Improving Rapid Unsupervised Speaker Adaptation Based on HMM-Sufficient Statistics in Noisy Environments Using Multi-Template Models.
Randy GomezAkinobu LeeTomoki TodaHiroshi SaruwatariKiyohiro ShikanoPublished in: IEICE Trans. Inf. Syst. (2006)
Keyphrases
- speaker adaptation
- speech recognition
- noisy environments
- automatic speech recognition
- hidden markov models
- speech recognizer
- maximum likelihood
- noise reduction
- support vector machine
- speech signal
- sufficient statistics
- pattern recognition
- prior knowledge
- supervised learning
- model selection
- neural network
- markov models