Concatenated Frame Image Based CNN for Visual Speech Recognition.

Takeshi Saitoh Ziheng Zhou Guoying Zhao Matti Pietikäinen

Published in: ACCV Workshops (2) (2016)

Keyphrases

visual speech recognition
lip reading
hidden markov models
speech recognition
feature vectors
video frames
pattern recognition
frame rate
computer vision
visual speech
probabilistic model
non stationary
dynamic textures