Speaker-independent isolated word recognition for telephone voice using phoneme-like templates.
Tetsuya NomuraRyohei NakatsuPublished in: ICASSP (1986)
Keyphrases
- speech recognition
- speaker independent
- speaker dependent
- speech synthesis
- hidden markov models
- speaker identification
- speech recognizer
- language model
- speaker adaptation
- mel frequency cepstral coefficients
- automatic speech recognition
- speech recognition systems
- speech signal
- noisy environments
- emotion recognition
- maximum likelihood
- speaker diarization
- vocal tract
- digit recognition
- video sequences
- language modeling
- vision system
- high dimensional