A two-channel training algorithm for hidden Markov model to identify visual speech elements.
Say Wei FooYong LianLiang DongPublished in: ISCAS (2) (2003)
Keyphrases
- hidden markov models
- training algorithm
- visual speech
- visual speech recognition
- back propagation
- neural network
- training process
- speech recognition
- support vector machine
- learning algorithm
- learning rate
- automatic speech recognition
- computer vision
- signal to noise ratio
- acoustic features
- audio signals
- artificial neural networks
- genetic algorithm