Audio-visual modeling for bimodal speech recognition.
Mustafa Nazmi KaynakQi ZhiAdrian David CheokKuntal SenguptaChi Chung KoPublished in: SMC (2001)
Keyphrases
- speech recognition
- audio visual
- audio visual speech recognition
- multi stream
- multi modal
- hidden markov models
- noisy environments
- visual information
- speech synthesis
- language model
- speaker verification
- speech recognizer
- pattern recognition
- speech recognition systems
- speech signal
- audio features
- visual data
- automatic speech recognition
- emotion recognition
- high level
- digit recognition
- neural network
- non stationary
- speaker identification
- image features
- image sequences
- multimedia
- image processing
- search engine