How effective is unsupervised data collection for children's speech recognition?

December 1998

How effective is unsupervised data collection for children's speech recognition?

Authors:

Gregory Aist, Peggy Chan, X. D. Huang, L. Jiang, Rebecca Kennedy, DeWitt Talmadge Latimer, Jack Mostow, and Calvin Yeung

Abstract:

Children present a unique challenge to automatic speech recognition. Today's state-of-the-art speech recognition systems still have problems handling children's speech because acoustic models are trained on data collected from adult speech. In this paper we describe an inexpensive way to mend this problem. We collected children's speech when they interact with an automated reading tutor. These data are subsequently transcribed by a speech recognition system and automatically filtered. We studied how to use these automatically collected data to improve children's speech recognition system's performance. Experiments indicate that automatically collected data can reduce the error rate significantly on children's speech.
@conference{Aist-1998-14827,
author = {Gregory Aist And Peggy Chan And X. D. Huang And L. Jiang And Rebecca Kennedy And DeWitt Talmadge Latimer And Jack Mostow And Calvin Yeung},
title = {How effective is unsupervised data collection for children's speech recognition?},
booktitle = {Proceedings of 5th International Conference on Spoken Language Processing (ICSLP '98)},
year = {1998},
month = {December},
}
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.