Improved speech modelling and recognition using a new training algorithm based on outlier-emphasis for non-stationary state HMM.
Rathinavelu ChengalvarayanPublished in: Speech Commun. (1998)
Keyphrases
- non stationary
- training algorithm
- speech signal
- neural network
- speech recognition
- back propagation
- hidden markov models
- training process
- data sets
- learning rate
- empirical mode decomposition
- support vector machine
- learning algorithm
- automatic speech recognition
- adaptive algorithms
- multi stream
- rbf neural network
- state space
- decision trees
- decision making
- data mining