Sign in

Accurate automatic visible speech synthesis of arbitrary 3D models based on concatenation of diviseme motion capture data.

Jiyong MaRonald A. ColeBryan L. PellomWayne H. WardBarbara Wise
Published in: Comput. Animat. Virtual Worlds (2004)
Keyphrases
  • speech synthesis
  • probabilistic model
  • motion capture data
  • speech recognition
  • computer vision
  • prior knowledge
  • d objects