An evaluation of using mutual information for selection of acoustic-features representation of phonemes for speech recognition.
Mohamed Kamal OmarKen ChenMark Hasegawa-JohnsonYigal BrandmanPublished in: INTERSPEECH (2002)
Keyphrases
- speech recognition
- speech signal
- automatic speech recognition
- acoustic features
- mutual information
- hidden markov models
- speech synthesis
- noisy environments
- pattern recognition
- mel frequency cepstral coefficients
- speech recognition systems
- language model
- speaker independent
- speaker identification
- similarity measure
- speaker verification
- cross correlation
- speech recognizer
- cepstral coefficients
- video sequences
- broadcast news
- music information retrieval
- speaker recognition