quiz bu lëkkale ak tegtal · Dëgër Niveau

VALL-E ak Codec ci wàllu làkk

Xoolaat VALL-E's codec-token language-model approach, token bi mu defar, ak anam yi ci ginaaw resultaa yi mu joxe ci kàddu yu néew.

Yooni njiit yu jëm ciVall E ak xeetu làkku codec
Laaj 1 de 8

Lan mooy xalaat bu am solo bi wuutale VALL-E ak sistemu bind-ci-kaddu yu njëkk ya?

Xoolaatal laaj bu nekk8 laaj

Sooy def quiz bi, tontu yi ak leeral yi dañuy feeñ.

  1. Lan mooy xalaat bu am solo bi wuutale VALL-E ak sistemu bind-ci-kaddu yu njëkk ya?
    • Dafay wax luy waaja am ci codec neuronal ni liggéeyu modeling làkk ci barabu wax luy waaja am ci spectrogram
    • Dafay jëfandikoo siñaal buñ defaree loxo kese
    • Dafay laaj ay waxtu audio ci kàddukat biñ bëgga wax
    • Dafay defar mbind ci wax
  2. Ñaata audio la VALL-E soxla ngir klone baat buy wax bu bees?
    • Lu tollu ci benn waxtu
    • Lu tollu ci ñetti segond
    • Amul benn royuwaay audio
    • Lu tollu ci fan weeri simili
  3. Ban codec neuronal la VALL-E di jëfandikoo ngir defar ay token audio?
    • MP3
    • Opus
    • Kodek
    • WAV
  4. Lan moo waral VALL-E di jëfandikoo etape buy dellu ginaaw ak bu dul dellu ginaaw?
    • Tekki kàddu yi ci làkk yu bari
    • ngir tàqale music ak wax
    • Ngir kompresse dugal mbind
    • Ndax jeton codec yi dañuy layered, kon dafay wax luy waaja am ci jeton yu dëgër yi ci toppalante ak jeton yu baax yi ci paralel
  5. Lu tollu ci ñaata done ci kàddu lañu tàggatee VALL-E, loolu mooy tax ñu mëna def klonaas bu am doole?
    • Lu tollu ci 60000 waxtu
    • Lu tollu ci 100 waxtu
    • Lu tollu ci 1000 waxtu
    • Lu tollu ci 10 waxtu
  6. Lu weesu timbre, lan leneen la VALL-E mëna denc ci clip bu gàtt bi?
    • Waxkat bi wax na kàddu yu dëggu ba fàww
    • Environmaa akustik bi ci enregistremaa bi
    • Wideo bi ànd ak moom
    • Format fichier bi njëkk
  7. What does VALL-E condition on to imitate a target speaker in its demonstration setup?
    • A photograph and a written biography only
    • A long labeled transcript from every target-speaker recording
    • A short audio prompt from that speaker plus the text to speak
    • A speaker ID with no audio example
  8. What text representation does the VALL-E paper use as input to its text-to-code model?
    • A raw waveform of the target utterance
    • A speaker’s face embedding
    • A list of MIDI notes
    • A phoneme sequence