Login / Signup

Audio-Visual Speech Separation Using Cross-Modal Correspondence Loss.

Naoki MakishimaMana IhoriAkihiko TakashimaTomohiro TanakaShota OrihashiRyo Masumura
Published in: ICASSP (2021)
Keyphrases
  • audio visual
  • cross modal
  • multi modal
  • visual data
  • sound source
  • visual information
  • multi stream
  • audio features
  • data sets
  • visual similarity
  • query processing
  • image annotation
  • visual features