Login / Signup
Viseme-dependent weight optimization for CHMM-based audio-visual speech recognition.
Alexey Karpov
Andrey Ronzhin
Konstantin Markov
Milos Zelezný
Published in:
INTERSPEECH (2010)
Keyphrases
</>
audio visual speech recognition
visual speech
hidden markov models
multi stream
audio visual
multimedia
motion estimation
speaker identification