Predictor codebook for speaker-independent speech recognition.
Takeshi KawabataPublished in: Systems and Computers in Japan (1994)
Keyphrases
- speech recognition
- speaker independent
- vector quantization
- speaker dependent
- hidden markov models
- speech recognizer
- language model
- speaker identification
- speech synthesis
- speech signal
- acoustic models
- automatic speech recognition
- speech recognition systems
- pattern recognition
- neural network
- feature vectors
- noisy environments
- multi modal
- image compression
- spoken language
- image classification
- speaker recognition
- support vector machine
- vocal tract
- feature selection
- speaker adaptation
- computer vision