Login / Signup

GAMVA: A Japanese Audio-Visual Multi-Angle Speech Corpus.

Shinnosuke IsobeRyuichi HiroseTakumi NishiwakiTomohiro HattoriSatoshi TamuraYuuto GotohMasaki Nose
Published in: O-COCOSDA (2021)
Keyphrases
  • audio visual
  • speech corpus
  • multi modal
  • multimedia
  • visual information
  • visual data
  • audio visual speech recognition
  • multi stream
  • neural network
  • automatic speech recognition
  • spatio temporal