CUED Publications database

Compression techniques applied to multiple speech recognition systems

Breslin, C and Stuttle, M and Knill, K (2009) Compression techniques applied to multiple speech recognition systems. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. pp. 1407-1410. ISSN 1990-9772

Full text not available from this repository.

Abstract

Speech recognition systems typically contain many Gaussian distributions, and hence a large number of parameters. This makes them both slow to decode speech, and large to store. Techniques have been proposed to decrease the number of parameters. One approach is to share parameters between multiple Gaussians, thus reducing the total number of parameters and allowing for shared likelihood calculation. Gaussian tying and subspace clustering are two related techniques which take this approach to system compression. These techniques can decrease the number of parameters with no noticeable drop in performance for single systems. However, multiple acoustic models are often used in real speech recognition systems. This paper considers the application of Gaussian tying and subspace compression to multiple systems. Results show that two speech recognition systems can be modelled using the same number of Gaussians as just one system, with little effect on individual system performance. Copyright © 2009 ISCA.

Item Type: Article
Uncontrolled Keywords: Automatic speech recognition Gaussian tying Graphemes Subspace compression
Subjects: UNSPECIFIED
Divisions: Div F > Machine Intelligence
Depositing User: Cron Job
Date Deposited: 07 Mar 2014 12:14
Last Modified: 08 Dec 2014 02:36
DOI: