Sign in

Non-parallel voice conversion using joint optimization of alignment by temporal context and spectral distortion.

Hadas BenistyDavid MalahKoby Crammer
Published in: ICASSP (2014)
Keyphrases
  • joint optimization
  • temporal context
  • spatial context
  • temporal information
  • audio visual
  • sparse representation
  • spatio temporal
  • three dimensional
  • d objects
  • face recognition
  • multiscale
  • image coding