Data-driven synthesis of expressive visual speech using an MPEG-4 talking head.

Jonas Beskow Mikael Nordenberg

Published in: INTERSPEECH (2005)

Keyphrases

data driven
facial animation
visual speech
visual speech recognition
video signals
facial expressions
hidden markov models
video sequences
human faces
head motion
speaker identification
multimedia
compressed domain
noisy environments
speech recognition
low level
acoustic features
multiresolution