Speech and Language Processing
-Introduction to Automatic Speech Recognition-
Lecture material for TAIST-Tokyo Tech Program
Lecture:
- Speech recognition based on GMM, HMM, and N-gram
pdf
2020/10/19 13:00-16:00 (15:00-18:00 JST)
- Maximum likelihood estimation and EM algorithm
pdf
2020/10/19 13:00-16:00 (15:00-18:00 JST)
- Bayesian network and Bayesian inference
pdf
Lecture: 2020/10/20 13:00-16:00 (15:00-18:00 JST)
- Variational inference and sampling
pdf
Lecture: 2020/10/20 13:00-16:00 (15:00-18:00 JST)
- Neural network based acoustic and language models
pdf
Lecture: 2020/10/22 13:00-16:00 (15:00-18:00 JST)
- Weighted finite state transducer (WFST) and speech decoding
pdf
Lecture: 2020/10/22 13:00-16:00 (15:00-18:00 JST)
*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]