Speaker-consistent parsing for speaker-independent continuous speech recognition.
Kouichi YamaguchiHarald SingerShoichi MatsunagaShigeki SagayamaPublished in: ICSLP (1994)
Keyphrases
- support vector machine
- continuous speech recognition
- speaker independent
- speech recognition
- speaker dependent
- digit recognition
- speaker identification
- hidden markov models
- speaker adaptation
- speech recognizer
- acoustic models
- natural language
- automatic speech recognition
- language model
- speech synthesis
- speech recognition systems
- feature extraction
- gaussian mixture model
- neural network
- natural language processing
- probabilistic neural network
- speaker recognition
- noisy environments
- speech signal
- multi modal
- broadcast news
- speaker diarization
- visual features
- low level
- pattern recognition