A structural Bayes approach to speaker adaptation.

Maximum a posteriori (MAP) estimation has been successfully applied to speaker adaptation in speech recognition systems using hidden Markov models. When the amount of data is sufficiently large, MAP estimation yields recognition performance as good as that obtained using maximum-likelihood (ML) esti...

Mô tả đầy đủ

Chi tiết về thư mục
Xuất bản năm:	IEEE Transactions on speech and audio processing 9, 3 (2001).
Tác giả chính:	Shinoda, K.
Định dạng:	Bài viết
Ngôn ngữ:	English
Những chủ đề:	MAP estimation. SMAP approach. Error rates. Hidden Markov models. Hierarchical structure. Maximum a posteriori estimation. Model parameter space. Nonnative speaker. Probability density functions. Speaker adaptation. Speech recognition systems. Structural Bayes approach. Structural maximum a posteriori approach. Supervised adaptation experiments. Unsupervised adaptation experiments. Utterances.