Rapid speaker adaptation using speaker-mixture allophone models applied to speaker-independent speech recognition.
Tetsuo KosakaJun-ichi TakamiShigeki SagayamaPublished in: ICASSP (2) (1993)
Keyphrases
- speaker adaptation
- speech recognition
- speaker independent
- acoustic models
- speaker dependent
- speech recognizer
- hidden markov models
- automatic speech recognition
- maximum likelihood
- speaker identification
- speech synthesis
- language model
- noisy environments
- speech recognition systems
- speech signal
- neural network
- pattern recognition
- mixture model
- digit recognition
- probabilistic model
- gaussian mixture model
- image processing