Login / Signup

Probing phoneme, language and speaker information in unsupervised speech representations.

Maureen de SeysselMarvin LavechinYossi AdiEmmanuel DupouxGuillaume Wisniewski
Published in: CoRR (2022)
Keyphrases
  • speech recognition
  • context dependent
  • information sharing
  • domain knowledge
  • audio visual
  • semi supervised
  • higher level
  • multimedia
  • feature extraction
  • visual information
  • language acquisition