Speaker independent audio-visual database for bimodal ASR.

Gerasimos Potamianos Eric Cosatto Hans Peter Graf David B. Roe

Published in: AVSP (1997)

Keyphrases

audio visual
digit recognition
speech recognition
multi modal
speaker independent
visual information
multi stream
emotion recognition
noisy environments
multimedia
image retrieval
hidden markov models
text mining
pattern recognition
video sequences
visual data
high level
speaker verification
neural network