University of Cambridge > Talks.cam > Machine Intelligence Lab Seminar > Incremental adaptation of speech recognition based on macroscopic time evolution system

Incremental adaptation of speech recognition based on macroscopic time evolution system

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Kai Yu.

In a real environment, acoustic and language features often vary depending on the speakers, speaking styles and topic changes. To accommodate these changes, speech recognition approaches have to include the incremental tracking of changing environments. In this talk, I introduce acoustic model adaptation based on macroscopic time evolution system, where posterior distributions of acoustic model parameters are successively updated based on a macroscopic time scale. I also introduce a topic tracking language model that can adaptively track changes in topics based on current text information and previously estimated topic models in an on-line manner. In addition, I briefly introduce recent NTT CS Labs’ speech recognition research, which mainly focuses on meeting recognition.

This talk is part of the Machine Intelligence Lab Seminar series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2020 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity