Improving Language Models by Learning from Speech Recognition Errors in a Reading Tutor that Listens

S. Banerjee, Jack Mostow, Joseph E. Beck, and W. Tam
Second International Conference on Applied Artificial Intelligence, December, 2003.


Download
  • Adobe portable document format (pdf) (250KB)
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Abstract
Lowering the perplexity of a language model does not always translate into higher speech recognition accuracy. Our goal is to improve language models by learning from speech recognition errors. In this paper we present an algorithm that first learns to predict which n-grams are likely to increase recognition errors, and then uses that prediction to improve language models so that the errors are reduced. We show that our algorithm reduces a measure of tracking error by more than 24% on unseen test data from a Reading Tutor that listens to children read aloud.

Notes
Associated Lab(s) / Group(s): Project LISTEN
Associated Project(s): Project LISTEN\'s Reading Tutor

Text Reference
S. Banerjee, Jack Mostow, Joseph E. Beck, and W. Tam, "Improving Language Models by Learning from Speech Recognition Errors in a Reading Tutor that Listens," Second International Conference on Applied Artificial Intelligence, December, 2003.

BibTeX Reference
@inproceedings{Mostow_2003_4652,
   author = "S. Banerjee and Jack Mostow and Joseph E Beck and W. Tam",
   title = "Improving Language Models by Learning from Speech Recognition Errors in a Reading Tutor that Listens",
   booktitle = "Second International Conference on Applied Artificial Intelligence",
   month = "December",
   year = "2003",
}