Using multiple vector quantization and semicontinuous hidden Markov models for speech recognition.
Antonio M. PeinadoJosé C. SeguraAntonio J. RubioM. Carmen BenítezPublished in: ICASSP (1) (1994)
Keyphrases
- speech recognition
- hidden markov models
- vector quantization
- image compression
- speaker recognition
- vector quantizer
- automatic speech recognition
- speech processing
- speech signal
- speaker identification
- keyword spotting
- speech synthesis
- noisy environments
- speech recognizer
- handwriting recognition
- discriminative training
- speech recognition systems
- pattern recognition
- language model
- speaker independent
- visual speech recognition
- noisy speech