Spectral subtraction in noisy environments applied to speaker adaptation based on HMM sufficient statistics.
Shingo YamadeKanako MatsunamiAkira BabaAkinobu LeeHiroshi SaruwatariKiyohiro ShikanoPublished in: INTERSPEECH (2002)
Keyphrases
- speech recognition
- noisy environments
- speaker adaptation
- speech signal
- automatic speech recognition
- hidden markov models
- spectral subtraction
- noisy speech
- speech enhancement
- speaker identification
- speech recognizer
- speaker independent
- speaker verification
- digit recognition
- hybrid method
- image coding
- background noise
- sufficient statistics
- pattern recognition