Variance compensation within the MLLR framework for robust speech recognition and speaker adaptation.
Mark J. F. GalesDavid PyePhilip C. WoodlandPublished in: ICSLP (1996)
Keyphrases
- speech recognition
- speaker adaptation
- speech recognizer
- maximum likelihood
- automatic speech recognition
- noisy environments
- speaker independent
- speech signal
- speaker dependent
- language model
- hidden markov models
- pattern recognition
- speech recognition systems
- speaker identification
- speech synthesis
- computer vision
- multi modal
- feature extraction
- face recognition
- machine learning