Visual speech feature extraction for improved speech recognition.
Xiaozheng ZhangRussell M. MersereauMark A. ClementsCharles C. BrounPublished in: ICASSP (2002)
Keyphrases
- speech recognition
- cepstral coefficients
- speaker identification
- visual speech recognition
- visual speech
- feature extraction
- speech signal
- hidden markov models
- audio visual speech recognition
- noisy environments
- language model
- automatic speech recognition
- pattern recognition
- speaker diarization
- linear prediction
- mel frequency cepstral coefficients
- speech recognition systems
- neural network
- principal component analysis
- low level
- multimedia
- image processing