Login / Signup

SynthVSR: Scaling Up Visual Speech RecognitionWith Synthetic Supervision.

Xubo LiuEgor LakomkinKonstantinos VougioukasPingchuan MaHonglie ChenRuiming XieMorrie DoulatyNiko MoritzJáchym KolárStavros PetridisMaja PanticChristian Fuegen
Published in: CVPR (2023)
Keyphrases
  • visual speech
  • visual speech recognition
  • person authentication
  • hidden markov models
  • multimedia
  • lip reading
  • image retrieval
  • probabilistic model
  • motion estimation
  • acoustic features