Speech recognition using dynamic transformation of phoneme templates depending on acoustic/phonetic environments.
Yoshiharu AbeKunio NakajimaPublished in: ICASSP (1989)
Keyphrases
- speech sounds
- speech recognition
- speaker independent
- speech signal
- automatic speech recognition
- speech synthesis
- speech recognition systems
- dynamic environments
- acoustic models
- speaker adaptation
- emotional speech
- vocal tract
- hidden markov models
- speaker dependent
- prosodic features
- speech recognizers
- noisy speech
- speech recognizer
- highly dynamic
- automatic speech recognition systems
- visual speech
- open environments
- acoustic features
- speaker identification
- noisy environments
- speaker verification
- pattern recognition
- spoken document retrieval
- emotion recognition
- speech retrieval
- phoneme recognition
- context dependent
- language model
- real world