Use of vector-valued dynamic weighting coefficients for speech recognition: maximum likelihood approach.
Rathinavelu ChengalvarayanPublished in: EUROSPEECH (1997)
Keyphrases
- speech recognition
- vector valued
- maximum likelihood
- weighting coefficients
- hidden markov models
- speaker adaptation
- speech synthesis
- automatic speech recognition
- language model
- speech signal
- speaker identification
- pattern recognition
- scale space
- speech recognition systems
- speech recognizer
- reproducing kernel hilbert space
- support vector
- loss function
- expectation maximization
- k means