate pitch range, light breath; affect is mildly positive, neutral stance, slightly guarded; no dominant emotion; style: casual, monologue; average recording, quiet background; genuineness 4.8/6; vocal-burst blend 4.9/10; 10.9s, LT.
lithuania_lithuania_13_18122018_12967808_12978736 · in -21.8 dBFS · gain +1.8 dB · eurospeech-01860
(shame, thankfulness gratitude· normal-paced, neutral tension, moderately variable, casual)valdančiųjų daugumos palaikymo. Matyt, jeigu prezidentūra arba jeigu teisėjai kartu vienu balsu garsiau kalbėtų, galbūt mums ir pavyktų įtikinti valdančiąją daugumą, kuri vis dėlto nenori tos geležinės uždangos (low mumble) (ahem) šioje srityje (ahem) pakelti.
full caption & clip details
A young adult feminine voice; delivery is normally alert, normal-paced, neutral tension, moderately variable; timbre is slightly cool, slightly bright, fairly smooth, thin; somewhat unclear, some disfluency, moderate pitch range, light breath; affect is mildly positive, neutral stance, slightly guarded; reads as shame, thankfulness gratitude; style: casual, monologue; average recording, quiet background; genuineness 3.8/6; vocal-burst blend 6.1/10; 18.8s, LT.
lithuania_lithuania_13_18122018_13025841_13044624 · in -22.9 dBFS · gain +2.9 dB · eurospeech-01860
(thankfulness gratitude, affection, contentment· normal-paced, neutral tension, moderately variable, playful)Aš turiu bendresnį klausimą dėl baudžiamosios politikos apskritai. (low mumble) Jau dvejus metus (ahem) dirbu čia, Seime, ir nėra (ahem) jokios kitos iniciatyvos, kaip tiktai griežtinti
full caption & clip details
A young adult feminine voice; delivery is normally alert, normal-paced, neutral tension, moderately variable; timbre is slightly cool, neutral-bright, fairly smooth, balanced body; average clarity, some disfluency, wide pitch range, light breath; affect is positive, slightly dominant, slightly guarded; reads as thankfulness gratitude, affection, contentment; style: playful; below-average recording, some background noise; genuineness 4.2/6; vocal-burst blend 4.0/10; 14.1s, LT.
lithuania_lithuania_13_18122018_13044624_13058752 · in -19.2 dBFS · gain -0.8 dB · eurospeech-01860
R_MASK — resonance: mask ↑c-eurospeech-VN1 · #7
This is a VoiceNet dimension, not an emotion: resonance: mask (R_MASK) describes the voice or the recording itself — how it sounds — rather than what the speaker feels. The rule asked it to sweep by at least 0.20.
The chain starts with resonance: mask (R_MASK) above average — 0.68, higher than 68 % of clips in this corpus — and ends with it at the very top of the range at 0.93, higher than 93 % of clips in this corpus. That is a total rise of 0.25.
It takes 2 clips to get there. Clip to clip the moves are +0.25 — a single step, so there is no internal shape to speak of.
No single step is larger than the 0.25 cap, which is exactly what stops this being a jump cut: the change has to be spread across the clips instead of landing all at once.
Same speaker? No similarity score is available here — the eurospeech clips in this chain are not covered by either speaker-embedding store. The chain therefore rests on the corpus's own speaker/track labelling, which is not the same as a measured check.
Voice consistency: these clips are separate recordings joined together, and no voice-similarity check could be run for this sample, so there is no measurement of how closely the voices match. You may hear the voice shift between segments. Voice conversion has not been applied yet in this build. A planned pass will re-render every segment onto the first segment's voice, which removes this effect entirely.
2 clips · 27 s · bg · eurospeech
k 2d_a 0.248d_b 0.248step_a 0.248step_b 0.248min_cos_consec —min_cos_anchor —dataset eurospeechlang bgspeaker bulgaria_bulgaria_1_040520track bulgaria_bulgaria_1_040520total 27.0slevel spread 1.2 dBmax seam 1.2 dB
Script — 2 chunks, 0 with a non-speech sound
Unchanged across all 2 clips: a middle-aged masculine voice · slightly cool, neutral-bright, balanced body, average recording, quiet background, neutral tension, moderately variable, some disfluency
(contempt, sourness, malevolence malice · normal-paced, normally alert, audible breath, cartoonish)и отмяна на имунитета на народните представители. И това изчезна някъде по пътя между обещанията и реалността днес. Очевидно това вече няма да е важно,
full caption & clip details
A middle-aged masculine voice; delivery is normally alert, normal-paced, neutral tension, moderately variable; timbre is slightly cool, neutral-bright, slightly rough, balanced body; average clarity, some disfluency, wide pitch range, audible breath; affect is positive, slightly dominant, guarded; reads as contempt, sourness, malevolence malice; style: cartoonish, authoritative; average recording, quiet background; genuineness 2.7/6; vocal-burst blend 3.8/10; 12.1s, BG.
bulgaria_bulgaria_1_04052017_2897600_2909696 · in -28.8 dBFS · gain +8.8 dB · eurospeech-00080
(contempt, bitterness, pride·brisk, energised, normal breath, authoritative)въпреки желанието на сигурно милиони хора да ни видят без имунитет, и ние бихме Ви подкрепили за това. Жалко, че се отказахте както от новата Конституция, така и от облагите на народните представители – имунитет и заплати.
full caption & clip details
A young adult masculine voice; delivery is energised, brisk, neutral tension, moderately variable; timbre is slightly cool, neutral-bright, fairly smooth, balanced body; average clarity, some disfluency, wide pitch range, normal breath; affect is neutral, slightly dominant, fairly guarded; reads as contempt, bitterness, pride; style: authoritative, dramatic; average recording, quiet background; genuineness 2.8/6; vocal-burst blend 5.5/10; 14.8s, BG.
bulgaria_bulgaria_1_04052017_2909696_2924496 · in -27.6 dBFS · gain +7.6 dB · eurospeech-00080
TEMP — tempo ↓c-eurospeech-VN1 · #8
This is a VoiceNet dimension, not an emotion: tempo (TEMP) describes the voice or the recording itself — how it sounds — rather than what the speaker feels. The rule asked it to sweep by at least 0.20.
The chain starts with tempo (TEMP) above average — 0.71, higher than 71 % of clips in this corpus — and works its way down to below average at 0.35, lower than 65 % of clips in this corpus. That is a total fall of 0.37.
It takes 3 clips to get there. Clip to clip the moves are -0.13, then -0.23 — a fairly even climb, though some clips carry more of the change than others.
No single step is larger than the 0.25 cap, which is exactly what stops this being a jump cut: the change has to be spread across the clips instead of landing all at once.
Same speaker? No similarity score is available here — the eurospeech clips in this chain are not covered by either speaker-embedding store. The chain therefore rests on the corpus's own speaker/track labelling, which is not the same as a measured check.
Voice consistency: these clips are separate recordings joined together, and no voice-similarity check could be run for this sample, so there is no measurement of how closely the voices match. You may hear the voice shift between segments. Voice conversion has not been applied yet in this build. A planned pass will re-render every segment onto the first segment's voice, which removes this effect entirely.
3 clips · 55 s · en · eurospeech
k 3d_a -0.369d_b -0.369step_a 0.234step_b 0.234min_cos_consec —min_cos_anchor —dataset eurospeechlang enspeaker uk_uk_26_10072023track uk_uk_26_10072023total 55.2slevel spread 1.4 dBmax seam 0.9 dB
Script — 3 chunks, 3 with a non-speech sound
Unchanged across all 3 clips: an adult masculine voice · neutral-toned, neutral-bright, fairly smooth, normally alert, slightly relaxed, moderate pitch range
(shame, contentment, triumph · measured, fairly steady, little disfluency, monologue)I welcome the recent (ahem) completion of the review into special educational needs provision, and I look forward to the outcome of the review of education provision for 14 to 19-year-olds. There has been a great deal of interest in the particular details of per-pupil funding. I propose to write to my hon Friend the Member for Worcester
full caption & clip details
An adult masculine voice; delivery is normally alert, measured, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, full; average clarity, little disfluency, moderate pitch range, minimal breath; affect is mildly positive, neutral stance, slightly guarded; reads as shame, contentment, triumph; style: monologue, formal; good recording, no background noise; genuineness 1.0/6; vocal-burst blend 0.9/10; 19.9s, EN.
uk_uk_26_10072023_29383408_29403328 · in -25.1 dBFS · gain +5.1 dB · eurospeech-00981
(concentration·normal-paced, fairly steady, some disfluency, conversational)in detail on (ahem) education funding. I shall place a copy of that letter in the Library for all Members who have expressed an interest. (ahem) The hon. Member for Gordon (Richard Thomson) in particular raised section 75 duties (ahem) and whether they are carried out (low mumble) by us and (low mumble) so on.
full caption & clip details
An adult masculine voice; delivery is normally alert, normal-paced, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; average clarity, some disfluency, moderate pitch range, light breath; affect is mildly positive, neutral stance, slightly guarded; reads as concentration; style: conversational; average recording, quiet background; genuineness 3.5/6; vocal-burst blend 3.4/10; 18.9s, EN.
uk_uk_26_10072023_29403328_29422192 · in -26.1 dBFS · gain +6.1 dB · eurospeech-00981
(concentration, infatuation·measured, steady, almost no disfluency, newsreading)(ahem) As the ones taking the decisions, Northern Ireland Departments completed indicative section 75 assessments that were considered by the Secretary of State when he set the overall budget allocations. In light of those budget totals, Departments are now completing final assessments.
full caption & clip details
An adult masculine voice; delivery is normally alert, measured, slightly relaxed, steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; clear, almost no disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as concentration, infatuation; style: newsreading, formal; good recording, no background noise; genuineness 0.7/6; vocal-burst blend 0.0/10; 16.1s, EN.
uk_uk_26_10072023_29422192_29438304 · in -26.5 dBFS · gain +6.5 dB · eurospeech-00981
VULN — vulnerability ↑c-eurospeech-VN1 · #9
This is a VoiceNet dimension, not an emotion: vulnerability (VULN) describes the voice or the recording itself — how it sounds — rather than what the speaker feels. The rule asked it to sweep by at least 0.50.
The chain starts with vulnerability (VULN) low — 0.09, lower than 91 % of clips in this corpus — and ends with it above average at 0.67, higher than 67 % of clips in this corpus. That is a total rise of 0.58.
It takes 5 clips to get there. Clip to clip the moves are -0.00, then +0.16, then +0.19, then +0.23 — not a clean run: step 1 moves back the other way by 0.00 before the chain recovers.
No single step is larger than the 0.25 cap, which is exactly what stops this being a jump cut: the change has to be spread across the clips instead of landing all at once.
Same speaker? No similarity score is available here — the eurospeech clips in this chain are not covered by either speaker-embedding store. The chain therefore rests on the corpus's own speaker/track labelling, which is not the same as a measured check.
Voice consistency: these clips are separate recordings joined together, and no voice-similarity check could be run for this sample, so there is no measurement of how closely the voices match. You may hear the voice shift between segments. Voice conversion has not been applied yet in this build. A planned pass will re-render every segment onto the first segment's voice, which removes this effect entirely.
5 clips · 73 s · da · eurospeech
k 5d_a 0.577d_b 0.577step_a 0.231step_b 0.231min_cos_consec —min_cos_anchor —dataset eurospeechlang daspeaker denmark_20191M055_2020-01-track denmark_20191M055_2020-01-total 72.5slevel spread 2.4 dBmax seam 1.9 dB
Script — 5 chunks, 4 with a non-speech sound
Unchanged across all 5 clips: an adult feminine voice · fairly smooth, average recording, quiet background, normally alert
(disappointment, concentration, triumph · normal-paced, slightly relaxed, fairly steady, monologue)man skal hvad, og det er trods alt de færreste, der holder op med at være blinde efter 3 måneder. Hvis der er en problemstilling i forhold til det, synes jeg da, vi skal drøfte den, (low mumble) ligesom vi har gjort det på anbringelsesområdet. Lad os få det på bordet, og lad os kigge på det, for for det meste handler det jo om, at der på andre områder
full caption & clip details
An adult feminine voice; delivery is normally alert, normal-paced, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; average clarity, some disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as disappointment, concentration, triumph; style: monologue, didactic; average recording, quiet background; genuineness 3.6/6; vocal-burst blend 4.9/10; 16.7s, DA.
denmark_20191M055_2020-01-29_1300_12962624_12979312 · in -22.6 dBFS · gain +2.6 dB · eurospeech-00381
(shame, triumph, fear· normal-paced, slightly relaxed, fairly steady, monologue)kan være nogle hjælpemidler, man har behov for, f.eks. efter en operation eller lignende, hvor det behov ophører igen. Spørgsmålet er så, om den skelnen i lovgivningen er god nok. Det kan jeg ikke sige på stående fod, men jeg kan sige, at jeg er stødt på problemstillingen før, (low mumble) og ja, jeg vil gerne kigge på det, hvis der ligger noget på mit område, hvor de grænser er blevet tåbelige.
full caption & clip details
A middle-aged masculine voice; delivery is normally alert, normal-paced, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; average clarity, some disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as shame, triumph, fear; style: monologue, didactic; average recording, quiet background; genuineness 2.8/6; vocal-burst blend 5.2/10; 18.6s, DA.
denmark_20191M055_2020-01-29_1300_12979312_12997904 · in -20.6 dBFS · gain +0.6 dB · eurospeech-00381
(intoxication altered states of consciousness, fear ·measured, slightly relaxed, moderately variable, didactic)Jeg giver ministeren ret i, at der jo helt klart er steder, hvor man kan sige, at det er en succes, at man er nødt til at
full caption & clip details
A middle-aged somewhat feminine voice; delivery is normally alert, measured, slightly relaxed, moderately variable; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; average clarity, frequent disfluency, wide pitch range, audible breath; affect is neutral, neutral stance, slightly guarded; reads as intoxication altered states of consciousness, fear; style: didactic, playful; average recording, quiet background; genuineness 4.1/6; vocal-burst blend 1.5/10; 10.6s, DA.
denmark_20191M055_2020-01-29_1300_12997904_13008511 · in -21.2 dBFS · gain +1.2 dB · eurospeech-00381
(pride, intoxication altered states of consciousness, interest· measured, neutral tension, moderately variable, monologue)at genbesøge og lave en ny visitering, (ahem) fordi det er et barn, der måske er i støt udvikling. (low mumble) Men man kan sige, at der i det her tilfælde i forhold til det, vi spørger ind til her, (ahem) hvor der er tale om et blindt barn, (ahem)
full caption & clip details
An elderly feminine voice; delivery is normally alert, measured, neutral tension, moderately variable; timbre is slightly cool, slightly dark, fairly smooth, thin; somewhat unclear, frequent disfluency, moderate pitch range, audible breath; affect is neutral, neutral stance, slightly guarded; reads as pride, intoxication altered states of consciousness, interest; style: monologue, casual; average recording, quiet background; genuineness 4.3/6; vocal-burst blend 3.9/10; 14.9s, DA.
denmark_20191M055_2020-01-29_1300_13008511_13023456 · in -20.1 dBFS · gain +0.1 dB · eurospeech-00381
(distress, fear, sadness·slow, slightly relaxed, moderately variable, didactic)barn, skal bruges kræfter både i familien men så sandelig også i (ahem) børnehaven og i kommunen fast hver tredje (low mumble) måned.
full caption & clip details
An elderly somewhat feminine voice; delivery is normally alert, slow, slightly relaxed, moderately variable; timbre is slightly cool, neutral-bright, fairly smooth, balanced body; very clear, frequent disfluency, wide pitch range, audible breath; affect is neutral, neutral stance, neutral openness; reads as distress, fear, sadness; style: didactic, dramatic; average recording, quiet background; genuineness 3.1/6; vocal-burst blend 0.7/10; 11.1s, DA.
denmark_20191M055_2020-01-29_1300_13023456_13034528 · in -20.2 dBFS · gain +0.2 dB · eurospeech-00381
GEND — perceived gender ↑c-eurospeech-VN1 · #10
This is a VoiceNet dimension, not an emotion: perceived gender (GEND) describes the voice or the recording itself — how it sounds — rather than what the speaker feels. The rule asked it to sweep by at least 0.20.
The chain starts with perceived gender (GEND) around average — 0.56, higher than 56 % of clips in this corpus — and ends with it at the very top of the range at 0.94, higher than 94 % of clips in this corpus. That is a total rise of 0.38.
It takes 3 clips to get there. Clip to clip the moves are +0.13, then +0.25 — a fairly even climb, though some clips carry more of the change than others.
No single step is larger than the 0.25 cap, which is exactly what stops this being a jump cut: the change has to be spread across the clips instead of landing all at once.
Same speaker? No similarity score is available here — the eurospeech clips in this chain are not covered by either speaker-embedding store. The chain therefore rests on the corpus's own speaker/track labelling, which is not the same as a measured check.
Voice consistency: these clips are separate recordings joined together, and no voice-similarity check could be run for this sample, so there is no measurement of how closely the voices match. You may hear the voice shift between segments. Voice conversion has not been applied yet in this build. A planned pass will re-render every segment onto the first segment's voice, which removes this effect entirely.
3 clips · 43 s · lt · eurospeech
k 3d_a 0.380d_b 0.380step_a 0.248step_b 0.248min_cos_consec —min_cos_anchor —dataset eurospeechlang ltspeaker lithuania_lithuania_18_170track lithuania_lithuania_18_170total 42.6slevel spread 1.6 dBmax seam 1.6 dB
Script — 3 chunks, 3 with a non-speech sound
Unchanged across all 3 clips: a child masculine voice · neutral-bright, balanced body, average recording, quiet background, moderately variable, light breath
(thankfulness gratitude, contentment, pride · normal-paced, normally alert, slightly relaxed, cartoonish)(low mumble) tam tikras sąlygas. Naudojant nuotolinį būdą dalyviai turi būti identifikuojami. Faktiškai čia kaip ir rinkimuose dalyvaujant, pavyzdžiui, elektroninėmis priemonėmis kitose šalyse. Žmogus turi būti identifikuojamas.
full caption & clip details
A child masculine voice; delivery is normally alert, normal-paced, slightly relaxed, moderately variable; timbre is neutral-toned, neutral-bright, slightly rough, balanced body; somewhat unclear, frequent disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as thankfulness gratitude, contentment, pride; style: cartoonish, monologue; average recording, quiet background; genuineness 3.5/6; vocal-burst blend 4.3/10; 16.1s, LT.
lithuania_lithuania_18_17032020_11492960_11509056 · in -29.1 dBFS · gain +9.1 dB · eurospeech-01901
(pride, pain·brisk, energised, neutral tension, cartoonish)(low mumble) Kas ten pakelia kokį telefoną ir pasako, kad aš už nutarimą, tai yra vienas dalykas. Aš manau, kad ir Seimas galėtų prisiderinti prie tų galimybių, juo labiau internete yra programėlės, kurios leidžia
full caption & clip details
A young adult masculine voice; delivery is energised, brisk, neutral tension, moderately variable; timbre is slightly cool, neutral-bright, fairly smooth, balanced body; average clarity, some disfluency, wide pitch range, light breath; affect is neutral, slightly dominant, slightly guarded; reads as pride, pain; style: cartoonish, authoritative; average recording, quiet background; genuineness 2.5/6; vocal-burst blend 6.2/10; 14.4s, LT.
lithuania_lithuania_18_17032020_11509056_11523424 · in -30.7 dBFS · gain +10.7 dB · eurospeech-01901
(normal-paced, normally alert, neutral tension, casual)(low mumble) konferencijas ir matyti pašnekovus (ahem) realiuoju laiku. Aš vis dėlto siūlyčiau apsispręsti dėl šios galimybės taikymo.
full caption & clip details
An adult masculine voice; delivery is normally alert, normal-paced, neutral tension, moderately variable; timbre is slightly cool, neutral-bright, slightly rough, balanced body; average clarity, some disfluency, wide pitch range, light breath; affect is mildly positive, slightly dominant, slightly guarded; no dominant emotion; style: casual, conversational; average recording, quiet background; genuineness 4.4/6; vocal-burst blend 3.6/10; 11.8s, LT.
lithuania_lithuania_18_17032020_11523424_11535264 · in -30.2 dBFS · gain +10.2 dB · eurospeech-01901
STRU — structuredness of delivery ↑c-eurospeech-VN1 · #11
This is a VoiceNet dimension, not an emotion: structuredness of delivery (STRU) describes the voice or the recording itself — how it sounds — rather than what the speaker feels. The rule asked it to sweep by at least 0.20.
The chain starts with structuredness of delivery (STRU) low — 0.24, lower than 76 % of clips in this corpus — and ends with it around average at 0.47, lower than 53 % of clips in this corpus. That is a total rise of 0.24.
It takes 2 clips to get there. Clip to clip the moves are +0.24 — a single step, so there is no internal shape to speak of.
No single step is larger than the 0.25 cap, which is exactly what stops this being a jump cut: the change has to be spread across the clips instead of landing all at once.
Same speaker? No similarity score is available here — the eurospeech clips in this chain are not covered by either speaker-embedding store. The chain therefore rests on the corpus's own speaker/track labelling, which is not the same as a measured check.
Voice consistency: these clips are separate recordings joined together, and no voice-similarity check could be run for this sample, so there is no measurement of how closely the voices match. You may hear the voice shift between segments. Voice conversion has not been applied yet in this build. A planned pass will re-render every segment onto the first segment's voice, which removes this effect entirely.
2 clips · 24 s · pt · eurospeech
k 2d_a 0.236d_b 0.236step_a 0.236step_b 0.236min_cos_consec —min_cos_anchor —dataset eurospeechlang ptspeaker portugal_11_2_49track portugal_11_2_49total 23.5slevel spread 0.9 dBmax seam 0.9 dB
Script — 2 chunks, 0 with a non-speech sound
Unchanged across all 2 clips: an adult masculine voice · slightly cool, neutral-bright, thin, quiet background, fast, moderately variable, wide pitch range
(jealousy and envy, sourness, disgust · energised, neutral tension, some disfluency, authoritative)e o mais que posso desejar é que o Governo ouça com tanta atenção quanto aquela com que ouvimos aquilo que o Sr. Deputado aqui disse. Se o Governo ouvisse algumas das coisas que aqui foram ditas pelo Sr. Deputado,
full caption & clip details
An adult masculine voice; delivery is energised, fast, neutral tension, moderately variable; timbre is slightly cool, neutral-bright, fairly smooth, thin; average clarity, some disfluency, wide pitch range, audible breath; affect is neutral, slightly dominant, slightly guarded; reads as jealousy and envy, sourness, disgust; style: authoritative, cartoonish; average recording, quiet background; genuineness 3.0/6; vocal-burst blend 5.6/10; 12.7s, PT.
portugal_11_2_49_4615760_4628480 · in -11.8 dBFS · gain -8.2 dB · eurospeech-02466
(triumph, anger, disappointment·highly aroused, slightly tense, almost no disfluency, authoritative)e, portanto, o problema que temos continua a ser a formação do preço, porque, pelo mesmo produto, pelos mesmos operadores, são cobrados preços diferentes, o que significa que, do ponto de vista da regulação,
full caption & clip details
A young adult masculine voice; delivery is highly aroused, fast, slightly tense, moderately variable; timbre is slightly cool, neutral-bright, rough, thin; clear, almost no disfluency, wide pitch range, normal breath; affect is neutral, slightly dominant, guarded; reads as triumph, anger, disappointment; style: authoritative, dramatic; below-average recording, quiet background; genuineness 2.1/6; vocal-burst blend 5.1/10; 10.7s, PT.
portugal_11_2_49_4663392_4674048 · in -12.7 dBFS · gain -7.3 dB · eurospeech-02466
This is a VoiceNet dimension, not an emotion: style: newsreading (S_NEWS) describes the voice or the recording itself — how it sounds — rather than what the speaker feels. The rule asked it to sweep by at least 0.50.
The chain starts with style: newsreading (S_NEWS) high — 0.83, higher than 83 % of clips in this corpus — and works its way down to low at 0.16, lower than 84 % of clips in this corpus. That is a total fall of 0.67.
It takes 5 clips to get there. Clip to clip the moves are -0.12, then -0.19, then -0.17, then -0.19 — a fairly even climb, though some clips carry more of the change than others.
No single step is larger than the 0.25 cap, which is exactly what stops this being a jump cut: the change has to be spread across the clips instead of landing all at once.
Same speaker? No similarity score is available here — the eurospeech clips in this chain are not covered by either speaker-embedding store. The chain therefore rests on the corpus's own speaker/track labelling, which is not the same as a measured check.
Voice consistency: these clips are separate recordings joined together, and no voice-similarity check could be run for this sample, so there is no measurement of how closely the voices match. You may hear the voice shift between segments. Voice conversion has not been applied yet in this build. A planned pass will re-render every segment onto the first segment's voice, which removes this effect entirely.
5 clips · 72 s · el · eurospeech
k 5d_a -0.669d_b -0.669step_a 0.192step_b 0.192min_cos_consec —min_cos_anchor —dataset eurospeechlang elspeaker greece_olomeleia-20110113-track greece_olomeleia-20110113-total 71.8slevel spread 7.7 dBmax seam 4.3 dB
Script — 5 chunks, 0 with a non-speech sound
Unchanged across all 5 clips: a middle-aged masculine voice · balanced body, quiet background
(contempt, shame, anger · measured, subdued, slightly relaxed, monologue)αν υπάρχει κεντρική πρωτοβουλία γιατί υπάρχει απροθυμία περιφερειακών οργάνων και οι περιφερειάρχες αυτήν τη στιγμή το πρώτο πράγμα που «κλαίνε» είναι η οριοθέτηση λατομικών ζωνών. Δεν έχουν αδρανή υλικά
full caption & clip details
A middle-aged masculine voice; delivery is subdued, measured, slightly relaxed, steady; timbre is neutral-toned, slightly dark, slightly rough, balanced body; somewhat unclear, some disfluency, fairly narrow pitch, light breath; affect is neutral, neutral stance, slightly guarded; reads as contempt, shame, anger; style: monologue, authoritative; average recording, quiet background; genuineness 1.7/6; vocal-burst blend 0.9/10; 17.1s, EL.
greece_olomeleia-20110113-part2_2968144_2985232 · in -24.5 dBFS · gain +4.5 dB · eurospeech-00673
(contempt, disgust, sourness·normal-paced, energised, slightly relaxed, authoritative)όπου θα οριοθετηθούν λατομικές ζώνες γιατί αυτήν τη στιγμή πολλές απ’ αυτές παύουν να λειτουργούν, έχουν κορεστεί ή χρειάζονται αναπλάσεις. Δεύτερον, με τους υδάτινους πόρους
full caption & clip details
A young adult masculine voice; delivery is energised, normal-paced, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; average clarity, almost no disfluency, wide pitch range, normal breath; affect is neutral, slightly dominant, fairly guarded; reads as contempt, disgust, sourness; style: authoritative, dramatic; good recording, quiet background; genuineness 0.9/6; vocal-burst blend 0.0/10; 10.8s, EL.
greece_olomeleia-20110113-part2_3001920_3012720 · in -20.2 dBFS · gain +0.2 dB · eurospeech-00673
(thankfulness gratitude, shame, malevolence malice·measured, normally alert, slightly relaxed, authoritative)Τέταρτον: Οδική, σιδηροδρομική, λιμενική υποδομή. Πώς μιλάμε για βιομηχανικές περιοχές δίχως σιδηρόδρομο; Στην Ελλάδα ο ΟΣΕ
full caption & clip details
A middle-aged masculine voice; delivery is normally alert, measured, slightly relaxed, fairly steady; timbre is slightly cool, neutral-bright, slightly rough, balanced body; somewhat unclear, some disfluency, wide pitch range, normal breath; affect is neutral, slightly dominant, fairly guarded; reads as thankfulness gratitude, shame, malevolence malice; style: authoritative, monologue; average recording, quiet background; genuineness 2.0/6; vocal-burst blend 1.3/10; 11.5s, EL.
greece_olomeleia-20110113-part2_3031600_3043072 · in -16.9 dBFS · gain -3.1 dB · eurospeech-00673
(bitterness, anger, triumph· measured, normally alert, neutral tension, storytelling)δηλώνει αδυναμία να αποδώσει λόγω της καθυστέρησης να εξυπηρετήσει τους πολίτες με τη μεγάλη διάρκεια των διαδρομών, με τη χρονοκαθυστέρηση, αλλά και γιατί δεν κάνει μεταφορά εμπορευμάτων.
full caption & clip details
A middle-aged masculine voice; delivery is normally alert, measured, neutral tension, fairly steady; timbre is neutral-toned, slightly dark, rough, balanced body; somewhat unclear, some disfluency, wide pitch range, normal breath; affect is neutral, slightly dominant, slightly guarded; reads as bitterness, anger, triumph; style: storytelling, cartoonish; average recording, quiet background; genuineness 3.4/6; vocal-burst blend 1.4/10; 15.7s, EL.
greece_olomeleia-20110113-part2_3043072_3058816 · in -19.5 dBFS · gain -0.5 dB · eurospeech-00673
(teasing, contempt, shame· measured, normally alert, neutral tension, authoritative)Δεν συνδέεται με τα λιμάνια μας. Γραμμές που υπήρχαν παλιά στα λιμάνια έχουν καταργηθεί. Τα τρένα που πέρναγαν κάθε μισή ώρα κάποτε και είχαν και εμπορεύματα, δεν υπάρχουν. Τώρα είναι μόνο οι απλές γραμμές.
full caption & clip details
A middle-aged masculine voice; delivery is normally alert, measured, neutral tension, moderately variable; timbre is slightly cool, neutral-bright, slightly rough, balanced body; somewhat unclear, some disfluency, wide pitch range, normal breath; affect is neutral, slightly dominant, slightly guarded; reads as teasing, contempt, shame; style: authoritative, cartoonish; average recording, quiet background; genuineness 4.1/6; vocal-burst blend 3.1/10; 16.1s, EL.
greece_olomeleia-20110113-part2_3058816_3074960 · in -17.4 dBFS · gain -2.6 dB · eurospeech-00673
RANG — pitch range used ↑c-eurospeech-VN1 · #13
This is a VoiceNet dimension, not an emotion: pitch range used (RANG) describes the voice or the recording itself — how it sounds — rather than what the speaker feels. The rule asked it to sweep by at least 0.20.
The chain starts with pitch range used (RANG) above average — 0.74, higher than 74 % of clips in this corpus — and ends with it at the very top of the range at 0.97, higher than 97 % of clips in this corpus. That is a total rise of 0.24.
It takes 2 clips to get there. Clip to clip the moves are +0.24 — a single step, so there is no internal shape to speak of.
No single step is larger than the 0.25 cap, which is exactly what stops this being a jump cut: the change has to be spread across the clips instead of landing all at once.
Same speaker? No similarity score is available here — the eurospeech clips in this chain are not covered by either speaker-embedding store. The chain therefore rests on the corpus's own speaker/track labelling, which is not the same as a measured check.
Voice consistency: these clips are separate recordings joined together, and no voice-similarity check could be run for this sample, so there is no measurement of how closely the voices match. You may hear the voice shift between segments. Voice conversion has not been applied yet in this build. A planned pass will re-render every segment onto the first segment's voice, which removes this effect entirely.
2 clips · 36 s · el · eurospeech
k 2d_a 0.237d_b 0.237step_a 0.237step_b 0.237min_cos_consec —min_cos_anchor —dataset eurospeechlang elspeaker greece_olomeleia-20110713track greece_olomeleia-20110713total 35.8slevel spread 0.5 dBmax seam 0.5 dB
Script — 2 chunks, 0 with a non-speech sound
Unchanged across all 2 clips: a middle-aged masculine voice · slightly cool, neutral-bright, slightly rough, average recording, quiet background, moderately variable, very clear, wide pitch range
(anger, triumph, impatience and irritability · measured, normally alert, slightly relaxed, cartoonish)Δεν μπορεί να βελτιώνεται η αοριστία με προφορικές δηλώσεις στο ακροατήριο. Για ποιο λόγο δεν μπορεί; Είναι τυπικό, άραγε, αυτό; Δεν μπορεί -το επαναλαμβάνω- διότι δεν τηρείται η απαραίτητη προδικασία.
full caption & clip details
A middle-aged masculine voice; delivery is normally alert, measured, slightly relaxed, moderately variable; timbre is slightly cool, neutral-bright, slightly rough, balanced body; very clear, frequent disfluency, wide pitch range, normal breath; affect is neutral, slightly dominant, fairly guarded; reads as anger, triumph, impatience and irritability; style: cartoonish, authoritative; average recording, quiet background; genuineness 2.0/6; vocal-burst blend 0.9/10; 19.1s, EL.
greece_olomeleia-20110713_8338771_8357824 · in -22.3 dBFS · gain +2.3 dB · eurospeech-00678
(bitterness, disgust, teasing·brisk, energised, slightly tense, cartoonish)Τα ζητήματα της αστικής δίκης είναι εξαιρετικά σύνθετα. Δεν μπορεί να απαντά ο διάδικος ακούγοντας εκείνη την ώρα το πώς βελτιώνεται το δικόγραφο. Γι’ αυτό και έχουμε στα πολυμελή προκαταθέσεις είκοσι μέρες πριν,
full caption & clip details
An adult masculine voice; delivery is energised, brisk, slightly tense, moderately variable; timbre is slightly cool, neutral-bright, slightly rough, thin; very clear, some disfluency, wide pitch range, normal breath; affect is neutral, slightly dominant, fairly guarded; reads as bitterness, disgust, teasing; style: cartoonish, ranting; average recording, quiet background; genuineness 3.1/6; vocal-burst blend 4.5/10; 16.6s, EL.
greece_olomeleia-20110713_8357824_8374448 · in -21.8 dBFS · gain +1.8 dB · eurospeech-00678
R_HEAD — resonance: head ↑c-eurospeech-VN1 · #14
This is a VoiceNet dimension, not an emotion: resonance: head (R_HEAD) describes the voice or the recording itself — how it sounds — rather than what the speaker feels. The rule asked it to sweep by at least 0.50.
The chain starts with resonance: head (R_HEAD) around average — 0.45, lower than 55 % of clips in this corpus — and ends with it at the very top of the range at 0.96, higher than 96 % of clips in this corpus. That is a total rise of 0.51.
It takes 4 clips to get there. Clip to clip the moves are +0.20, then +0.24, then +0.07 — an uneven climb, but always in the same direction.
No single step is larger than the 0.25 cap, which is exactly what stops this being a jump cut: the change has to be spread across the clips instead of landing all at once.
Same speaker? No similarity score is available here — the eurospeech clips in this chain are not covered by either speaker-embedding store. The chain therefore rests on the corpus's own speaker/track labelling, which is not the same as a measured check.
Voice consistency: these clips are separate recordings joined together, and no voice-similarity check could be run for this sample, so there is no measurement of how closely the voices match. You may hear the voice shift between segments. Voice conversion has not been applied yet in this build. A planned pass will re-render every segment onto the first segment's voice, which removes this effect entirely.
4 clips · 63 s · da · eurospeech
k 4d_a 0.512d_b 0.512step_a 0.236step_b 0.236min_cos_consec —min_cos_anchor —dataset eurospeechlang daspeaker denmark_20222M015_2023-01-track denmark_20222M015_2023-01-total 63.4slevel spread 0.4 dBmax seam 0.4 dB
Script — 4 chunks, 1 with a non-speech sound
Unchanged across all 4 clips: an adult feminine voice · slightly cool, neutral-bright, fairly smooth, average recording, moderately variable
(sourness, interest, impatience and irritability · normal-paced, normally alert, neutral tension, dramatic)indskrænket fleksibiliteten i uddannelsessystemet, så man mere og mere kun kan lykkes, hvis man er én slags ung. Vi er jo forskellige mennesker, og vi uddanner os forskelligt, også på forskellige steder i livet, og vi har
full caption & clip details
An adult feminine voice; delivery is normally alert, normal-paced, neutral tension, moderately variable; timbre is slightly cool, neutral-bright, fairly smooth, thin; average clarity, some disfluency, wide pitch range, normal breath; affect is neutral, slightly dominant, slightly guarded; reads as sourness, interest, impatience and irritability; style: dramatic; average recording, quiet background; genuineness 3.8/6; vocal-burst blend 2.0/10; 15.6s, DA.
denmark_20222M015_2023-01-19_0900_39313776_39329392 · in -23.0 dBFS · gain +3.0 dB · eurospeech-00476
(emotional numbness, concentration, pain·measured, normally alert, slightly relaxed, monologue)brug for et (ahem) uddannelsessystem, der er langt mere fleksibelt. I så rigt et land som Danmark bør man ikke reducere og skære i uddannelser, men bør investere i dem.
full caption & clip details
An elderly feminine voice; delivery is normally alert, measured, slightly relaxed, moderately variable; timbre is slightly cool, neutral-bright, fairly smooth, thin; very clear, almost no disfluency, very wide pitch range, audible breath; affect is neutral, slightly dominant, slightly guarded; reads as emotional numbness, concentration, pain; style: monologue, dramatic; average recording, quiet background; genuineness 1.9/6; vocal-burst blend 0.6/10; 12.7s, DA.
denmark_20222M015_2023-01-19_0900_39329392_39342064 · in -23.1 dBFS · gain +3.1 dB · eurospeech-00476
(infatuation, affection, contemplation·brisk, energised, neutral tension, casual)Det må gerne gøre ondt, hvis man skal gøre noget godt for klimaet. Det tænker jeg måske godt kunne være noget, Alternativet kunne have fundet på at sige på et eller andet tidspunkt. Det kan godt være, at jeg har misforstået det, men det er den udlægning, jeg nogle gange oplever, når jeg hører Alternativet tale. Derfor vil jeg gerne spørge ind til det her med at sætte store bededag til folkeafstemning.
full caption & clip details
A young adult feminine voice; delivery is energised, brisk, neutral tension, moderately variable; timbre is slightly cool, neutral-bright, fairly smooth, slightly thin; average clarity, some disfluency, wide pitch range, light breath; affect is positive, slightly dominant, neutral openness; reads as infatuation, affection, contemplation; style: casual, playful; average recording, quiet background; genuineness 4.8/6; vocal-burst blend 5.5/10; 20.0s, DA.
denmark_20222M015_2023-01-19_0900_39352831_39372831 · in -22.9 dBFS · gain +2.9 dB · eurospeech-00476
(concentration, contempt, shame· brisk, energised, neutral tension)Hvis nu man skal begynde at sætte alt muligt, som borgerne er utilfredse med, til folkeafstemning, hvor stopper det så? Så jeg vil gerne høre fru Franciska Rosenkilde: Hvor går grænsen? Og for resten vil jeg sige tillykke med debuten; det nåede jeg ikke at sige.
full caption & clip details
A young adult feminine voice; delivery is energised, brisk, neutral tension, moderately variable; timbre is slightly cool, neutral-bright, fairly smooth, balanced body; average clarity, some disfluency, wide pitch range, normal breath; affect is positive, slightly dominant, slightly guarded; reads as concentration, contempt, shame; average recording, some background noise; genuineness 3.8/6; vocal-burst blend 3.0/10; 14.6s, DA.
denmark_20222M015_2023-01-19_0900_39372831_39387471 · in -23.2 dBFS · gain +3.2 dB · eurospeech-00476
VOLT — loudness / volume ↓c-eurospeech-VN1 · #15
This is a VoiceNet dimension, not an emotion: loudness / volume (VOLT) describes the voice or the recording itself — how it sounds — rather than what the speaker feels. The rule asked it to sweep by at least 0.50.
The chain starts with loudness / volume (VOLT) above average — 0.67, higher than 67 % of clips in this corpus — and works its way down to low at 0.12, lower than 88 % of clips in this corpus. That is a total fall of 0.55.
It takes 4 clips to get there. Clip to clip the moves are -0.10, then -0.23, then -0.22 — an uneven climb, but always in the same direction.
No single step is larger than the 0.25 cap, which is exactly what stops this being a jump cut: the change has to be spread across the clips instead of landing all at once.
Same speaker? No similarity score is available here — the eurospeech clips in this chain are not covered by either speaker-embedding store. The chain therefore rests on the corpus's own speaker/track labelling, which is not the same as a measured check.
Voice consistency: these clips are separate recordings joined together, and no voice-similarity check could be run for this sample, so there is no measurement of how closely the voices match. You may hear the voice shift between segments. Voice conversion has not been applied yet in this build. A planned pass will re-render every segment onto the first segment's voice, which removes this effect entirely.
4 clips · 56 s · lt · eurospeech
k 4d_a -0.552d_b -0.552step_a 0.231step_b 0.231min_cos_consec —min_cos_anchor —dataset eurospeechlang ltspeaker lithuania_lithuania_19_151track lithuania_lithuania_19_151total 55.7slevel spread 6.9 dBmax seam 6.0 dB
Script — 4 chunks, 1 with a non-speech sound
Unchanged across all 4 clips: a young adult masculine voice · average recording, quiet background, slightly relaxed
(normal-paced, energised, fairly steady, dramatic)Balsuojame dėl komiteto siūlymo įstatymo projektą atmesti.
full caption & clip details
A young adult masculine voice; delivery is energised, normal-paced, slightly relaxed, fairly steady; timbre is slightly cool, neutral-bright, fairly smooth, balanced body; average clarity, some disfluency, wide pitch range, normal breath; affect is neutral, slightly dominant, fairly guarded; no dominant emotion; style: dramatic, authoritative; average recording, quiet background; genuineness 1.2/6; vocal-burst blend 0.0/10; 15.0s, LT.
lithuania_lithuania_19_15112007_2820640_2835640 · in -24.2 dBFS · gain +4.2 dB · eurospeech-01910
(sourness, malevolence malice, contempt· normal-paced, normally alert, fairly steady, monologue)Siūloma, kad valstybės kontrolierius savo išvadą dėl biudžeto projekto teiktų ne tik Biudžeto ir finansų komitetui iki lapkričio 15 dienos, bet ir Audito komitetui. Taip Audito komitetas įgytų
full caption & clip details
A middle-aged masculine voice; delivery is normally alert, normal-paced, slightly relaxed, fairly steady; timbre is neutral-toned, slightly dark, slightly rough, thin; somewhat unclear, frequent disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as sourness, malevolence malice, contempt; style: monologue, authoritative; average recording, quiet background; genuineness 4.5/6; vocal-burst blend 3.0/10; 16.4s, LT.
lithuania_lithuania_19_15112007_2885120_2901504 · in -18.3 dBFS · gain -1.7 dB · eurospeech-01910
(triumph, pride· normal-paced, normally alert, fairly steady, monologue)(low mumble) išskirtinę teisę, skirtingai negu kiti komitetai, parengti savo išvadą dėl valstybės biudžeto projekto Biudžeto ir finansų komitetui iki lapkričio 29 dienos.
full caption & clip details
An adult masculine voice; delivery is normally alert, normal-paced, slightly relaxed, fairly steady; timbre is neutral-toned, slightly dark, fairly smooth, thin; somewhat unclear, frequent disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as triumph, pride; style: monologue, casual; average recording, quiet background; genuineness 4.8/6; vocal-burst blend 1.9/10; 13.5s, LT.
lithuania_lithuania_19_15112007_2901504_2915008 · in -18.4 dBFS · gain -1.6 dB · eurospeech-01910
(affection, thankfulness gratitude·measured, normally alert, steady, didactic)Išskiria šį komitetą iš visų kitų tarpo, o pagal mūsų Statutą pagrindinis komitetas biudžeto
full caption & clip details
A middle-aged masculine voice; delivery is normally alert, measured, slightly relaxed, steady; timbre is neutral-toned, slightly dark, slightly rough, balanced body; somewhat unclear, frequent disfluency, fairly narrow pitch, audible breath; affect is neutral, neutral stance, slightly guarded; reads as affection, thankfulness gratitude; style: didactic, monologue; average recording, quiet background; genuineness 2.8/6; vocal-burst blend 0.1/10; 10.4s, LT.
lithuania_lithuania_19_15112007_2915008_2925385 · in -17.3 dBFS · gain -2.7 dB · eurospeech-01910
S_RANT — style: ranting ↓c-eurospeech-VN1 · #16
This is a VoiceNet dimension, not an emotion: style: ranting (S_RANT) describes the voice or the recording itself — how it sounds — rather than what the speaker feels. The rule asked it to sweep by at least 0.20.
The chain starts with style: ranting (S_RANT) high — 0.85, higher than 85 % of clips in this corpus — and works its way down to around average at 0.51, higher than 51 % of clips in this corpus. That is a total fall of 0.34.
It takes 3 clips to get there. Clip to clip the moves are -0.14, then -0.20 — an even, steady climb — each clip carries about the same share.
No single step is larger than the 0.25 cap, which is exactly what stops this being a jump cut: the change has to be spread across the clips instead of landing all at once.
Same speaker? No similarity score is available here — the eurospeech clips in this chain are not covered by either speaker-embedding store. The chain therefore rests on the corpus's own speaker/track labelling, which is not the same as a measured check.
Voice consistency: these clips are separate recordings joined together, and no voice-similarity check could be run for this sample, so there is no measurement of how closely the voices match. You may hear the voice shift between segments. Voice conversion has not been applied yet in this build. A planned pass will re-render every segment onto the first segment's voice, which removes this effect entirely.
3 clips · 42 s · hr · eurospeech
k 3d_a -0.338d_b -0.338step_a 0.201step_b 0.201min_cos_consec —min_cos_anchor —dataset eurospeechlang hrspeaker croatia_20160413073259-230track croatia_20160413073259-230total 41.8slevel spread 6.3 dBmax seam 3.9 dB
Script — 3 chunks, 0 with a non-speech sound
Unchanged across all 3 clips: a middle-aged masculine voice · neutral-toned, slightly rough, average recording, quiet background, measured, somewhat unclear, normal breath
(malevolence malice, contempt, pain · normally alert, neutral tension, fairly steady, storytelling)Pa vam potpredsjedniče ove tragikomične Vlade postavljam pitanje, do kada vi to svojim ponašanjem mislite tolerirati ova bolesni,
full caption & clip details
A middle-aged masculine voice; delivery is normally alert, measured, neutral tension, fairly steady; timbre is neutral-toned, slightly dark, slightly rough, balanced body; somewhat unclear, frequent disfluency, wide pitch range, normal breath; affect is neutral, slightly dominant, fairly guarded; reads as malevolence malice, contempt, pain; style: storytelling, monologue; average recording, quiet background; genuineness 2.3/6; vocal-burst blend 1.8/10; 15.5s, HR.
croatia_20160413073259-23041_11530256_11545759 · in -34.8 dBFS · gain +14.8 dB · eurospeech-01448
(relief, triumph·very low-energy, relaxed, moderately variable, monologue)primitivni povratak ustaštvo, ovu ustašofiliju i tako sramotiti Hrvatsku državu i hrvatski narod? **Reiner, Željko (HDZ)** Hvala lijepa. Ja bih samo zamolio da
full caption & clip details
An elderly masculine voice; delivery is very low-energy, measured, relaxed, moderately variable; timbre is neutral-toned, slightly dark, slightly rough, balanced body; somewhat unclear, frequent disfluency, fairly narrow pitch, normal breath; affect is mildly negative, neutral stance, slightly guarded; reads as relief, triumph; style: monologue, casual; average recording, quiet background; genuineness 3.1/6; vocal-burst blend 2.5/10; 13.1s, HR.
croatia_20160413073259-23041_11545759_11558880 · in -32.4 dBFS · gain +12.4 dB · eurospeech-01448
(shame, thankfulness gratitude, pride· very low-energy, neutral tension, fairly steady, casual)pazimo kakve riječi rabimo jer priča o tragikomičnim Vladama i slične stvari nisu primjerene, nisu
full caption & clip details
A middle-aged masculine voice; delivery is very low-energy, measured, neutral tension, fairly steady; timbre is neutral-toned, neutral-bright, slightly rough, booming; somewhat unclear, some disfluency, moderate pitch range, normal breath; affect is mildly negative, slightly dominant, fairly guarded; reads as shame, thankfulness gratitude, pride; style: casual, monologue; average recording, quiet background; genuineness 3.5/6; vocal-burst blend 4.8/10; 12.8s, HR.
croatia_20160413073259-23041_11558880_11571712 · in -28.5 dBFS · gain +8.5 dB · eurospeech-01448
VALS — valence stability ↑c-eurospeech-VN1 · #17
This is a VoiceNet dimension, not an emotion: valence stability (VALS) describes the voice or the recording itself — how it sounds — rather than what the speaker feels. The rule asked it to sweep by at least 0.50.
The chain starts with valence stability (VALS) low — 0.25, lower than 75 % of clips in this corpus — and ends with it high at 0.81, higher than 81 % of clips in this corpus. That is a total rise of 0.56.
It takes 4 clips to get there. Clip to clip the moves are +0.18, then +0.17, then +0.21 — an even, steady climb — each clip carries about the same share.
No single step is larger than the 0.25 cap, which is exactly what stops this being a jump cut: the change has to be spread across the clips instead of landing all at once.
Same speaker? No similarity score is available here — the eurospeech clips in this chain are not covered by either speaker-embedding store. The chain therefore rests on the corpus's own speaker/track labelling, which is not the same as a measured check.
Voice consistency: these clips are separate recordings joined together, and no voice-similarity check could be run for this sample, so there is no measurement of how closely the voices match. You may hear the voice shift between segments. Voice conversion has not been applied yet in this build. A planned pass will re-render every segment onto the first segment's voice, which removes this effect entirely.
4 clips · 61 s · pt · eurospeech
k 4d_a 0.562d_b 0.562step_a 0.214step_b 0.214min_cos_consec —min_cos_anchor —dataset eurospeechlang ptspeaker portugal_10_2_1track portugal_10_2_1total 60.6slevel spread 0.3 dBmax seam 0.3 dB
Script — 4 chunks, 0 with a non-speech sound
Unchanged across all 4 clips: a young adult masculine voice · slightly cool, neutral-bright, quiet background, highly aroused, tense, audible breath
(interest, disgust, pride · brisk, moderately variable, almost no disfluency, authoritative)Entendemos que este sistema, sendo objectivamente muito melhor do que aquele que está a ser proposto pelo Governo, não é contudo o que melhor defende todos os trabalhadores, nomeadamente os trabalhadores com os salários mais baixos. Mas o mais grave
full caption & clip details
A young adult masculine voice; delivery is highly aroused, brisk, tense, moderately variable; timbre is slightly cool, neutral-bright, slightly rough, balanced body; clear, almost no disfluency, wide pitch range, audible breath; affect is elated, slightly dominant, guarded; reads as interest, disgust, pride; style: authoritative, cartoonish; average recording, quiet background; genuineness 1.2/6; vocal-burst blend 4.7/10; 15.8s, PT.
portugal_10_2_1_2037264_2053024 · in -22.1 dBFS · gain +2.1 dB · eurospeech-02414
(impatience and irritability, anger, bitterness·fast, moderately variable, some disfluency, cartoonish)grave é vermos que há um conjunto de medidas propostas pelo Governo, que são avançadas nas propostas governamentais, que mantém
full caption & clip details
A middle-aged masculine voice; delivery is highly aroused, fast, tense, moderately variable; timbre is slightly cool, neutral-bright, very rough, thin; very clear, some disfluency, very wide pitch range, audible breath; affect is elated, very dominant, guarded; reads as impatience and irritability, anger, bitterness; style: cartoonish, dramatic; poor recording, quiet background; genuineness 2.3/6; vocal-burst blend 3.6/10; 10.4s, PT.
portugal_10_2_1_2053024_2063391 · in -22.2 dBFS · gain +2.2 dB · eurospeech-02414
(sourness, interest, contempt· fast, moderately variable, almost no disfluency, dramatic)a concentração do sistema fechado sobre o Estado, ignorando a opção do plafonamento que está prevista na lei de bases desde 1984, e que parece resumir-se a um sofisticado exercício matemático, que só tem duas conclusões:
full caption & clip details
An adult masculine voice; delivery is highly aroused, fast, tense, moderately variable; timbre is slightly cool, neutral-bright, rough, thin; very clear, almost no disfluency, very wide pitch range, audible breath; affect is elated, dominant, guarded; reads as sourness, interest, contempt; style: dramatic, authoritative; average recording, quiet background; genuineness 1.5/6; vocal-burst blend 3.7/10; 15.5s, PT.
portugal_10_2_1_2063391_2078912 · in -21.9 dBFS · gain +1.9 dB · eurospeech-02414
(contempt, anger, malevolence malice·normal-paced, volatile, almost no disfluency, authoritative)por um lado, aumentar as contribuições e, por outro lado, reduzir as pensões. Isto é, primeiro, por vias directas e indirectas, reduzir os direitos dos pensionistas e, segundo, por vias directas e indirectas, aumentar a taxa social única.
full caption & clip details
A middle-aged masculine voice; delivery is highly aroused, normal-paced, tense, volatile; timbre is slightly cool, neutral-bright, rough, thin; very clear, almost no disfluency, very wide pitch range, audible breath; affect is elated, very dominant, guarded; reads as contempt, anger, malevolence malice; style: authoritative, cartoonish; below-average recording, quiet background; genuineness 1.3/6; vocal-burst blend 4.1/10; 18.5s, PT.
portugal_10_2_1_2078912_2097392 · in -22.2 dBFS · gain +2.2 dB · eurospeech-02414
WARM — warmth ↓c-eurospeech-VN1 · #18
This is a VoiceNet dimension, not an emotion: warmth (WARM) describes the voice or the recording itself — how it sounds — rather than what the speaker feels. The rule asked it to sweep by at least 0.50.
The chain starts with warmth (WARM) high — 0.82, higher than 82 % of clips in this corpus — and works its way down to low at 0.14, lower than 86 % of clips in this corpus. That is a total fall of 0.68.
It takes 4 clips to get there. Clip to clip the moves are -0.23, then -0.20, then -0.25 — an even, steady climb — each clip carries about the same share.
No single step is larger than the 0.25 cap, which is exactly what stops this being a jump cut: the change has to be spread across the clips instead of landing all at once.
Same speaker? No similarity score is available here — the eurospeech clips in this chain are not covered by either speaker-embedding store. The chain therefore rests on the corpus's own speaker/track labelling, which is not the same as a measured check.
Voice consistency: these clips are separate recordings joined together, and no voice-similarity check could be run for this sample, so there is no measurement of how closely the voices match. You may hear the voice shift between segments. Voice conversion has not been applied yet in this build. A planned pass will re-render every segment onto the first segment's voice, which removes this effect entirely.
4 clips · 60 s · en · eurospeech
k 4d_a -0.680d_b -0.680step_a 0.248step_b 0.248min_cos_consec —min_cos_anchor —dataset eurospeechlang enspeaker uk_uk_16_23032022track uk_uk_16_23032022total 60.5slevel spread 1.4 dBmax seam 1.4 dB
Script — 4 chunks, 2 with a non-speech sound
Unchanged across all 4 clips: a middle-aged masculine voice · average recording, quiet background, some disfluency
(concentration, thankfulness gratitude · normal-paced, normally alert, slightly relaxed, dramatic)We are maintaining generous levels of support for devolved Administrations, in Scotland, in Wales and in parts of England. So it is vital that UK taxpayers can be assured that they are receiving value for money for expenditure behind devolved curtains. Will the
full caption & clip details
A middle-aged masculine voice; delivery is normally alert, normal-paced, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, full; clear, some disfluency, moderate pitch range, light breath; affect is mildly positive, slightly dominant, slightly guarded; reads as concentration, thankfulness gratitude; style: dramatic, storytelling; average recording, quiet background; genuineness 0.5/6; vocal-burst blend 1.4/10; 17.7s, EN.
uk_uk_16_23032022_10521792_10539504 · in -24.7 dBFS · gain +4.7 dB · eurospeech-00900
(thankfulness gratitude, relief· normal-paced, normally alert, neutral tension, conversational)Will the new Cabinet Efficiency and Value for Money Committee be paying attention (ahem) to
full caption & clip details
An adult masculine voice; delivery is normally alert, normal-paced, neutral tension, fairly steady; timbre is neutral-toned, neutral-bright, slightly rough, balanced body; average clarity, some disfluency, wide pitch range, light breath; affect is neutral, slightly dominant, slightly guarded; reads as thankfulness gratitude, relief; style: conversational, authoritative; average recording, quiet background; genuineness 3.0/6; vocal-burst blend 1.2/10; 10.5s, EN.
uk_uk_16_23032022_10539504_10550047 · in -23.9 dBFS · gain +3.9 dB · eurospeech-00900
(relief, affection, thankfulness gratitude ·brisk, energised, neutral tension, conversational)his suggestion and having further conversations with him about it. I am glad that (ahem) over 1 million Welsh taxpayers will benefit from the announcements we made today.
full caption & clip details
A young adult masculine voice; delivery is energised, brisk, neutral tension, moderately variable; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; average clarity, some disfluency, wide pitch range, light breath; affect is positive, slightly dominant, slightly guarded; reads as relief, affection, thankfulness gratitude; style: conversational, casual; average recording, quiet background; genuineness 4.9/6; vocal-burst blend 6.2/10; 11.8s, EN.
uk_uk_16_23032022_10550047_10561824 · in -25.2 dBFS · gain +5.2 dB · eurospeech-00900
(disappointment, sourness, interest· brisk, energised, neutral tension, dramatic)The richest Member of Parliament just spoke about how he understands the impact that the cost of living crisis is having on millions of people, but what he said will sound like a cruel joke to people across the country. Energy bills are rocketing, while fossil fuel giants BP and Shell are set to make £40 billion in profits this year. Why has the Chancellor refused to introduce a windfall
full caption & clip details
A young adult feminine voice; delivery is energised, brisk, neutral tension, moderately variable; timbre is slightly cool, slightly bright, fairly smooth, thin; clear, some disfluency, wide pitch range, normal breath; affect is positive, slightly dominant, fairly guarded; reads as disappointment, sourness, interest; style: dramatic, cartoonish; average recording, quiet background; genuineness 1.8/6; vocal-burst blend 4.9/10; 20.0s, EN.
uk_uk_16_23032022_10561824_10581824 · in -24.6 dBFS · gain +4.6 dB · eurospeech-00900
This is a VoiceNet dimension, not an emotion: style: storytelling (S_STRY) describes the voice or the recording itself — how it sounds — rather than what the speaker feels. The rule asked it to sweep by at least 0.20.
The chain starts with style: storytelling (S_STRY) high — 0.81, higher than 81 % of clips in this corpus — and works its way down to below average at 0.39, lower than 61 % of clips in this corpus. That is a total fall of 0.42.
It takes 5 clips to get there. Clip to clip the moves are -0.18, then -0.10, then -0.00, then -0.14 — most of the change happening immediately, then levelling off.
No single step is larger than the 0.25 cap, which is exactly what stops this being a jump cut: the change has to be spread across the clips instead of landing all at once.
Same speaker? No similarity score is available here — the eurospeech clips in this chain are not covered by either speaker-embedding store. The chain therefore rests on the corpus's own speaker/track labelling, which is not the same as a measured check.
Voice consistency: these clips are separate recordings joined together, and no voice-similarity check could be run for this sample, so there is no measurement of how closely the voices match. You may hear the voice shift between segments. Voice conversion has not been applied yet in this build. A planned pass will re-render every segment onto the first segment's voice, which removes this effect entirely.
5 clips · 68 s · lv · eurospeech
k 5d_a -0.418d_b -0.418step_a 0.177step_b 0.177min_cos_consec —min_cos_anchor —dataset eurospeechlang lvspeaker latvia_20171122124702track latvia_20171122124702total 68.0slevel spread 1.4 dBmax seam 1.4 dB
Script — 5 chunks, 1 with a non-speech sound
Unchanged across all 5 clips: a middle-aged masculine voice · slightly cool, neutral-bright, neutral tension, moderately variable, some disfluency, wide pitch range
(contempt, confusion, distress · brisk, energised, average clarity, authoritative)šeit ir ļoti daudz jautājumu. Ko nozīmē vārds “laikus”? Ja būtu laikus, tad šis plāns jau šodien būtu uz galda. Bet nav! Mēs spriežam par šo internātskolu pastāvēšanu vai nepastāvēšanu, un kur tad ir šis “laikus”?
full caption & clip details
A middle-aged masculine voice; delivery is energised, brisk, neutral tension, moderately variable; timbre is slightly cool, neutral-bright, slightly rough, balanced body; average clarity, some disfluency, wide pitch range, light breath; affect is mildly negative, slightly dominant, fairly guarded; reads as contempt, confusion, distress; style: authoritative, monologue; below-average recording, quiet background; genuineness 2.1/6; vocal-burst blend 4.1/10; 13.4s, LV.
latvia_20171122124702_2139008_2152432 · in -24.0 dBFS · gain +4.0 dB · eurospeech-02017
(bitterness, anger, contempt · brisk, energised, somewhat unclear, authoritative)Vai Šadurska kungs ir gaišreģis, kurš paredzēs nākotni bērniem, kuri nāk ne no tām labākajām, sociālekonomiski maznodrošinātajām ģimenēm, trūcīgajām ģimenēm? Daudzi ir bāreņi, un daudzi nemaz nav draugos ar kārtību un disciplīnu.
full caption & clip details
A middle-aged masculine voice; delivery is energised, brisk, neutral tension, moderately variable; timbre is slightly cool, neutral-bright, rough, thin; somewhat unclear, some disfluency, wide pitch range, normal breath; affect is neutral, slightly dominant, fairly guarded; reads as bitterness, anger, contempt; style: authoritative, cartoonish; average recording, quiet background; genuineness 2.1/6; vocal-burst blend 6.3/10; 14.8s, LV.
latvia_20171122124702_2152432_2167232 · in -22.6 dBFS · gain +2.6 dB · eurospeech-02017
(disappointment, disgust, bitterness · brisk, highly aroused, clear, cartoonish)Kāds ir ģimeņu materiālais stāvoklis, kuras neietilpst uzturlīdzekļu saņemšanas... kurām nav šī statusa un kuru bērni mācās internātskolās? Vai ministram ir skaidrs darbības plāns, lai bērni būtu spējīgi iekļauties vispārizglītojošās skolas vidē un kā nodrošināt maksimālu profesionāļu atbalstu
full caption & clip details
A middle-aged masculine voice; delivery is highly aroused, brisk, neutral tension, moderately variable; timbre is slightly cool, neutral-bright, rough, balanced body; clear, some disfluency, wide pitch range, normal breath; affect is neutral, slightly dominant, fairly guarded; reads as disappointment, disgust, bitterness; style: cartoonish, authoritative; average recording, some background noise; genuineness 1.0/6; vocal-burst blend 3.8/10; 16.7s, LV.
latvia_20171122124702_2167232_2183968 · in -23.9 dBFS · gain +3.9 dB · eurospeech-02017
(pride, triumph, distress·measured, highly aroused, average clarity, cartoonish)un arī skolas vides, sabiedrības izpratni? Vai sociālie pedagogi, psihologi, kuri ir vajadzīgi daudziem internātskolu audzēkņiem, būs pieejami šiem audzēkņiem
full caption & clip details
A middle-aged masculine voice; delivery is highly aroused, measured, neutral tension, moderately variable; timbre is slightly cool, neutral-bright, slightly rough, balanced body; average clarity, some disfluency, wide pitch range, normal breath; affect is neutral, slightly dominant, fairly guarded; reads as pride, triumph, distress; style: cartoonish, authoritative; average recording, quiet background; genuineness 1.7/6; vocal-burst blend 1.4/10; 10.9s, LV.
latvia_20171122124702_2183968_2194912 · in -24.0 dBFS · gain +4.0 dB · eurospeech-02017
(disgust, disappointment, pride ·brisk, energised, average clarity, ranting)arī vispārizglītojošās vidusskolās, jo vēl esošajās internātskolās piespiedu kārtā 2016.gadā (low mumble) finansējuma samazinājuma rezultātā šie speciālisti tika atlaisti?
full caption & clip details
An adult masculine voice; delivery is energised, brisk, neutral tension, moderately variable; timbre is slightly cool, neutral-bright, slightly rough, thin; average clarity, some disfluency, wide pitch range, light breath; affect is neutral, slightly dominant, fairly guarded; reads as disgust, disappointment, pride; style: ranting, cartoonish; average recording, quiet background; genuineness 2.8/6; vocal-burst blend 7.4/10; 11.5s, LV.
latvia_20171122124702_2194912_2206368 · in -23.9 dBFS · gain +3.9 dB · eurospeech-02017
R_ORAL — resonance: oral ↑c-eurospeech-VN1 · #20
This is a VoiceNet dimension, not an emotion: resonance: oral (R_ORAL) describes the voice or the recording itself — how it sounds — rather than what the speaker feels. The rule asked it to sweep by at least 0.20.
The chain starts with resonance: oral (R_ORAL) around average — 0.57, higher than 57 % of clips in this corpus — and ends with it at the very top of the range at 0.94, higher than 94 % of clips in this corpus. That is a total rise of 0.37.
It takes 5 clips to get there. Clip to clip the moves are -0.05, then +0.24, then +0.10, then +0.08 — not a clean run: step 1 moves back the other way by 0.05 before the chain recovers.
No single step is larger than the 0.25 cap, which is exactly what stops this being a jump cut: the change has to be spread across the clips instead of landing all at once.
Same speaker? No similarity score is available here — the eurospeech clips in this chain are not covered by either speaker-embedding store. The chain therefore rests on the corpus's own speaker/track labelling, which is not the same as a measured check.
Voice consistency: these clips are separate recordings joined together, and no voice-similarity check could be run for this sample, so there is no measurement of how closely the voices match. You may hear the voice shift between segments. Voice conversion has not been applied yet in this build. A planned pass will re-render every segment onto the first segment's voice, which removes this effect entirely.
5 clips · 81 s · sr · eurospeech
k 5d_a 0.373d_b 0.373step_a 0.237step_b 0.237min_cos_consec —min_cos_anchor —dataset eurospeechlang srspeaker serbia_serbia_2016_1140_18track serbia_serbia_2016_1140_18total 80.7slevel spread 1.1 dBmax seam 0.9 dB
Script — 5 chunks, 1 with a non-speech sound
Unchanged across all 5 clips: an adult masculine voice · neutral-toned, neutral-bright, balanced body, average recording, normally alert, fairly steady, some disfluency
(measured, neutral tension, average clarity, authoritative)iskreno iznela svoj problem u kome je prikazala kako je izgubila sina pre 15 godina od te sekte zvane „Crna ruža“
full caption & clip details
An adult masculine voice; delivery is normally alert, measured, neutral tension, fairly steady; timbre is neutral-toned, neutral-bright, slightly rough, balanced body; average clarity, some disfluency, wide pitch range, normal breath; affect is neutral, slightly dominant, slightly guarded; no dominant emotion; style: authoritative, cartoonish; average recording, quiet background; genuineness 2.8/6; vocal-burst blend 1.6/10; 11.4s, SR.
serbia_serbia_2016_1140_18052017_2609360_2620720 · in -24.7 dBFS · gain +4.7 dB · eurospeech-02705
(disgust, thankfulness gratitude, contempt· measured, slightly relaxed, average clarity, authoritative)i njena borba ovih 15 godina da pokuša da narednim naraštajima omogući da se tako nešto nikada ne
full caption & clip details
A middle-aged masculine voice; delivery is normally alert, measured, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; average clarity, some disfluency, moderate pitch range, normal breath; affect is neutral, slightly dominant, slightly guarded; reads as disgust, thankfulness gratitude, contempt; style: authoritative, monologue; average recording, no background noise; genuineness 1.8/6; vocal-burst blend 1.2/10; 11.8s, SR.
serbia_serbia_2016_1140_18052017_2620720_2632544 · in -25.6 dBFS · gain +5.6 dB · eurospeech-02705
(triumph, concentration, relief· measured, slightly relaxed, average clarity, monologue)desi.Pokušavajući da sagledam ovaj problem interesovao sam se da vidim ko se bavim tim problemima i ko može tu da pomogne. Nekada je poslanik ovde u Skupštini bio i Slađan Mijaljević, bio je poslanik SRS, on je jedna od onih koji se bave tim problemom,
full caption & clip details
An adult masculine voice; delivery is normally alert, measured, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; average clarity, some disfluency, moderate pitch range, light breath; affect is neutral, slightly dominant, slightly guarded; reads as triumph, concentration, relief; style: monologue, authoritative; average recording, quiet background; genuineness 1.6/6; vocal-burst blend 3.0/10; 19.2s, SR.
serbia_serbia_2016_1140_18052017_2632544_2651760 · in -25.8 dBFS · gain +5.8 dB · eurospeech-02705
(anger, concentration, shame· measured, slightly relaxed, somewhat unclear, authoritative)problemom, Zoran Luković se takođe bavio tim problemom ali vidim da i ti ljudi se povlače iz tog problema, najverovatnije zbog toga što nemaju sistemsku podršku ministarstava i celokupne naše vlasti.
full caption & clip details
A middle-aged masculine voice; delivery is normally alert, measured, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, slightly rough, balanced body; somewhat unclear, some disfluency, moderate pitch range, normal breath; affect is neutral, slightly dominant, fairly guarded; reads as anger, concentration, shame; style: authoritative, monologue; average recording, quiet background; genuineness 1.5/6; vocal-burst blend 2.8/10; 19.4s, SR.
serbia_serbia_2016_1140_18052017_2651760_2671136 · in -25.2 dBFS · gain +5.2 dB · eurospeech-02705
(anger, triumph, concentration ·normal-paced, neutral tension, somewhat unclear, authoritative)Računam, da je to velik problem i da ga je teško rešiti. Ali, ako ne možemo sami nešto da uradimo, možemo da pogledamo kako su to uradile zemlje EU i to dve najače zemlje (low mumble) Francuska i Nemačka,
full caption & clip details
An adult masculine voice; delivery is normally alert, normal-paced, neutral tension, fairly steady; timbre is neutral-toned, neutral-bright, slightly rough, balanced body; somewhat unclear, some disfluency, moderate pitch range, light breath; affect is neutral, slightly dominant, slightly guarded; reads as anger, triumph, concentration; style: authoritative, monologue; average recording, quiet background; genuineness 3.0/6; vocal-burst blend 5.5/10; 18.3s, SR.
serbia_serbia_2016_1140_18052017_2671136_2689456 · in -25.0 dBFS · gain +5.0 dB · eurospeech-02705