A hybrid visual feature extraction method for audio-visual speech recognition.

Guanyong Wu Jie Zhu Haihua Xu

Published in: ICIP (2009)

Keyphrases

audio visual speech recognition
visual information
audio visual
multi stream
visual speech
speech recognition
visual data
high level
video sequences
hidden markov models
low level
data points
image data
e learning
multimedia data
human visual system
noisy environments