Improving Language Models by Learning from Speech Recognition Errors in a Reading Tutor that Listens - Robotics Institute Carnegie Mellon University

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
Conference Paper, Proceedings of 2nd International Conference on Applied Artificial Intelligence (ICAAI '03), December, 2003

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.

BibTeX

@conference{Banerjee-2003-8831,
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 = {Proceedings of 2nd International Conference on Applied Artificial Intelligence (ICAAI '03)},
year = {2003},
month = {December},
}