A hidden Markov model based visual speech synthesizer.

Jay J. Williams Aggelos K. Katsaggelos Mark A. Randolph

Published in: ICASSP (2000)

Keyphrases

visual speech
text to speech
visual speech recognition
hidden markov models
person authentication
lip reading
noisy environments
speaker identification
video signals
word processing
speech signal
speech recognition
keywords
audio signal
audio signals
spatial domain
multiresolution
pattern recognition