Login / Signup

Continuous visual speech recognition for multimodal fusion.

Eric BenhaimHichem SahbiGuillaume Vitte
Published in: ICASSP (2014)
Keyphrases
  • visual speech recognition
  • multimodal fusion
  • high robustness
  • audio visual
  • lip reading
  • hidden markov models
  • relevance feedback
  • machine learning
  • speech recognition
  • head tracking
  • three dimensional
  • dynamic textures