Sign in

Audio-Visual Speech Recognition with a Hybrid CTC/Attention Architecture.

Stavros PetridisThemos StafylakisPingchuan MaGeorgios TzimiropoulosMaja Pantic
Published in: SLT (2018)
Keyphrases
  • audio visual speech recognition
  • multi stream
  • audio visual
  • edge detection
  • high level
  • context aware
  • visual attention