On the use of matrix derivatives in integrated design of dynamic feature parameters for speech recognition.
Rathinavelu ChengalvarayanPublished in: ICASSP (2001)
Keyphrases
- speech recognition
- hidden markov models
- speech processing
- language model
- automatic speech recognition
- speech recognizer
- neural network
- speech recognition technology
- speech signal
- noisy environments
- keyword spotting
- pattern recognition
- speaker dependent
- speech understanding
- speaker identification
- handwriting recognition
- speech recognition systems
- speaker independent
- expectation maximization
- maximum likelihood