A lip geometry approach for feature-fusion based audio-visual speech recognition.

M. Z. Ibrahim D. J. Mulvaney

Published in: ISCCSP (2014)

Keyphrases

audio visual speech recognition
feature fusion
multi stream
feature extraction
audio visual
multiple features
three dimensional
multi sensor
data reduction
fusion algorithm
speech recognition
subspace learning
noisy environments
hidden markov models
visual speech
fusion method
multi modal