Rapid speech recognizer adaptation to new speakers

Vassilios Digalakis, Heather Collier, Sid Berkowitz, Adrian Corduneanu, Enrico Bocchieri, Ashvin Kannan, Constantinos Boulis, Sanjeev Khudanpur, William Byrne, Ananth SankarICASSP 1999 · OpenReview

Abstract

This paper summarizes the work of the "Rapid Speech Recognizer Adaptation" team in the workshop held at Johns Hopkins University in the summer of 1998. The project addressed the modeling of dependencies between units of speech with the goal of making more effective use of small amounts of data for speaker adaptation. A variety of methods were investigated and their effectiveness in a rapid adaptation task defined on the Switchboard conversational speech corpus is reported.
BibTeX
@inproceedings{digalakis1999rapid,
  author = {Vassilios Digalakis and Heather Collier and Sid Berkowitz and Adrian Corduneanu and Enrico Bocchieri and Ashvin Kannan and Constantinos Boulis and Sanjeev Khudanpur and William Byrne and Ananth Sankar},
  title = {{Rapid speech recognizer adaptation to new speakers}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {1999},
  url = {https://openreview.net/forum?id=ic1a8Bjp9z_},
}

Loading related content...

Figure