Evaluation on unsupervised speaker adaptation based on sufficient HMM statictics of selected speakers.
Shinichi YoshizawaAkira BabaKanako MatsunamiYuichiro MeraMiichi YamadaAkinobu LeeKiyohiro ShikanoPublished in: INTERSPEECH (2001)
Keyphrases
- non stationary
- speaker adaptation
- speech recognition
- maximum likelihood
- automatic speech recognition
- speech signal
- hidden markov models
- speaker dependent
- speech recognizer
- speaker independent
- language model
- information retrieval systems
- vocal tract
- text classification
- natural language processing
- semi supervised
- pattern recognition
- machine learning
- neural network