Phoneme recognition in connected speech using both static and dynamic properties of spectrum described by vector quantization.
Kazunori ManoShunichi IshigeKatsuhiko ShiraiPublished in: ICASSP (1986)
Keyphrases
- vector quantization
- phoneme recognition
- hidden markov models
- speaker recognition
- speaker dependent
- image compression
- vector quantizer
- automatic speech recognition
- distortion measure
- speech recognition
- feature selection
- codebook design
- visual features
- image processing
- computational complexity
- speaker identification
- pattern recognition
- audio signal
- video sequences
- multiscale