An audio-visual approach to simultaneous-speaker speech recognition.

Eric K. Patterson John N. Gowdy

Published in: ICASSP (5) (2003)

Keyphrases

audio visual
speech recognition
audio visual speech recognition
multi modal
multi stream
visual information
speaker verification
hidden markov models

automatic speech recognition
speech synthesis
visual data
multimedia
speech signal
language model
speaker identification
emotion recognition

speech recognizer
noisy environments
pattern recognition
speaker independent
speaker dependent
speaker diarization
digit recognition
speech recognition systems

audio features
speaker recognition
neural network
non stationary
image data
high level
speaker adaptation
image processing