CUED Publications database

Improving LVCSR system combination using neural network language model cross adaptation

Liu, X and Gales, MJF and Woodland, PC (2011) Improving LVCSR system combination using neural network language model cross adaptation. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. pp. 2857-2860. ISSN 1990-9772

Full text not available from this repository.

Abstract

State-of-the-art large vocabulary continuous speech recognition (LVCSR) systems often combine outputs from multiple subsystems developed at different sites. Cross system adaptation can be used as an alternative to direct hypothesis level combination schemes such as ROVER. The standard approach involves only cross adapting acoustic models. To fully exploit the complimentary features among sub-systems, language model (LM) cross adaptation techniques can be used. Previous research on multi-level n-gram LM cross adaptation is extended to further include the cross adaptation of neural network LMs in this paper. Using this improved LM cross adaptation framework, significant error rate gains of 4.0%-7.1% relative were obtained over acoustic model only cross adaptation when combining a range of Chinese LVCSR sub-systems used in the 2010 and 2011 DARPA GALE evaluations. Copyright © 2011 ISCA.

Item Type: Article
Subjects: UNSPECIFIED
Divisions: Div F > Machine Intelligence
Depositing User: Cron Job
Date Deposited: 07 Mar 2014 12:30
Last Modified: 08 Dec 2014 02:38
DOI: