Phoneme-based vector quantization in a discrete HMM speech recognizer.
Yaxin ZhangRoberto TogneriMichael D. AlderPublished in: IEEE Trans. Speech Audio Process. (1997)
Keyphrases
- vector quantization
- speech recognition
- speech recognizer
- hidden markov models
- speaker adaptation
- image compression
- automatic speech recognition
- vector quantizer
- speaker dependent
- language model
- speaker independent
- speaker recognition
- speech signal
- distortion measure
- speaker identification
- noisy environments
- reduced complexity
- speech recognition systems
- codebook design
- pattern recognition
- spoken language
- successive approximation
- probabilistic model
- neural network