Login / Signup

Looking to listen at the cocktail party: a speaker-independent audio-visual model for speech separation.

Ariel EphratInbar MosseriOran LangTali DekelKevin WilsonAvinatan HassidimWilliam T. FreemanMichael Rubinstein
Published in: ACM Trans. Graph. (2018)
Keyphrases
  • audio visual
  • probabilistic model
  • information retrieval
  • speech recognition
  • visual data
  • e learning
  • image processing
  • multimedia
  • high level
  • feature space
  • multi modal
  • em algorithm
  • mixture model
  • visual information