Phoneme-to-viseme Mapping for Visual Speech Recognition.

Luca Cappelletta Naomi Harte

Published in: ICPRAM (2) (2012)

Keyphrases

visual speech
visual speech recognition
hidden markov models
noisy environments
speaker identification
speech signal
video signals
acoustic features
text to speech
speech recognition
audio signals
multiresolution
image quality
noise reduction
speaker verification