Speech and Language Processing

-Introduction to Automatic Speech Recognition-

Lecture: 15:05-16:35(JST) G224
  1. Speech recognition based on GMM, HMM, and N-gram html pdf Lecture: 2017/10/20
  2. Maximum likelihood estimation and EM algorithm pdf (updated 2017/11/3) Lecture: 2017/10/27
  3. Bayesian network and Bayesian inference pdf Lecture: 2017/11/3
  4. Variational inference and sampling pdf Lecture: 2017/11/6
  5. Neural network based acoustic and language models pdf Lecture: 2017/11/7
  6. Weighted finite state transducer (WFST) and speech decoding pdf Lecture: 2017/11/7
*sound is not available in the PDF.

Takahiro Shinozaki
Department of Information and Communication Engineering
School of Engineering
Tokyo Institute of Technology

[back to home]