Login / Signup

SCANet: A Self- and Cross-Attention Network for Audio-Visual Speech Separation.

Kai LiRunxuan YangXiaolin Hu
Published in: CoRR (2023)
Keyphrases
  • visual speech
  • audio visual speech recognition
  • multimedia
  • wireless sensor networks
  • visual speech recognition
  • multiresolution
  • hidden markov models
  • visual attention