Rule.B1 — one-sided: emotion B rises by >=T; the other axis is unconstrained Source. trajectories_v5.parquet | Family. one corpus in isolation Sampled from 350,044 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 %.
Pride ↑ (unconstrained axis: Concentration)c-eurospeech-B1 · #1
This chain comes from the one-sided rule: only Pride had to get where it was going, by at least 0.20. The other emotion was left completely free.
The chain starts with Pride strongly present — 0.75, higher than 75 % of clips in this corpus — and ends with it at the very top of the corpus at 0.98, higher than 98 % of clips in this corpus. That is a total rise of 0.22.
Nothing was asked of the other axis, and in fact Concentration barely moves at all, sitting near 0.99 throughout.
It takes 2 clips to get there. Clip to clip the moves are +0.22 — 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 · 31 s · da · eurospeech
hear it un-normalised (raw levels, max seam 1.0 dB)
k 2d_a -0.018d_b 0.223step_a 0.018step_b 0.223min_cos_consec —min_cos_anchor —dataset eurospeechlang daspeaker denmark_20141M018_2014-11-track denmark_20141M018_2014-11-total 31.1slevel spread 1.0 dBmax seam 1.0 dB
Script — 2 chunks, 1 with a non-speech sound
Unchanged across all 2 clips: an adult masculine voice · neutral-toned, fairly smooth, balanced body, average recording, quiet background, slightly relaxed, steady, somewhat unclear
(concentration, contemplation, intoxication altered states of consciousness · measured, subdued, frequent disfluency, monologue)(low mumble) Jeg synes også, det er værd at bemærke – (exhausted groan) da Liberal Alliance nu er det eneste parti, som (low mumble) stiller sig kritisk over for (low mumble) det samlede (low mumble) lovforslag – at man i betænkningen fra det, der
full caption & clip details
An adult masculine voice; delivery is subdued, measured, slightly relaxed, 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 concentration, contemplation, intoxication altered states of consciousness; style: monologue, whispered; average recording, quiet background; genuineness 3.4/6; vocal-burst blend 2.6/10; 18.4s, DA.
denmark_20141M018_2014-11-13_1000_16698720_16717167 · in -30.6 dBFS · gain +10.6 dB · eurospeech-00223
(pride, concentration, bitterness·normal-paced, normally alert, some disfluency, monologue)populært kaldes taxaudvalget, fra oktober 2013 kom med følgende anbefaling: »I forbindelse med en fremtidig ændring af reguleringen bør spørgsmålet om den skatte- og afgiftsmæssige behandling af køretøjer indgå som et element.«
full caption & clip details
An adult masculine voice; delivery is normally alert, normal-paced, slightly relaxed, steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; somewhat unclear, some disfluency, fairly narrow pitch, light breath; affect is neutral, neutral stance, slightly guarded; reads as pride, concentration, bitterness; style: monologue, formal; average recording, quiet background; genuineness 1.5/6; vocal-burst blend 1.6/10; 12.5s, DA.
denmark_20141M018_2014-11-13_1000_16717167_16729712 · in -29.6 dBFS · gain +9.6 dB · eurospeech-00223
This chain comes from the one-sided rule: only Doubt had to get where it was going, by at least 0.50. The other emotion was left completely free.
The chain starts with Doubt below average — 0.37, lower than 63 % of clips in this corpus — and ends with it strongly present at 0.87, higher than 87 % of clips in this corpus. That is a total rise of 0.51.
Nothing was asked of the other axis, and in fact Concentration drifts down from 0.95 to 0.86 (-0.09), which the rule did not require.
It takes 4 clips to get there. Clip to clip the moves are +0.23, then +0.15, then +0.12 — 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.
4 clips · 68 s · sl · eurospeech
hear it un-normalised (raw levels, max seam 0.9 dB)
k 4d_a -0.089d_b 0.508step_a 0.112step_b 0.233min_cos_consec —min_cos_anchor —dataset eurospeechlang slspeaker slovenia_slovenia_25_Rednatrack slovenia_slovenia_25_Rednatotal 67.5slevel spread 0.9 dBmax seam 0.9 dB
Script — 4 chunks, 3 with a non-speech sound
Unchanged across all 4 clips: an elderly feminine voice · neutral-bright, thin, average recording, quiet background, normal-paced, normally alert, moderately variable, some disfluency
(concentration · neutral tension, audible breath, casual, monologue)da bo dolgoročno samo kvaliteten šolski sistem na trg pripeljal kvalitetne kadre, ki bodo odgovorni za nadaljnje dobro življenje, za nadaljnji razvoj (low mumble) Slovenije, slovenskega gospodarstva.
full caption & clip details
An elderly feminine voice; delivery is normally alert, normal-paced, neutral tension, moderately variable; timbre is slightly cool, neutral-bright, slightly rough, thin; average clarity, some disfluency, moderate pitch range, audible breath; affect is mildly positive, slightly dominant, slightly guarded; reads as concentration; style: casual, monologue; average recording, quiet background; genuineness 4.2/6; vocal-burst blend 5.9/10; 15.0s, SL.
slovenia_slovenia_25_Redna_1_19112024_2699184_2714224 · in -26.1 dBFS · gain +6.1 dB · eurospeech-02671
(thankfulness gratitude, relief, hope enthusiasm optimism· neutral tension, light breath, cartoonish, monologue)(low mumble) Pričujoči proračunski dokumenti, ki jih bom seveda podprla, so korak v smer, v pravo smer, torej v razvojno smer, v optimistično smer. Zato se zahvaljujem v prvi vrsti Ministrstvu za finance in finančnemu ministru
full caption & clip details
An elderly feminine voice; delivery is normally alert, normal-paced, neutral tension, moderately variable; timbre is neutral-toned, neutral-bright, fairly smooth, thin; average clarity, some disfluency, moderate pitch range, light breath; affect is mildly positive, slightly dominant, slightly guarded; reads as thankfulness gratitude, relief, hope enthusiasm optimism; style: cartoonish, monologue; average recording, quiet background; genuineness 4.1/6; vocal-burst blend 3.7/10; 17.1s, SL.
slovenia_slovenia_25_Redna_1_19112024_2714224_2731359 · in -26.0 dBFS · gain +6.0 dB · eurospeech-02671
(shame, pride, concentration·slightly relaxed, light breath, monologue, authoritative)ter vsem ostalim ministricam in ministrom s svojimi ekipami, ki ste uspeli pripeljati proračunske dokumente v fazo tik pred sprejetjem, ki so torej pozitivno naravnani, pa kljub temu že upoštevajo novo fiskalno pravilo. Verjamem, da vam je bilo
full caption & clip details
A middle-aged feminine voice; delivery is normally alert, normal-paced, slightly relaxed, moderately variable; timbre is neutral-toned, neutral-bright, fairly smooth, thin; average clarity, some disfluency, moderate pitch range, light breath; affect is neutral, slightly dominant, slightly guarded; reads as shame, pride, concentration; style: monologue, authoritative; average recording, quiet background; genuineness 2.8/6; vocal-burst blend 3.4/10; 19.5s, SL.
slovenia_slovenia_25_Redna_1_19112024_2731359_2750832 · in -26.6 dBFS · gain +6.6 dB · eurospeech-02671
(neutral tension, audible breath, dramatic, monologue)tukaj težko klestiti (low mumble) proračunske izdatke pri upoštevanju tega fiskalnega pravila, a vam je uspelo. In za to bodo verjetno lahko hvaležne tudi naslednje generacije, saj to kaže (low mumble)
full caption & clip details
A middle-aged feminine voice; delivery is normally alert, normal-paced, neutral tension, moderately variable; timbre is neutral-toned, neutral-bright, fairly smooth, thin; average clarity, some disfluency, moderate pitch range, audible breath; affect is neutral, slightly dominant, slightly guarded; no dominant emotion; style: dramatic, monologue; average recording, quiet background; genuineness 4.0/6; vocal-burst blend 3.0/10; 15.4s, SL.
slovenia_slovenia_25_Redna_1_19112024_2750832_2766240 · in -25.7 dBFS · gain +5.7 dB · eurospeech-02671
This chain comes from the one-sided rule: only Thankfulness Gratitude had to get where it was going, by at least 0.25. The other emotion was left completely free.
The chain starts with Thankfulness Gratitude clearly present — 0.64, higher than 64 % of clips in this corpus — and ends with it at the very top of the corpus at 0.95, higher than 95 % of clips in this corpus. That is a total rise of 0.31.
Nothing was asked of the other axis, and in fact Pride drifts down from 0.96 to 0.89 (-0.07), which the rule did not require.
It takes 3 clips to get there. Clip to clip the moves are +0.07, then +0.24 — 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 · 45 s · no · eurospeech
hear it un-normalised (raw levels, max seam 1.7 dB)
k 3d_a -0.070d_b 0.333step_a 0.162step_b 0.237min_cos_consec —min_cos_anchor —dataset eurospeechlang nospeaker norway_9641-1track norway_9641-1total 44.5slevel spread 1.7 dBmax seam 1.7 dB
Script — 3 chunks, 0 with a non-speech sound
Unchanged across all 3 clips: an adult masculine voice · neutral-toned, neutral-bright, balanced body, average recording, quiet background, some disfluency, average clarity, wide pitch range
(pride, contempt · brisk, energised, neutral tension, cartoonish)Men slik jeg har lest komitéinnstillingen, vil Arbeiderpartiet stemme for samtlige forslag som regjeringspartiene foreslår som ny arbeidsmarkedspolitikk. Det er jeg fornøyd med.
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; average clarity, some disfluency, wide pitch range, light breath; affect is neutral, slightly dominant, slightly guarded; reads as pride, contempt; style: cartoonish, authoritative; average recording, quiet background; genuineness 3.9/6; vocal-burst blend 2.2/10; 13.0s, NO.
norway_9641-1_19580848_19593824 · in -30.6 dBFS · gain +10.6 dB · eurospeech-02360
(concentration, contemplation, jealousy and envy·normal-paced, normally alert, slightly relaxed, authoritative)Jeg er også svært fornøyd med at vi har fått et bredt fler tall som sikrer bedrifter økt fleksibilitet i framtiden, som senker terskelen for å komme inn i arbeidslivet, som øker fleksibiliteten for dem som er i arbeidslivet, og som gjør det enklere for ungdom, innvandrere og mennesker med nedsatt funksjons- og arbeidsevne å få jobb, enten
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, wide pitch range, light breath; affect is neutral, slightly dominant, fairly guarded; reads as concentration, contemplation, jealousy and envy; style: authoritative, monologue; average recording, quiet background; genuineness 1.9/6; vocal-burst blend 1.2/10; 19.9s, NO.
norway_9641-1_19593824_19613743 · in -28.9 dBFS · gain +8.9 dB · eurospeech-02360
(thankfulness gratitude·measured, normally alert, neutral tension, cartoonish)via midlertidige ansettelser eller gjennom å benytte de nye Navtiltakene som nå i større grad justeres etter behovet.
full caption & clip details
An adult masculine voice; delivery is normally alert, measured, neutral tension, moderately variable; 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; style: cartoonish, authoritative; average recording, quiet background; genuineness 2.9/6; vocal-burst blend 3.1/10; 11.3s, NO.
norway_9641-1_19613743_19625088 · in -29.2 dBFS · gain +9.2 dB · eurospeech-02360
Pride ↑ (unconstrained axis: Malevolence Malice)c-eurospeech-B1 · #4
This chain comes from the one-sided rule: only Pride had to get where it was going, by at least 0.20. The other emotion was left completely free.
The chain starts with Pride strongly present — 0.77, higher than 77 % of clips in this corpus — and ends with it at the very top of the corpus at 0.98, higher than 98 % of clips in this corpus. That is a total rise of 0.21.
Nothing was asked of the other axis, and in fact Malevolence Malice drifts down from 0.97 to 0.87 (-0.10), which the rule did not require.
It takes 3 clips to get there. Clip to clip the moves are -0.02, then +0.24 — not a clean run: step 1 moves back the other way by 0.02 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.
3 clips · 52 s · hr · eurospeech
hear it un-normalised (raw levels, max seam 1.7 dB)
k 3d_a -0.102d_b 0.214step_a 0.277step_b 0.237min_cos_consec —min_cos_anchor —dataset eurospeechlang hrspeaker croatia_20081120171620-345track croatia_20081120171620-345total 51.6slevel spread 3.0 dBmax seam 1.7 dB
Script — 3 chunks, 1 with a non-speech sound
Unchanged across all 3 clips: a young adult masculine voice · neutral-toned, neutral-bright, balanced body, average recording, quiet background, normally alert, some disfluency
(malevolence malice, contempt, triumph · brisk, neutral tension, moderately variable, authoritative)primjerenim cijenama trajektnih karata za automobile, dakle govorim za automobile nego da i vama koji dolazite na otok možda jednom ili dva put godišnje omogućimo da to napravite po jednoj puno pristupačnijoj cijeni jer je i nama drago kad vi dođete
full caption & clip details
A young adult masculine voice; delivery is normally alert, 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 neutral, slightly dominant, fairly guarded; reads as malevolence malice, contempt, triumph; style: authoritative, dramatic; average recording, quiet background; genuineness 2.3/6; vocal-burst blend 5.5/10; 14.5s, HR.
croatia_20081120171620-3459_3017920_3032432 · in -25.1 dBFS · gain +5.1 dB · eurospeech-01261
(doubt·measured, neutral tension, moderately variable, monologue)i kad ostanete što duže. Ostanite, ostanite koliko želite, ovaj, koliko i očekujemo dakle da se u tom smislu u sklopu te skrbi i ta situacija pokuša na taj način riješiti
full caption & clip details
An adult masculine voice; delivery is normally alert, measured, neutral tension, moderately variable; timbre is neutral-toned, neutral-bright, slightly rough, balanced body; somewhat unclear, some disfluency, wide pitch range, normal breath; affect is neutral, slightly dominant, slightly guarded; reads as doubt; style: monologue, cartoonish; average recording, quiet background; genuineness 3.6/6; vocal-burst blend 3.5/10; 18.8s, HR.
croatia_20081120171620-3459_3032432_3051216 · in -26.4 dBFS · gain +6.5 dB · eurospeech-01261
(pride, triumph, relief· measured, slightly relaxed, fairly steady, monologue)država tretira i ovo plovljenje po moru kao (low mumble) vožnju po cesti kada u toj cijeni goriva plaćamo i naknadu za državne, lokalne i županijske ceste pa neka onda doista imamo i ove plave ceste koje će se financirati iz toga. Zahvaljujem.
full caption & clip details
An adult 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, light breath; affect is neutral, neutral stance, slightly guarded; reads as pride, triumph, relief; style: monologue, casual; average recording, quiet background; genuineness 3.4/6; vocal-burst blend 4.8/10; 18.0s, HR.
croatia_20081120171620-3459_3051216_3069216 · in -28.1 dBFS · gain +8.2 dB · eurospeech-01261
This chain comes from the one-sided rule: only Interest had to get where it was going, by at least 0.20. The other emotion was left completely free.
The chain starts with Interest clearly present — 0.73, higher than 73 % of clips in this corpus — and ends with it at the very top of the corpus at 0.98, higher than 98 % of clips in this corpus. That is a total rise of 0.25.
Nothing was asked of the other axis, and in fact Sourness drifts down from 0.99 to 0.82 (-0.17), which the rule did not require.
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 · de · eurospeech
hear it un-normalised (raw levels, max seam 0.0 dB)
k 2d_a -0.168d_b 0.250step_a 0.168step_b 0.250min_cos_consec —min_cos_anchor —dataset eurospeechlang despeaker germany_7533172track germany_7533172total 26.8slevel spread 0.0 dBmax seam 0.0 dB
Script — 2 chunks, 0 with a non-speech sound
Unchanged across all 2 clips: an adult masculine voice · neutral-toned, neutral-bright, fairly smooth, balanced body, average recording, slightly relaxed, fairly steady, light breath
(sourness, pride, anger · brisk, energised, almost no disfluency, authoritative)Unsere neue Bildungs- und Forschungsministerin Bettina Stark-Watzinger hat ebenfalls gestern in ihrer Rede neue Technologien der Zukunft angesprochen und hat gefordert, dass wir Zitat aus ihrer Rede Brücken zwischen den Disziplinen bauen.
full caption & clip details
An adult masculine voice; delivery is energised, brisk, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; clear, almost no disfluency, wide pitch range, light breath; affect is neutral, slightly dominant, fairly guarded; reads as sourness, pride, anger; style: authoritative, ranting; average recording, quiet background; genuineness 1.2/6; vocal-burst blend 1.3/10; 11.8s, DE.
germany_7533172_18558528_18570288 · in -25.6 dBFS · gain +5.6 dB · eurospeech-00537
(interest, fear·normal-paced, normally alert, little disfluency, monologue)Als erstes Beispiel für all das hat die Forschungsministerin eine neue Wasserstofftechnologie genannt. Das Ziel muss natürlich sein, dass am Ende in Deutschland nur noch wirklich Grüner Wasserstoff zum Einsatz kommt, immer dann, wenn die schwankenden Energiequellen aus Wind und Sonne gerade nicht liefern können.
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, little disfluency, moderate pitch range, light breath; affect is neutral, slightly dominant, slightly guarded; reads as interest, fear; style: monologue, formal; average recording, no background noise; genuineness 1.9/6; vocal-burst blend 0.0/10; 14.9s, DE.
germany_7533172_18570288_18585216 · in -25.6 dBFS · gain +5.5 dB · eurospeech-00537
This chain comes from the one-sided rule: only Contempt had to get where it was going, by at least 0.20. The other emotion was left completely free.
The chain starts with Contempt strongly present — 0.79, higher than 79 % of clips in this corpus — and ends with it at the very top of the corpus at 1.00, virtually no clip in this corpus scores higher. That is a total rise of 0.20.
Nothing was asked of the other axis, and in fact Triumph barely moves at all, sitting near 0.97 throughout.
It takes 3 clips to get there. Clip to clip the moves are +0.15, then +0.05 — 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.
3 clips · 42 s · lt · eurospeech
k 3d_a -0.025d_b 0.203step_a 0.142step_b 0.155min_cos_consec —min_cos_anchor —dataset eurospeechlang ltspeaker lithuania_lithuania_5_1911track lithuania_lithuania_5_1911total 42.1slevel spread 6.8 dBmax seam 6.8 dB
Script — 3 chunks, 2 with a non-speech sound
Unchanged across all 3 clips: an adult masculine voice · slightly cool, thin, quiet background
(triumph, disappointment, concentration · fast, normally alert, neutral tension, dramatic)1992 m. buvo įsteigti du perinatologijos centrai, todėl pasiekėme stulbinamus rezultatus neišnešiotų naujagimių srityje, kartu sumažinome perinatalinį ir ankstyvą neonatalinį mirtingumą.
full caption & clip details
An adult masculine voice; delivery is normally alert, fast, neutral tension, moderately variable; timbre is slightly cool, neutral-bright, fairly smooth, thin; clear, some disfluency, wide pitch range, light breath; affect is neutral, slightly dominant, slightly guarded; reads as triumph, disappointment, concentration; style: dramatic, authoritative; average recording, quiet background; genuineness 2.4/6; vocal-burst blend 3.9/10; 13.5s, LT.
lithuania_lithuania_5_19112015_2445408_2458880 · in -20.8 dBFS · gain +0.8 dB · eurospeech-01957
(contempt·measured, normally alert, slightly relaxed, cartoonish)(ahem) į balą, o visos optimizacijos netenka prasmės, nes ligonių bus (ahem) tiek, kiek reikia. Ir ne optimizuoti, mažinti lovas reikės, bet jas prikurti.
full caption & clip details
A middle-aged masculine voice; delivery is normally alert, measured, slightly relaxed, fairly steady; timbre is slightly cool, slightly dark, slightly rough, thin; somewhat unclear, frequent disfluency, moderate pitch range, audible breath; affect is neutral, neutral stance, slightly guarded; reads as contempt; style: cartoonish; average recording, quiet background; genuineness 3.8/6; vocal-burst blend 1.8/10; 12.9s, LT.
lithuania_lithuania_5_19112015_2542560_2555440 · in -13.9 dBFS · gain -6.1 dB · eurospeech-01957
(contempt, anger, bitterness· measured, very low-energy, neutral tension, monologue)(ahem) Jūs labai gerai priminėte prieš 25 metus generuotas koncepcijas, nuo kurių vienas ministras nueina, kitas vėl grįžta, kitas vėl nueina į kitą pusę, kitas vėl bando sugrįžti.
full caption & clip details
A middle-aged masculine voice; delivery is very low-energy, measured, neutral tension, moderately variable; timbre is slightly cool, slightly dark, rough, thin; somewhat unclear, frequent disfluency, fairly narrow pitch, audible breath; affect is neutral, slightly dominant, fairly guarded; reads as contempt, anger, bitterness; style: monologue, authoritative; below-average recording, quiet background; genuineness 3.6/6; vocal-burst blend 4.6/10; 15.4s, LT.
lithuania_lithuania_5_19112015_2587328_2602736 · in -16.9 dBFS · gain -3.1 dB · eurospeech-01957
This chain comes from the one-sided rule: only Triumph had to get where it was going, by at least 0.25. The other emotion was left completely free.
The chain starts with Triumph clearly present — 0.60, higher than 60 % of clips in this corpus — and ends with it at the very top of the corpus at 0.99, higher than 99 % of clips in this corpus. That is a total rise of 0.38.
Nothing was asked of the other axis, and in fact Shame drifts down from 0.94 to 0.81 (-0.13), which the rule did not require.
It takes 4 clips to get there. Clip to clip the moves are +0.24, then -0.03, then +0.18 — not a clean run: step 2 moves back the other way by 0.03 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 · 65 s · sr · eurospeech
k 4d_a -0.127d_b 0.382step_a 0.379step_b 0.236min_cos_consec —min_cos_anchor —dataset eurospeechlang srspeaker serbia_serbia_2012_24_0312track serbia_serbia_2012_24_0312total 65.0slevel spread 2.8 dBmax seam 1.7 dB
Script — 4 chunks, 1 with a non-speech sound
Unchanged across all 4 clips: an adult masculine voice · neutral-bright, average recording, quiet background, fairly steady
(shame, thankfulness gratitude · normal-paced, normally alert, slightly relaxed, casual)A do kada će raditi to ćemo videti tokom dana. Nema potrebe za (low mumble) nervozom.Što se tiče inače dostojanstva Narodne skupštine, podsećam narodne poslanike iz svih poslaničkih grupa, da je obaveza poslanika Narodne skupštine da učestvuju u radu Narodne skupštine,
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 neutral, neutral stance, slightly guarded; reads as shame, thankfulness gratitude; style: casual, authoritative; average recording, quiet background; genuineness 3.2/6; vocal-burst blend 4.3/10; 15.7s, SR.
serbia_serbia_2012_24_03122013_2728816_2744512 · in -19.9 dBFS · gain -0.1 dB · eurospeech-02687
(disappointment, hope enthusiasm optimism·brisk, normally alert, slightly relaxed, authoritative)kada su sednice Narodne skupštine, pošto smo jednaki u svim drugim pravima, obaveza poslanika je da učestvuje u radu. To naravno važi za poslanike opozicije, i ja sam uveren da je vaša poslanička grupa želeći da da ogroman doprinos u raspravi o budžetu će danas aktivno učestvovati
full caption & clip details
A young adult masculine voice; delivery is normally alert, brisk, 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 disappointment, hope enthusiasm optimism; style: authoritative, monologue; average recording, quiet background; genuineness 2.5/6; vocal-burst blend 3.4/10; 15.7s, SR.
serbia_serbia_2012_24_03122013_2744512_2760240 · in -19.0 dBFS · gain -1.0 dB · eurospeech-02687
(concentration, pride·normal-paced, normally alert, slightly relaxed, authoritative)koji kaže da vreme za glasanje upotrebom elektronskog sistema iznosi 15. sekundi. Malopre smo prisustvovali najdužem čekanju, najdužih 15 sekundi u istoriji Srbije od dolaska Južnih Slovena na Balkan.Mi
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, almost no disfluency, moderate pitch range, light breath; affect is neutral, slightly dominant, slightly guarded; reads as concentration, pride; style: authoritative, monologue; average recording, quiet background; genuineness 1.0/6; vocal-burst blend 2.8/10; 14.0s, SR.
serbia_serbia_2012_24_03122013_2777024_2791024 · in -17.3 dBFS · gain -2.7 dB · eurospeech-02687
(triumph, thankfulness gratitude, pride · normal-paced, energised, neutral tension, authoritative)Balkan.Mi nikada duže nismo odbrojali 15 sekundi. Možda vama vreme stoji, nama vreme neumitno teče i ovoj vladi je vreme isteklo. Trebalo je da odredite pauzu, da ne ponižavamo Skupštinu Srbije, jer zaista neprimereno je
full caption & clip details
An adult masculine voice; delivery is energised, normal-paced, neutral tension, fairly steady; 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 triumph, thankfulness gratitude, pride; style: authoritative, monologue; average recording, quiet background; genuineness 2.0/6; vocal-burst blend 5.0/10; 19.1s, SR.
serbia_serbia_2012_24_03122013_2791024_2810160 · in -17.1 dBFS · gain -2.9 dB · eurospeech-02687
This chain comes from the one-sided rule: only Anger had to get where it was going, by at least 0.25. The other emotion was left completely free.
The chain starts with Anger clearly present — 0.58, higher than 58 % of clips in this corpus — and ends with it at the very top of the corpus at 0.96, higher than 96 % of clips in this corpus. That is a total rise of 0.38.
Nothing was asked of the other axis, and in fact Concentration drifts down from 0.97 to 0.91 (-0.06), which the rule did not require.
It takes 3 clips to get there. Clip to clip the moves are +0.19, then +0.19 — 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 · 40 s · it · eurospeech
k 3d_a -0.064d_b 0.383step_a 0.115step_b 0.193min_cos_consec —min_cos_anchor —dataset eurospeechlang itspeaker italy_15_125track italy_15_125total 40.2slevel spread 0.8 dBmax seam 0.8 dB
Script — 3 chunks, 0 with a non-speech sound
Unchanged across all 3 clips: a young adult masculine voice · slightly cool, neutral-bright, fairly smooth, thin, average recording, quiet background, brisk, energised
(concentration, pride, triumph · some disfluency, somewhat unclear, light breath, authoritative)Certo, però, che, se non bisogna essere allarmisti, c'è motivo di essere preoccupati e credo che da qui si debba partire. Ed è giusto che da qui partano i documenti che sono al nostro esame e che intendo sostenere, a cominciare dal documento presentato dai colleghi del Gruppo dell'Ulivo.
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, thin; somewhat unclear, some disfluency, wide pitch range, light breath; affect is neutral, slightly dominant, slightly guarded; reads as concentration, pride, triumph; style: authoritative, dramatic; average recording, quiet background; genuineness 3.6/6; vocal-burst blend 9.4/10; 17.8s, IT.
italy_15_125_11266848_11284655 · in -20.3 dBFS · gain +0.3 dB · eurospeech-01637
(pride, disgust, contempt·almost no disfluency, clear, normal breath, ranting)Vorrei ricordare che negli Stati Uniti esiste un'organizzazione non governativa, il *Bulletin of the atomic scientists*, il bollettino degli scienziati atomici,
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, thin; clear, almost no disfluency, wide pitch range, normal breath; affect is neutral, slightly dominant, guarded; reads as pride, disgust, contempt; style: ranting, cartoonish; average recording, quiet background; genuineness 2.5/6; vocal-burst blend 6.0/10; 10.8s, IT.
italy_15_125_11284655_11295488 · in -19.5 dBFS · gain -0.5 dB · eurospeech-01637
(anger, impatience and irritability, concentration·some disfluency, clear, light breath, ranting)che dal 1947 riporta il grado di rischio atomico del mondo su un quadrante simbolico, conosciuto come *Doomsday Clock*, l'orologio dell'Apocalisse.
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, thin; clear, some disfluency, wide pitch range, light breath; affect is neutral, slightly dominant, guarded; reads as anger, impatience and irritability, concentration; style: ranting, dramatic; average recording, quiet background; genuineness 3.2/6; vocal-burst blend 7.9/10; 11.2s, IT.
italy_15_125_11295488_11306720 · in -20.4 dBFS · gain +0.3 dB · eurospeech-01637
This chain comes from the one-sided rule: only Emotional Numbness had to get where it was going, by at least 0.20. The other emotion was left completely free.
The chain starts with Emotional Numbness clearly present — 0.65, higher than 65 % of clips in this corpus — and ends with it at the very top of the corpus at 0.99, higher than 99 % of clips in this corpus. That is a total rise of 0.33.
Nothing was asked of the other axis, and in fact Pride drifts down from 0.94 to 0.02 (-0.92), which the rule did not require.
It takes 5 clips to get there. Clip to clip the moves are -0.12, then +0.17, then +0.24, then +0.05 — not a clean run: step 1 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 · 76 s · fr · eurospeech
k 5d_a -0.925d_b 0.335step_a 0.925step_b 0.236min_cos_consec —min_cos_anchor —dataset eurospeechlang frspeaker france_france_senate_12045track france_france_senate_12045total 75.6slevel spread 3.1 dBmax seam 1.8 dB
Script — 5 chunks, 1 with a non-speech sound
Unchanged across all 5 clips: an elderly masculine voice · average recording, quiet background
(pride, relief · measured, very low-energy, relaxed, monologue)Merci, monsieur le Ministre. Monsieur le président, Monsieur le Président et blé en ce qui concerne l'application de la loi de finances pour 2018 sur l'article 68, (low mumble) je ne me rappelle pas ce pour quoi le retard a été pris, vous l'avez fait mieux que moi,
full caption & clip details
An elderly 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, audible breath; affect is mildly negative, submissive, slightly guarded; reads as pride, relief; style: monologue, casual; average recording, quiet background; genuineness 4.1/6; vocal-burst blend 4.5/10; 15.7s, FR.
france_france_senate_1204593_5d008608f2ce6_2563632_2579376 · in -30.7 dBFS · gain +10.7 dB · eurospeech-01103
(concentration·normal-paced, normally alert, neutral tension, cartoonish)une réunion interministérielle de validation du projet décret a toutefois été organisée le 19 avril 2019, le Centre national au Conseil national de la transaction la gestion immobilière désormais au complet se prononcera sur le projet relatif au plafonnement des frais le 19 juin prochain,
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, light breath; affect is neutral, slightly dominant, slightly guarded; reads as concentration; style: cartoonish, casual; average recording, quiet background; genuineness 3.1/6; vocal-burst blend 4.6/10; 16.3s, FR.
france_france_senate_1204593_5d008608f2ce6_2579376_2595680 · in -29.6 dBFS · gain +9.6 dB · eurospeech-01103
(relief, triumph, thankfulness gratitude·brisk, energised, neutral tension, casual)ouvrant la voie à la publication du décret durant l'été 2019 pour vous réponde précisément sur l'article 171 afin de trouver une solution permettant d'assurer la gratuité des péages aux véhicules des pompiers lors d'une intervention une négociation était conduite par le ministère des Transports,
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; average clarity, some disfluency, moderate pitch range, light breath; affect is neutral, slightly dominant, slightly guarded; reads as relief, triumph, thankfulness gratitude; style: casual, dramatic; average recording, quiet background; genuineness 4.0/6; vocal-burst blend 8.6/10; 13.5s, FR.
france_france_senate_1204593_5d008608f2ce6_2595680_2609216 · in -27.8 dBFS · gain +7.8 dB · eurospeech-01103
(relief, concentration, emotional numbness·normal-paced, normally alert, slightly relaxed, monologue)avec l'ensemble des sociétés concessionnaires d'autoroutes qui a permis de faire progresser le sujet la gratuité serait traité par des mesures commerciales que les concessionnaires accorderait aux véhicules des indices qui empruntent le réseau autoroutier afin d'intervenir sur des sinistres, quel que soit le lieu de l'intervention
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; average clarity, some disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as relief, concentration, emotional numbness; style: monologue; average recording, quiet background; genuineness 1.1/6; vocal-burst blend 3.3/10; 14.5s, FR.
france_france_senate_1204593_5d008608f2ce6_2609216_2623712 · in -28.1 dBFS · gain +8.1 dB · eurospeech-01103
(emotional numbness, concentration, triumph· normal-paced, normally alert, slightly relaxed, monologue)je précise sans facturation au conseil départementaux ni compensation financière de la part de l'État, le périmètre de l'accord couvre aujourd'hui 90 pourcent du réseau autoroutier concédé les concessionnaires rendront compte d'ici l'été de l'actualisation des conventions qui les lient au SDIS
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 neutral, slightly dominant, slightly guarded; reads as emotional numbness, concentration, triumph; style: monologue, dramatic; average recording, quiet background; genuineness 1.7/6; vocal-burst blend 5.0/10; 15.0s, FR.
france_france_senate_1204593_5d008608f2ce6_2623712_2638672 · in -27.7 dBFS · gain +7.7 dB · eurospeech-01103
This chain comes from the one-sided rule: only Contempt had to get where it was going, by at least 0.25. The other emotion was left completely free.
The chain starts with Contempt clearly present — 0.61, higher than 61 % of clips in this corpus — and ends with it at the very top of the corpus at 0.98, higher than 98 % of clips in this corpus. That is a total rise of 0.37.
Nothing was asked of the other axis, and in fact Concentration barely moves at all, sitting near 0.89 throughout.
It takes 4 clips to get there. Clip to clip the moves are +0.25, then +0.10, then +0.02 — 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.
4 clips · 59 s · en · eurospeech
k 4d_a -0.018d_b 0.369step_a 0.072step_b 0.250min_cos_consec —min_cos_anchor —dataset eurospeechlang enspeaker uk_uk_19_21022024track uk_uk_19_21022024total 59.1slevel spread 0.9 dBmax seam 0.9 dB
Script — 4 chunks, 2 with a non-speech sound
Unchanged across all 4 clips: a young adult masculine voice · quiet background, moderately variable, some disfluency, wide pitch range, light breath
(brisk, energised, slightly relaxed, dramatic)to ensure the safety of medical personnel and facilities. The British Government have repeated that point in all our engagements with Israeli counterparts and partners, including (ahem) during the Foreign Secretary’s visit to Israel on 24 January, and with regional partners, including Saudi Arabia,
full caption & clip details
A young adult masculine voice; delivery is energised, brisk, slightly relaxed, 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; no dominant emotion; style: dramatic, cartoonish; average recording, quiet background; genuineness 0.9/6; vocal-burst blend 2.0/10; 17.8s, EN.
uk_uk_19_21022024_11219776_11237600 · in -22.9 dBFS · gain +2.9 dB · eurospeech-00921
(anger· brisk, normally alert, neutral tension, cartoonish)give a response from the Government to the interim decisions made by the International Court of Justice—the world court—which effectively called for an immediate unilateral
full caption & clip details
A middle-aged masculine voice; delivery is normally alert, 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 neutral, slightly dominant, slightly guarded; reads as anger; style: cartoonish, monologue; average recording, quiet background; genuineness 2.2/6; vocal-burst blend 1.0/10; 10.8s, EN.
uk_uk_19_21022024_11256176_11266928 · in -23.9 dBFS · gain +3.9 dB · eurospeech-00921
(malevolence malice, sourness, anger ·normal-paced, energised, neutral tension, dramatic)halt to the hostilities by Israel against the people of Gaza? Surely, if the Government believe in the rule of international law, they should respect
full caption & clip details
An adult masculine voice; delivery is energised, normal-paced, neutral tension, moderately variable; timbre is slightly cool, neutral-bright, slightly rough, full; very clear, some disfluency, wide pitch range, light breath; affect is positive, slightly dominant, slightly guarded; reads as malevolence malice, sourness, anger; style: dramatic, cartoonish; good recording, quiet background; genuineness 1.6/6; vocal-burst blend 1.3/10; 10.4s, EN.
uk_uk_19_21022024_11266928_11277312 · in -23.8 dBFS · gain +3.8 dB · eurospeech-00921
(contempt, anger, infatuation·brisk, energised, neutral tension, dramatic)changed since I last told him (ahem) it. The most effective way now to alleviate the suffering is an immediate pause in fighting to get aid in and hostages out. That is the best route to make progress towards a future for Gaza freed from rule by Hamas. Britain has set out
full caption & clip details
A young adult masculine voice; delivery is energised, brisk, neutral tension, moderately variable; timbre is slightly cool, slightly bright, fairly smooth, full; average clarity, some disfluency, wide pitch range, light breath; affect is positive, slightly dominant, slightly guarded; reads as contempt, anger, infatuation; style: dramatic, playful; average recording, quiet background; genuineness 1.3/6; vocal-burst blend 2.9/10; 19.6s, EN.
uk_uk_19_21022024_11297312_11316960 · in -23.1 dBFS · gain +3.1 dB · eurospeech-00921
This chain comes from the one-sided rule: only Disgust had to get where it was going, by at least 0.20. The other emotion was left completely free.
The chain starts with Disgust clearly present — 0.71, higher than 71 % of clips in this corpus — and ends with it at the very top of the corpus at 0.96, higher than 96 % of clips in this corpus. That is a total rise of 0.25.
Nothing was asked of the other axis, and in fact Shame barely moves at all, sitting near 0.96 throughout.
It takes 4 clips to get there. Clip to clip the moves are +0.00, then +0.18, then +0.07 — a plateau around step 1, where it barely moves.
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 · no · eurospeech
k 4d_a -0.007d_b 0.248step_a 0.948step_b 0.181min_cos_consec —min_cos_anchor —dataset eurospeechlang nospeaker norway_9986-1track norway_9986-1total 63.4slevel spread 2.3 dBmax seam 2.3 dB
Script — 4 chunks, 1 with a non-speech sound
Unchanged across all 4 clips: an adult feminine voice · neutral-toned, average recording, some background noise, neutral tension, some disfluency
(shame, contentment, sexual lust · brisk, normally alert, moderately variable, authoritative)har vi brukt mer penger på å bygge ut veiene, på å redusere vedlikeholdsetterslepet og på å redusere bilavgiftene, sånn at det skal være mulig å holde seg med en bil også for dem som har helt vanlige (low mumble) inntekter.
full caption & clip details
An adult feminine voice; delivery is normally alert, 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 mildly positive, slightly dominant, slightly guarded; reads as shame, contentment, sexual lust; style: authoritative, didactic; average recording, some background noise; genuineness 2.7/6; vocal-burst blend 3.0/10; 18.3s, NO.
norway_9986-1_4157808_4176064 · in -24.2 dBFS · gain +4.2 dB · eurospeech-02408
(relief, fatigue exhaustion, triumph·normal-paced, very low-energy, fairly steady, casual)fikk redusert det behovsprøvde barnetillegget for dem som er uføretrygdet. Det er et veldig godt eksempel på regjeringas prioriteringer. Men mitt spørsmål knytter seg til flyktninger.
full caption & clip details
An adult masculine voice; delivery is very low-energy, normal-paced, neutral tension, fairly steady; timbre is neutral-toned, slightly dark, slightly rough, slightly thin; somewhat unclear, some disfluency, fairly narrow pitch, normal breath; affect is mildly positive, neutral stance, slightly guarded; reads as relief, fatigue exhaustion, triumph; style: casual, monologue; average recording, some background noise; genuineness 3.9/6; vocal-burst blend 4.4/10; 12.7s, NO.
norway_9986-1_4188496_4201216 · in -26.5 dBFS · gain +6.5 dB · eurospeech-02408
(pride, concentration· normal-paced, normally alert, moderately variable, casual)Folketrygdloven ble innført 1. januar 1967 av statsminister Per Borten og sosialminister Egil Aarvik. Vi fikk minstepensjon også for husmødre og sjølstendig næringsdrivende uten inntekt. Senterpartiet er stolt av det. Loven ble endret videre i 1971 slik at
full caption & clip details
An adult masculine voice; delivery is normally alert, normal-paced, neutral tension, moderately variable; timbre is neutral-toned, neutral-bright, slightly rough, balanced body; somewhat unclear, some disfluency, fairly narrow pitch, light breath; affect is neutral, neutral stance, slightly guarded; reads as pride, concentration; style: casual, monologue; average recording, some background noise; genuineness 3.3/6; vocal-burst blend 4.4/10; 16.8s, NO.
norway_9986-1_4201216_4217984 · in -25.2 dBFS · gain +5.2 dB · eurospeech-02408
(disgust, bitterness, shame· normal-paced, subdued, fairly steady, casual)flyktninger ble ansett å stå i en særstilling og fikk dermed også aldersbestemt minstepensjonen. Det som er saken i dag, er at regjeringa vil bryte med denne grunnholdningen ved at flyktninger ikke automatisk skal få minstepensjon når de passerer aldersgrensa.
full caption & clip details
An adult masculine voice; delivery is subdued, normal-paced, neutral tension, fairly steady; timbre is neutral-toned, neutral-bright, slightly rough, balanced body; somewhat unclear, some disfluency, fairly narrow pitch, normal breath; affect is mildly negative, neutral stance, slightly guarded; reads as disgust, bitterness, shame; style: casual, monologue; average recording, some background noise; genuineness 4.0/6; vocal-burst blend 5.6/10; 15.2s, NO.
norway_9986-1_4217984_4233183 · in -24.9 dBFS · gain +4.9 dB · eurospeech-02408
This chain comes from the one-sided rule: only Concentration had to get where it was going, by at least 0.25. The other emotion was left completely free.
The chain starts with Concentration clearly present — 0.69, higher than 69 % of clips in this corpus — and ends with it at the very top of the corpus at 1.00, virtually no clip in this corpus scores higher. That is a total rise of 0.31.
Nothing was asked of the other axis, and in fact Fatigue Exhaustion drifts down from 0.88 to 0.18 (-0.70), which the rule did not require.
It takes 5 clips to get there. Clip to clip the moves are +0.09, then +0.12, then +0.06, then +0.03 — 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.
5 clips · 74 s · en · eurospeech
k 5d_a -0.701d_b 0.308step_a 0.587step_b 0.117min_cos_consec —min_cos_anchor —dataset eurospeechlang enspeaker uk_uk_4_26062013track uk_uk_4_26062013total 74.2slevel spread 1.8 dBmax seam 1.3 dB
Script — 5 chunks, 5 with a non-speech sound
Unchanged across all 5 clips: a middle-aged masculine voice · neutral-toned, slightly dark, balanced body, average recording, quiet background, slightly relaxed, fairly steady, normal breath
(measured, normally alert, some disfluency, monologue)(low mumble) The Comptroller and Auditor General tells me that he expects that report to be completed next month, in July, so the (low mumble) Minister may not have to wait long before he considers action. I invite him to (low mumble)
full caption & clip details
A middle-aged masculine voice; delivery is normally alert, measured, slightly relaxed, fairly steady; timbre is neutral-toned, slightly dark, slightly rough, balanced body; average clarity, some disfluency, fairly narrow pitch, normal breath; affect is neutral, neutral stance, slightly guarded; no dominant emotion; style: monologue, whispered; average recording, quiet background; genuineness 3.5/6; vocal-burst blend 0.7/10; 12.4s, EN.
uk_uk_4_26062013_6804592_6817024 · in -29.0 dBFS · gain +9.0 dB · eurospeech-01038
(slow, very low-energy, frequent disfluency, whispered)tell the Chamber how he intends, from the centre of Government, to respond to that NAO report and the findings that it may have. (low mumble) (low mumble)
full caption & clip details
An elderly masculine voice; delivery is very low-energy, slow, slightly relaxed, fairly steady; timbre is neutral-toned, slightly dark, slightly rough, balanced body; somewhat unclear, frequent disfluency, fairly narrow pitch, normal breath; affect is neutral, neutral stance, neutral openness; no dominant emotion; style: whispered, monologue; average recording, quiet background; genuineness 2.9/6; vocal-burst blend 0.1/10; 11.0s, EN.
uk_uk_4_26062013_6817024_6828016 · in -27.7 dBFS · gain +7.7 dB · eurospeech-01038
(relief, disappointment, fear·measured, normally alert, frequent disfluency)of (low mumble) services, (low mumble) who, as the hon. Gentleman has said, might have benefited disproportionately (low mumble) in the past with regard to the charges that they have effectively made (low mumble) to the public. The point that I was labouring is that we now have a real
full caption & clip details
A middle-aged masculine voice; delivery is normally alert, measured, slightly relaxed, fairly steady; timbre is neutral-toned, slightly dark, slightly rough, balanced body; somewhat unclear, frequent disfluency, fairly narrow pitch, normal breath; affect is neutral, neutral stance, slightly guarded; reads as relief, disappointment, fear; average recording, quiet background; genuineness 4.3/6; vocal-burst blend 0.4/10; 15.6s, EN.
uk_uk_4_26062013_6900624_6916224 · in -28.0 dBFS · gain +8.0 dB · eurospeech-01038
(concentration· measured, subdued, frequent disfluency)body of experience that is saving billions of pounds of taxpayers’ money in negotiating and renegotiating, often in flight, (low mumble) these contracts with suppliers to ensure that the taxpayer (low mumble) (low mumble) gets a better deal.
full caption & clip details
An adult masculine voice; delivery is subdued, measured, slightly relaxed, fairly steady; timbre is neutral-toned, slightly dark, fairly smooth, balanced body; somewhat unclear, frequent disfluency, moderate pitch range, normal breath; affect is neutral, neutral stance, slightly guarded; reads as concentration; average recording, quiet background; genuineness 3.7/6; vocal-burst blend 0.8/10; 15.6s, EN.
uk_uk_4_26062013_6916224_6931791 · in -28.7 dBFS · gain +8.7 dB · eurospeech-01038
(concentration, interest, fear· measured, subdued, frequent disfluency, monologue)What I am asking of hon. Members is patience. Let us see the NAO report and what signals it sends in terms of (low mumble) the deficiencies of the current system and the need for a bit more central control, (low mumble) and then the Cabinet Office will respond. We are now a great deal more interested in this subject
full caption & clip details
A middle-aged masculine voice; delivery is subdued, measured, slightly relaxed, fairly steady; timbre is neutral-toned, slightly dark, slightly rough, balanced body; somewhat unclear, frequent disfluency, fairly narrow pitch, normal breath; affect is neutral, neutral stance, slightly guarded; reads as concentration, interest, fear; style: monologue; average recording, quiet background; genuineness 3.1/6; vocal-burst blend 0.1/10; 19.0s, EN.
uk_uk_4_26062013_6931791_6950800 · in -29.5 dBFS · gain +9.5 dB · eurospeech-01038
This chain comes from the one-sided rule: only Anger had to get where it was going, by at least 0.50. The other emotion was left completely free.
The chain starts with Anger around average — 0.48, lower than 52 % of clips in this corpus — and ends with it at the very top of the corpus at 0.99, higher than 99 % of clips in this corpus. That is a total rise of 0.52.
Nothing was asked of the other axis, and in fact Interest drifts down from 0.98 to 0.66 (-0.32), which the rule did not require.
It takes 5 clips to get there. Clip to clip the moves are +0.00, then +0.07, then +0.25, then +0.20 — a plateau around step 1, where it barely moves.
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 · pt · eurospeech
k 5d_a -0.316d_b 0.516step_a 0.373step_b 0.248min_cos_consec —min_cos_anchor —dataset eurospeechlang ptspeaker portugal_15_1_149track portugal_15_1_149total 82.4slevel spread 6.2 dBmax seam 5.1 dB
Script — 5 chunks, 1 with a non-speech sound
Unchanged across all 5 clips: a young adult feminine voice · slightly cool, thin, moderately variable, wide pitch range, audible breath
(interest, concentration, disappointment · brisk, energised, neutral tension, dramatic)de promoção da saúde, e é essa a aposta que existe já noutros países. Neste debate, no entanto, o PAN gostaria de sinalizar um ponto que apenas consta da nossa iniciativa, que é a possibilidade de o Governo poder, mesmo que sob a forma de projeto-piloto, numa fase inicial, comparticipar os custos relacionados com o alojamento e o transporte
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, thin; clear, some disfluency, wide pitch range, audible breath; affect is positive, slightly dominant, slightly guarded; reads as interest, concentration, disappointment; style: dramatic, cartoonish; average recording, quiet background; genuineness 1.7/6; vocal-burst blend 3.2/10; 18.5s, PT.
portugal_15_1_149_12223136_12241648 · in -22.4 dBFS · gain +2.4 dB · eurospeech-02614
(shame·normal-paced, normally alert, neutral tension, dramatic)das pessoas em situação de vulnerabilidade, como sejam os idosos com complemento solidário para (ahem) idoso, ou as crianças beneficiárias de garantia para a infância.
full caption & clip details
An elderly 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, audible breath; affect is neutral, neutral stance, neutral openness; reads as shame; style: dramatic; average recording, quiet background; genuineness 3.4/6; vocal-burst blend 2.3/10; 10.5s, PT.
portugal_15_1_149_12241648_12252096 · in -21.7 dBFS · gain +1.7 dB · eurospeech-02614
(thankfulness gratitude, contentment, disgust·brisk, energised, slightly relaxed, dramatic)Esta comparticipação que propomos existe, por exemplo, em países como França ou Espanha, e acreditamos que trará justiça social a este regime de comparticipação. Sem este mecanismo, dificilmente uma pessoa idosa com complemento solidário terá dinheiro para se tratar,
full caption & clip details
An elderly feminine voice; delivery is energised, brisk, slightly relaxed, moderately variable; timbre is slightly cool, slightly bright, fairly smooth, thin; average clarity, almost no disfluency, wide pitch range, audible breath; affect is positive, slightly dominant, neutral openness; reads as thankfulness gratitude, contentment, disgust; style: dramatic, storytelling; average recording, some background noise; genuineness 1.9/6; vocal-burst blend 2.1/10; 15.1s, PT.
portugal_15_1_149_12252096_12267152 · in -21.8 dBFS · gain +1.8 dB · eurospeech-02614
(interest, concentration, thankfulness gratitude ·fast, energised, slightly relaxed, dramatic)tratar a sua osteoporose, ou uma criança asmática, no primeiro escalão do abono de família, poderá ir, por exemplo, até ao Gerês. Era importante discutir este e outros temas em sede de especialidade, de forma que, em 2024, possamos novamente ter em vigor, como até 2011, um regime de comparticipação de tratamentos termais, apostando, assim, na promoção da saúde.
full caption & clip details
A young adult feminine voice; delivery is energised, fast, slightly relaxed, moderately variable; timbre is slightly cool, neutral-bright, fairly smooth, thin; clear, almost no disfluency, wide pitch range, audible breath; affect is positive, slightly dominant, guarded; reads as interest, concentration, thankfulness gratitude; style: dramatic, formal; average recording, quiet background; genuineness 1.4/6; vocal-burst blend 3.3/10; 19.9s, PT.
portugal_15_1_149_12267152_12287046 · in -21.3 dBFS · gain +1.3 dB · eurospeech-02614
(anger, contempt, malevolence malice· fast, highly aroused, tense, cartoonish)Srs. Deputados do Grupo Parlamentar do Partido Socialista, há quase oito anos que suportam este Governo e têm de ter muita lata para vir aqui hoje acusar a direita de ter ido além da troica e de não valorizar os tratamentos termais, quanto mais o resto dos tratamentos.
full caption & clip details
A young adult masculine voice; delivery is highly aroused, fast, tense, moderately variable; timbre is slightly cool, neutral-bright, rough, thin; somewhat unclear, some disfluency, wide pitch range, audible breath; affect is negative, very dominant, guarded; reads as anger, contempt, malevolence malice; style: cartoonish, dramatic; below-average recording, quiet background; genuineness 2.6/6; vocal-burst blend 7.7/10; 17.9s, PT.
portugal_15_1_149_12313872_12331744 · in -16.2 dBFS · gain -3.8 dB · eurospeech-02614
This chain comes from the one-sided rule: only Shame had to get where it was going, by at least 0.20. The other emotion was left completely free.
The chain starts with Shame clearly present — 0.66, higher than 66 % of clips in this corpus — and ends with it at the very top of the corpus at 0.97, higher than 97 % of clips in this corpus. That is a total rise of 0.31.
Nothing was asked of the other axis, and in fact Pride drifts down from 0.94 to 0.02 (-0.92), which the rule did not require.
It takes 5 clips to get there. Clip to clip the moves are +0.23, then +0.04, then -0.04, then +0.08 — not a clean run: step 3 moves back the other way by 0.04 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 · 68 s · pt · eurospeech
k 5d_a -0.921d_b 0.308step_a 0.937step_b 0.230min_cos_consec —min_cos_anchor —dataset eurospeechlang ptspeaker portugal_15_1_128track portugal_15_1_128total 68.5slevel spread 3.0 dBmax seam 1.8 dB
Script — 5 chunks, 3 with a non-speech sound
Unchanged across all 5 clips: a young adult feminine voice · slightly cool, quiet background
(pride, disgust · brisk, energised, neutral tension, dramatic)para que venha, de facto, a ser promulgado e para que possa vir a ser devidamente (childlike giggle) aplicado. Será assim, em estrito cumprimento da Constituição, mas também de um dever maior, que a todas e a todos nós, Deputados desta Assembleia da República, nos cabe,
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 negative, slightly dominant, guarded; reads as pride, disgust; style: dramatic, casual; below-average recording, quiet background; genuineness 2.8/6; vocal-burst blend 4.7/10; 12.1s, PT.
portugal_15_1_128_1185920_1197984 · in -23.0 dBFS · gain +3.0 dB · eurospeech-02610
(thankfulness gratitude, awe·measured, subdued, relaxed, monologue)Para uma intervenção em nome do Grupo Parlamentar do PCP, tem a palavra a Sr.ª Deputada Alma Rivera.
full caption & clip details
An adolescent masculine voice; delivery is subdued, measured, relaxed, fairly steady; timbre is slightly cool, slightly dark, slightly rough, slightly thin; slurred, frequent disfluency, fairly narrow pitch, normal breath; affect is mildly negative, neutral stance, neutral openness; reads as thankfulness gratitude, awe; style: monologue, whispered; average recording, quiet background; genuineness 1.6/6; vocal-burst blend 0.0/10; 12.0s, PT.
portugal_15_1_128_1215438_1227392 · in -24.2 dBFS · gain +4.2 dB · eurospeech-02610
(pride, shame, contemplation·normal-paced, normally alert, neutral tension, casual)Rivera (PCP): — Sr. Presidente, Sr.as e Srs. Deputados: A oposição do PCP em relação à legalização da eutanásia é (low mumble) conhecida e ficou expressa em todos os debates que foram realizados nas duas últimas Legislaturas. Evidentemente, o PCP manterá o seu sentido (low mumble)
full caption & clip details
A young adult feminine voice; delivery is normally alert, normal-paced, neutral tension, fairly steady; timbre is slightly cool, neutral-bright, fairly smooth, thin; somewhat unclear, some disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as pride, shame, contemplation; style: casual; average recording, quiet background; genuineness 4.4/6; vocal-burst blend 3.0/10; 17.5s, PT.
portugal_15_1_128_1227392_1244848 · in -26.0 dBFS · gain +6.0 dB · eurospeech-02610
(disgust, affection, pride ·fast, normally alert, neutral tension, dramatic)de voto. Reafirmamos que a opção do PCP de votar contra a legalização da eutanásia não foi tomada de ânimo leve e resulta de uma reflexão profunda sobre um tema que, pela sua complexidade,
full caption & clip details
An elderly feminine voice; delivery is normally alert, 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 disgust, affection, pride; style: dramatic, storytelling; average recording, quiet background; genuineness 3.8/6; vocal-burst blend 4.7/10; 12.5s, PT.
portugal_15_1_128_1244848_1257344 · in -24.8 dBFS · gain +4.8 dB · eurospeech-02610
(shame, distress, disgust ·normal-paced, normally alert, neutral tension, casual)pelas inquietações que suscita e pelos valores que estão (low mumble) em causa, não pode ser tratado ou discutido a partir de posições de superioridade moral, (ahem) de arrogância intelectual ou de qualquer tipo de maniqueísmo.
full caption & clip details
An elderly somewhat feminine voice; delivery is normally alert, normal-paced, 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 shame, distress, disgust; style: casual; average recording, quiet background; genuineness 4.5/6; vocal-burst blend 2.9/10; 13.9s, PT.
portugal_15_1_128_1257344_1271248 · in -25.4 dBFS · gain +5.4 dB · eurospeech-02610
Pride ↑ (unconstrained axis: Fatigue Exhaustion)c-eurospeech-B1 · #15
This chain comes from the one-sided rule: only Pride had to get where it was going, by at least 0.25. The other emotion was left completely free.
The chain starts with Pride clearly present — 0.67, higher than 67 % of clips in this corpus — and ends with it at the very top of the corpus at 0.99, higher than 99 % of clips in this corpus. That is a total rise of 0.32.
Nothing was asked of the other axis, and in fact Fatigue Exhaustion barely moves at all, sitting near 0.97 throughout.
It takes 5 clips to get there. Clip to clip the moves are +0.22, then +0.09, then -0.03, then +0.04 — not a clean run: step 3 moves back the other way by 0.03 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 · 76 s · hr · eurospeech
k 5d_a -0.021d_b 0.322step_a 0.329step_b 0.221min_cos_consec —min_cos_anchor —dataset eurospeechlang hrspeaker croatia_20110202155005-312track croatia_20110202155005-312total 76.4slevel spread 3.8 dBmax seam 3.8 dB
Script — 5 chunks, 1 with a non-speech sound
Unchanged across all 5 clips: an elderly masculine voice · neutral-toned, quiet background, measured, somewhat unclear, normal breath
(fatigue exhaustion, intoxication altered states of consciousness, disgust · very low-energy, relaxed, fairly steady, casual)Kaskamo u odnosu na ugovorene iznose prema mjerilima koje smo dogovorili zajedno sa EU tu smo u jednom zaostatku, ali
full caption & clip details
An elderly 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 fatigue exhaustion, intoxication altered states of consciousness, disgust; style: casual, monologue; below-average recording, quiet background; genuineness 4.0/6; vocal-burst blend 0.1/10; 12.4s, HR.
croatia_20110202155005-3122_975152_987536 · in -21.1 dBFS · gain +1.1 dB · eurospeech-01324
(thankfulness gratitude, contentment, relief· very low-energy, relaxed, fairly steady, casual)s obzirom da je objava obavijesti od natječaja u skladu s rokom još plana nabave gotovo 100%-tna gotovo uz malo zakašnjenje, za očekivati je da će se i taj dio razriješiti za razliku od Operativnog programa Promet, gdje će se sasvim sigurno desiti summa summarum
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, balanced body; somewhat unclear, some disfluency, fairly narrow pitch, normal breath; affect is neutral, neutral stance, slightly guarded; reads as thankfulness gratitude, contentment, relief; style: casual, monologue; below-average recording, quiet background; genuineness 4.8/6; vocal-burst blend 6.9/10; 19.5s, HR.
croatia_20110202155005-3122_987536_1007072 · in -21.6 dBFS · gain +1.6 dB · eurospeech-01324
(triumph, shame, contempt·normally alert, neutral tension, fairly steady, casual)(low mumble) da nećemo moći iskoristiti sva moguća sredstva kao i u Zaštiti okoliša, a kolegica je malo prije spomenula IPARD, u IPARD-u gotovo sigurno po pravilu 1+3 će nam ove godine propasti sigurno između
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, some disfluency, fairly narrow pitch, normal breath; affect is neutral, slightly dominant, slightly guarded; reads as triumph, shame, contempt; style: casual, monologue; below-average recording, quiet background; genuineness 4.0/6; vocal-burst blend 6.3/10; 13.6s, HR.
croatia_20110202155005-3122_1007072_1020672 · in -19.7 dBFS · gain -0.3 dB · eurospeech-01324
(pride, bitterness, contempt · normally alert, neutral tension, moderately variable, casual)između 17 milijuna nekakva matematika, možda 15, možda 14 ali više od 10 milijuna je gotovo sigurno, izgubit ćemo, nećemo dobiti. A sve kaj nismo dobili to smo izgubili.
full caption & clip details
A middle-aged masculine voice; delivery is normally alert, measured, neutral tension, moderately variable; timbre is neutral-toned, neutral-bright, slightly rough, thin; somewhat unclear, some disfluency, moderate pitch range, normal breath; affect is neutral, slightly dominant, slightly guarded; reads as pride, bitterness, contempt; style: casual, monologue; average recording, quiet background; genuineness 5.1/6; vocal-burst blend 4.7/10; 12.5s, HR.
croatia_20110202155005-3122_1020672_1033215 · in -23.4 dBFS · gain +3.5 dB · eurospeech-01324
(pride, anger, fatigue exhaustion·subdued, relaxed, fairly steady, monologue)Prema tome, i kod ovog operativnog programa postoji opasnost jer u 2010. smo se uspjeli izvući, međutim postoji opasnost u 2011. godini s obzirom na pravilo 1+3
full caption & clip details
A middle-aged masculine voice; delivery is subdued, measured, relaxed, fairly steady; timbre is neutral-toned, slightly dark, rough, balanced body; somewhat unclear, frequent disfluency, fairly narrow pitch, normal breath; affect is mildly negative, slightly dominant, fairly guarded; reads as pride, anger, fatigue exhaustion; style: monologue, storytelling; below-average recording, quiet background; genuineness 2.8/6; vocal-burst blend 0.0/10; 17.8s, HR.
croatia_20110202155005-3122_1033215_1050976 · in -20.7 dBFS · gain +0.7 dB · eurospeech-01324
This chain comes from the one-sided rule: only Concentration had to get where it was going, by at least 0.20. The other emotion was left completely free.
The chain starts with Concentration around average — 0.54, higher than 54 % of clips in this corpus — and ends with it at the very top of the corpus at 0.95, higher than 95 % of clips in this corpus. That is a total rise of 0.41.
Nothing was asked of the other axis, and in fact Shame barely moves at all, sitting near 0.97 throughout.
It takes 5 clips to get there. Clip to clip the moves are -0.02, then +0.24, then +0.16, then +0.03 — not a clean run: step 1 moves back the other way by 0.02 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 · 79 s · hr · eurospeech
k 5d_a -0.035d_b 0.412step_a 0.330step_b 0.243min_cos_consec —min_cos_anchor —dataset eurospeechlang hrspeaker croatia_20070524172915-402track croatia_20070524172915-402total 79.1slevel spread 6.6 dBmax seam 6.6 dB
Script — 5 chunks, 3 with a non-speech sound
Unchanged across all 5 clips: an elderly feminine voice · neutral-toned, quiet background
(shame, bitterness, hope enthusiasm optimism · brisk, normally alert, neutral tension, storytelling)nadajmo se djelovanje Hrvatske akademije znanosti i umjetnosti, tog sukusa hrvatske pameti biti prepoznati i u medijima i u javnosti kako ne bi sve ostalo nažalost samo između korica, žutih korica ove vrlo dragocjene publikacije. Hvala lijepo.
full caption & clip details
An elderly feminine voice; delivery is normally alert, brisk, neutral tension, moderately variable; timbre is neutral-toned, neutral-bright, slightly rough, thin; average clarity, some disfluency, wide pitch range, light breath; affect is positive, slightly dominant, slightly guarded; reads as shame, bitterness, hope enthusiasm optimism; style: storytelling, monologue; average recording, quiet background; genuineness 3.7/6; vocal-burst blend 7.9/10; 19.8s, HR.
croatia_20070524172915-4027_2489584_2509335 · in -20.2 dBFS · gain +0.2 dB · eurospeech-01226
(fatigue exhaustion, confusion, contempt·measured, subdued, relaxed, monologue)Hvala lijepo. Na redu je zastupnik gospodin Petar Selem. Izvolite **Selem, Petar (HDZ)** Hvala gospodine potpredsjedniče.
full caption & clip details
A middle-aged masculine voice; delivery is subdued, measured, relaxed, fairly steady; timbre is neutral-toned, slightly dark, rough, thin; somewhat unclear, frequent disfluency, fairly narrow pitch, normal breath; affect is mildly negative, slightly dominant, fairly guarded; reads as fatigue exhaustion, confusion, contempt; style: monologue, storytelling; below-average recording, quiet background; genuineness 2.2/6; vocal-burst blend 0.0/10; 11.0s, HR.
croatia_20070524172915-4027_2509335_2520384 · in -26.8 dBFS · gain +6.8 dB · eurospeech-01226
(thankfulness gratitude, affection, pride· measured, normally alert, slightly relaxed, monologue)(low mumble) Osjećam potrebu da dopunim sa nekoliko riječi ono što sam kazao kao predsjednik Odbora za obrazovanje, znanost i kulturu a u svezi sa izvješćem o radu Hrvatske akademije znanosti i umjetnosti u protekloj godini.
full caption & clip details
An adult 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, fairly narrow pitch, light breath; affect is neutral, neutral stance, slightly guarded; reads as thankfulness gratitude, affection, pride; style: monologue; average recording, quiet background; genuineness 2.5/6; vocal-burst blend 2.2/10; 13.4s, HR.
croatia_20070524172915-4027_2520384_2533824 · in -26.6 dBFS · gain +6.6 dB · eurospeech-01226
(pride, bitterness, shame· measured, normally alert, neutral tension, monologue)Čini mi se da je već spomenuto u ovim raspravama, ali mislim da možda i nismo još dovoljno tu stvar (ahem) istaknuli da je Hrvatska akademija jasno jedna od temeljnih (ahem) ustanova hrvatske kulture, hrvatske znanosti, hrvatskog nacionalnog identiteta.
full caption & clip details
A middle-aged masculine voice; delivery is normally alert, measured, neutral tension, fairly steady; timbre is neutral-toned, neutral-bright, slightly rough, balanced body; somewhat unclear, some disfluency, fairly narrow pitch, light breath; affect is neutral, neutral stance, slightly guarded; reads as pride, bitterness, shame; style: monologue, narration; average recording, quiet background; genuineness 2.2/6; vocal-burst blend 3.4/10; 16.8s, HR.
croatia_20070524172915-4027_2533824_2550624 · in -26.5 dBFS · gain +6.5 dB · eurospeech-01226
(concentration, malevolence malice, shame ·brisk, normally alert, neutral tension, cartoonish)Hrvatska akademija znanosti i umjetnosti i Sveučilište, Matica Hrvatska to su ti instituti po kojima Hrvatska postoji kao jedna kulturna nacija i kao nacija znanosti i tim više čude i mogu reći zaista ponekad i zaprepaste (low mumble) destruktivne
full caption & clip details
A middle-aged masculine voice; delivery is normally alert, brisk, neutral tension, moderately variable; timbre is neutral-toned, neutral-bright, slightly rough, balanced body; somewhat unclear, some disfluency, wide pitch range, light breath; affect is neutral, slightly dominant, slightly guarded; reads as concentration, malevolence malice, shame; style: cartoonish, authoritative; average recording, quiet background; genuineness 2.7/6; vocal-burst blend 6.2/10; 17.5s, HR.
croatia_20070524172915-4027_2550624_2568112 · in -23.8 dBFS · gain +3.8 dB · eurospeech-01226
This chain comes from the one-sided rule: only Concentration had to get where it was going, by at least 0.20. The other emotion was left completely free.
The chain starts with Concentration clearly present — 0.75, higher than 75 % of clips in this corpus — and ends with it at the very top of the corpus at 0.96, higher than 96 % of clips in this corpus. That is a total rise of 0.22.
Nothing was asked of the other axis, and in fact Pride barely moves at all, sitting near 0.98 throughout.
It takes 5 clips to get there. Clip to clip the moves are +0.20, then +0.03, then +0.01, then -0.03 — not a clean run: step 4 moves back the other way by 0.03 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 -0.021d_b 0.218step_a 0.212step_b 0.197min_cos_consec —min_cos_anchor —dataset eurospeechlang daspeaker denmark_20101M034_2010-12-track denmark_20101M034_2010-12-total 72.8slevel spread 1.6 dBmax seam 1.0 dB
Script — 5 chunks, 0 with a non-speech sound
Unchanged across all 5 clips: a middle-aged masculine voice · neutral-toned, neutral-bright, slightly rough, balanced body, average recording, quiet background, measured, normally alert
(pride, triumph · fairly steady, frequent disfluency, somewhat unclear, monologue)Det var slut, og det var samlet 80 ord. For Venstre er udgangspunktet, at det er statens opgave at stille den nødvendige viden til rådighed for kommunerne,
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, frequent disfluency, fairly narrow pitch, audible breath; affect is neutral, slightly dominant, slightly guarded; reads as pride, triumph; style: monologue, authoritative; average recording, quiet background; genuineness 2.1/6; vocal-burst blend 0.1/10; 11.4s, DA.
denmark_20101M034_2010-12-14_1200_11733472_11744864 · in -28.3 dBFS · gain +8.3 dB · eurospeech-00112
(bitterness, sourness, disgust· fairly steady, some disfluency, average clarity, authoritative)mens det er kommunerne selv, der skal træffe beslutning om, hvad de vil gøre for at klimatilpasse. Kommunerne kender selv deres egne forhold. Man kan ikke sidde her i Folketinget eller i Klima- og Energiministeriet og kende alle kloakforhold i Danmark,
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; average clarity, some disfluency, wide pitch range, audible breath; affect is neutral, slightly dominant, slightly guarded; reads as bitterness, sourness, disgust; style: authoritative, monologue; average recording, quiet background; genuineness 1.8/6; vocal-burst blend 1.0/10; 17.2s, DA.
denmark_20101M034_2010-12-14_1200_11744864_11762096 · in -27.3 dBFS · gain +7.3 dB · eurospeech-00112
(concentration, anger, malevolence malice· fairly steady, frequent disfluency, average clarity, authoritative)og der er forskel fra kommune til kommune på, hvad der er behov for. Der er forskel på, hvad der skal gøres i Løgstør, og hvad der skal gøres på Langeland, og i Venstre har vi respekt for det kommunale selvstyre.
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; average clarity, frequent disfluency, wide pitch range, normal breath; affect is neutral, slightly dominant, fairly guarded; reads as concentration, anger, malevolence malice; style: authoritative, monologue; average recording, quiet background; genuineness 1.6/6; vocal-burst blend 0.3/10; 14.2s, DA.
denmark_20101M034_2010-12-14_1200_11762096_11776288 · in -27.8 dBFS · gain +7.8 dB · eurospeech-00112
(concentration ·moderately variable, frequent disfluency, average clarity, cartoonish)Man kan ikke skabe ensartede løsninger for 98 forskellige kommuner. Endelig handler det jo også om økonomi. Mange vil gerne sende regningen videre til statskassen,
full caption & clip details
A middle-aged masculine voice; delivery is normally alert, measured, slightly relaxed, moderately variable; timbre is neutral-toned, neutral-bright, slightly rough, balanced body; average clarity, frequent disfluency, wide pitch range, audible breath; affect is neutral, slightly dominant, fairly guarded; reads as concentration; style: cartoonish, didactic; average recording, quiet background; genuineness 2.1/6; vocal-burst blend 0.2/10; 13.2s, DA.
denmark_20101M034_2010-12-14_1200_11776288_11789488 · in -26.8 dBFS · gain +6.8 dB · eurospeech-00112
(concentration, pride, bitterness·fairly steady, some disfluency, average clarity, monologue)men hvis f.eks. statskassen påtog sig opgaven og opkrævede pengene i skatter, ville regningen ende med at blive betalt af skatteborgerne i de kommuner, hvor man har været forudseende og for længst investeret i klimatilpasning, og det vil jo ikke være rimeligt.
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; average clarity, some disfluency, wide pitch range, normal breath; affect is neutral, slightly dominant, slightly guarded; reads as concentration, pride, bitterness; style: monologue, cartoonish; average recording, quiet background; genuineness 1.6/6; vocal-burst blend 0.2/10; 16.2s, DA.
denmark_20101M034_2010-12-14_1200_11789488_11805712 · in -26.7 dBFS · gain +6.7 dB · eurospeech-00112
This chain comes from the one-sided rule: only Thankfulness Gratitude had to get where it was going, by at least 0.25. The other emotion was left completely free.
The chain starts with Thankfulness Gratitude clearly present — 0.69, higher than 69 % of clips in this corpus — and ends with it at the very top of the corpus at 0.98, higher than 98 % of clips in this corpus. That is a total rise of 0.29.
Nothing was asked of the other axis, and in fact Shame barely moves at all, sitting near 0.99 throughout.
It takes 5 clips to get there. Clip to clip the moves are +0.15, then +0.12, then +0.01, then +0.02 — 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 · 78 s · it · eurospeech
k 5d_a -0.010d_b 0.294step_a 0.102step_b 0.147min_cos_consec —min_cos_anchor —dataset eurospeechlang itspeaker italy_19_152track italy_19_152total 78.0slevel spread 10.1 dBmax seam 8.1 dB
Script — 5 chunks, 0 with a non-speech sound
Unchanged across all 5 clips: a young adult masculine voice
(shame, disappointment, contemplation · fast, highly aroused, neutral tension, ranting)che sia all'altezza dei tempi che sono cambiati. Il modo migliore per ricordare questo trentennale, oltre che ringraziare le donne e gli uomini che lavorarono a questo significativo risultato, è aprire una stagione
full caption & clip details
A young adult masculine voice; delivery is highly aroused, fast, neutral tension, moderately variable; timbre is slightly cool, neutral-bright, fairly smooth, thin; average clarity, some disfluency, very wide pitch range, normal breath; affect is elated, very dominant, guarded; reads as shame, disappointment, contemplation; style: ranting, cartoonish; average recording, quiet background; genuineness 3.0/6; vocal-burst blend 8.5/10; 16.0s, IT.
italy_19_152_21327296_21343248 · in -25.9 dBFS · gain +5.9 dB · eurospeech-01800
(distress, contentment, anger· fast, highly aroused, slightly tense, cartoonish)riformatrice che vada nella direzione di assicurare pari dignità e tutela a un territorio che si sta spopolando sempre di più, che sta vedendo un invecchiamento della popolazione
full caption & clip details
A young adult masculine voice; delivery is highly aroused, fast, slightly tense, moderately variable; timbre is slightly cool, slightly bright, rough, thin; clear, almost no disfluency, very wide pitch range, audible breath; affect is elated, slightly dominant, guarded; reads as distress, contentment, anger; style: cartoonish, ranting; poor recording, some background noise; genuineness 1.5/6; vocal-burst blend 6.6/10; 13.0s, IT.
italy_19_152_21343248_21356240 · in -27.0 dBFS · gain +7.0 dB · eurospeech-01800
(contentment, triumph, pride·measured, normally alert, neutral tension, storytelling)personalmente nei primi anni della mia attività professionale di avvocato. Ne ho un ricordo stupendo, anche per la sua giovialità, il suo carattere e il suo modo gioioso di affrontare la vita. *(Applausi)*. Prego,
full caption & clip details
A middle-aged masculine voice; delivery is normally alert, measured, neutral tension, fairly steady; timbre is warm, slightly dark, rough, thin; somewhat unclear, some disfluency, wide pitch range, audible breath; affect is negative, slightly dominant, fairly guarded; reads as contentment, triumph, pride; style: storytelling, authoritative; below-average recording, quiet background; genuineness 2.5/6; vocal-burst blend 8.7/10; 17.8s, IT.
italy_19_152_21389136_21406912 · in -35.0 dBFS · gain +15.0 dB · eurospeech-01800
(shame, disappointment, thankfulness gratitude·normal-paced, normally alert, slightly relaxed, authoritative)«sarà per quella faccia mite, da primo della classe che si lascia copiare i compiti, sarà per il rigore che dimostra nelle sue inchieste, Alessandrini è il prototipo del magistrato di cui tutti si possono fidare perché non combina sciocchezze».
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; average clarity, almost no disfluency, moderate pitch range, light breath; affect is neutral, slightly dominant, slightly guarded; reads as shame, disappointment, thankfulness gratitude; style: authoritative, monologue; average recording, quiet background; genuineness 0.0/6; vocal-burst blend 3.5/10; 15.3s, IT.
italy_19_152_21406912_21422256 · in -35.8 dBFS · gain +15.8 dB · eurospeech-01800
(thankfulness gratitude, shame, bitterness·fast, normally alert, neutral tension, authoritative)Signor Presidente, senatrici, senatori, scriveva così sulle colonne del «Corriere della Sera» Walter Tobagi il 29 gennaio 1979 all'indomani dell'agguato compiuto a Milano da un gruppo di fuoco di Prima linea a danno del giudice Emilio Alessandrini.
full caption & clip details
A young adult masculine voice; delivery is normally alert, fast, neutral tension, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; somewhat unclear, almost no disfluency, moderate pitch range, light breath; affect is neutral, slightly dominant, slightly guarded; reads as thankfulness gratitude, shame, bitterness; style: authoritative, monologue; average recording, quiet background; genuineness 1.3/6; vocal-burst blend 7.1/10; 15.4s, IT.
italy_19_152_21422256_21437616 · in -36.0 dBFS · gain +16.0 dB · eurospeech-01800
This chain comes from the one-sided rule: only Contempt had to get where it was going, by at least 0.25. The other emotion was left completely free.
The chain starts with Contempt clearly present — 0.61, higher than 61 % of clips in this corpus — and ends with it at the very top of the corpus at 0.97, higher than 97 % of clips in this corpus. That is a total rise of 0.36.
Nothing was asked of the other axis, and in fact Relief drifts down from 0.88 to 0.71 (-0.17), which the rule did not require.
It takes 3 clips to get there. Clip to clip the moves are +0.20, then +0.16 — 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 · 39 s · hr · eurospeech
k 3d_a -0.174d_b 0.358step_a 0.096step_b 0.195min_cos_consec —min_cos_anchor —dataset eurospeechlang hrspeaker croatia_20221208092421-209track croatia_20221208092421-209total 38.6slevel spread 7.7 dBmax seam 7.7 dB
Script — 3 chunks, 0 with a non-speech sound
Unchanged across all 3 clips: a young adult masculine voice · neutral-toned, neutral-bright, balanced body, average recording, quiet background, normally alert, some disfluency, moderate pitch range
(brisk, slightly relaxed, fairly steady, authoritative)Gospodine ministre, radnici kojima je Agregator poslodavac objektivno mogu se naći u nepovoljnijem položaju u odnosu na druge platformske radnike.
full caption & clip details
A young adult masculine voice; delivery is normally alert, brisk, 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; no dominant emotion; style: authoritative, monologue; average recording, quiet background; genuineness 2.0/6; vocal-burst blend 1.1/10; 10.5s, HR.
croatia_20221208092421-20964_7425648_7436113 · in -16.9 dBFS · gain -3.1 dB · eurospeech-01567
(thankfulness gratitude, contemplation·measured, neutral tension, moderately variable, conversational)Kako? Pa vrlo jednostavno, oni mogu osmisliti svojevrsnu naknadu za posredovanje koja se ne mora tako zvati. Kako ćemo ih zaštititi ovim zakonskim prijedlogom?
full caption & clip details
An adult masculine voice; delivery is normally alert, measured, neutral tension, moderately variable; timbre is neutral-toned, neutral-bright, slightly rough, balanced body; average clarity, some disfluency, moderate pitch range, light breath; affect is mildly positive, neutral stance, slightly guarded; reads as thankfulness gratitude, contemplation; style: conversational, monologue; average recording, quiet background; genuineness 3.5/6; vocal-burst blend 2.6/10; 13.2s, HR.
croatia_20221208092421-20964_7436113_7449327 · in -20.9 dBFS · gain +0.9 dB · eurospeech-01567
(contempt, malevolence malice, disgust·normal-paced, slightly relaxed, fairly steady, monologue)Marin (HDZ)** Uvažena zastupnice Jeckov, dakle Agregator kao i svaki drugi poslodavac je poslodavac i odgovara prema svom radniku sukladno dakle svim pozitivnim zakonskim propisima, pa tako i Zakon o radu.
full caption & clip details
An adult masculine voice; delivery is normally alert, normal-paced, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, slightly rough, balanced body; somewhat unclear, some disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as contempt, malevolence malice, disgust; style: monologue, casual; average recording, quiet background; genuineness 4.0/6; vocal-burst blend 2.3/10; 14.6s, HR.
croatia_20221208092421-20964_7449327_7463904 · in -13.3 dBFS · gain -6.7 dB · eurospeech-01567
Pride ↑ (unconstrained axis: Contempt)c-eurospeech-B1 · #20
This chain comes from the one-sided rule: only Pride had to get where it was going, by at least 0.20. The other emotion was left completely free.
The chain starts with Pride strongly present — 0.75, higher than 75 % of clips in this corpus — and ends with it at the very top of the corpus at 0.95, higher than 95 % of clips in this corpus. That is a total rise of 0.20.
Nothing was asked of the other axis, and in fact Contempt drifts down from 0.94 to 0.14 (-0.81), which the rule did not require.
It takes 2 clips to get there. Clip to clip the moves are +0.20 — 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 -0.807d_b 0.201step_a 0.807step_b 0.201min_cos_consec —min_cos_anchor —dataset eurospeechlang bgspeaker bulgaria_bulgaria_1_090920track bulgaria_bulgaria_1_090920total 27.2slevel spread 3.3 dBmax seam 3.3 dB
Script — 2 chunks, 0 with a non-speech sound
Unchanged across all 2 clips: a young adult masculine voice · neutral-toned, neutral-bright, balanced body, average recording, quiet background, normally alert, slightly relaxed, fairly steady
(contempt, concentration, malevolence malice · normal-paced, average clarity, moderate pitch range, authoritative)Напоследък често се коментира – и в медиите, и публично, въпросът за мерките за неотклонение. Те се превърнаха в някаква лакмусова хартия, по която се съди за бъдещия успех или неуспех на едно дело.
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; average clarity, some disfluency, moderate pitch range, light breath; affect is neutral, slightly dominant, slightly guarded; reads as contempt, concentration, malevolence malice; style: authoritative, monologue; average recording, quiet background; genuineness 2.1/6; vocal-burst blend 0.6/10; 12.4s, BG.
bulgaria_bulgaria_1_09092010_3594368_3606816 · in -17.8 dBFS · gain -2.2 dB · eurospeech-00091
(pride·measured, somewhat unclear, fairly narrow pitch, monologue)Длъжен съм да ви кажа, че като цяло само 3% от исканията ни за тежки мерки за неотклонение, говоря за задържане под стража и за домашен арест, са отхвърлени от съдилищата. Три
full caption & clip details
An adult 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, fairly narrow pitch, light breath; affect is neutral, neutral stance, slightly guarded; reads as pride; style: monologue, didactic; average recording, quiet background; genuineness 3.1/6; vocal-burst blend 0.0/10; 14.6s, BG.
bulgaria_bulgaria_1_09092010_3606816_3621456 · in -21.1 dBFS · gain +1.1 dB · eurospeech-00091