Date of Original Version

9-2010

Type

Conference Proceeding

Journal Title

Proceedings of INTERSPEECH

First Page

1501

Last Page

1504

Rights Management

Copyright 2010 ISCA

Abstract or Description

This paper describes the latest Speech-to-Text system developed for the Global Autonomous Language Exploitation ("GALE") domain by Carnegie Mellon University (CMU). This systems uses discriminative training, bottle-neck features and other techniques that were not used in previous versions of our system, and is trained on 1150 hours of data from a variety of Arabic speech sources. In this paper, we show how different lexica, pre-processing, and system combination techniques can be used to improve the final output, and provide analysis of the improvements achieved by the individual techniques.

Share

COinS
 

Published In

Proceedings of INTERSPEECH, 1501-1504.