CUED Publications database

Word boundary modelling and full covariance gaussians for Arabic Speech-to-Text systems

Dieh, F and Gales, MJF and Liu, X and Tomalin, M and Woodland, PC (2011) Word boundary modelling and full covariance gaussians for Arabic Speech-to-Text systems. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. pp. 777-780. ISSN 1990-9772

Full text not available from this repository.

Abstract

This paper describes recent improvements to the Cambridge Arabic Large Vocabulary Continuous Speech Recognition (LVCSR) Speech-to-Text (STT) system. It is shown that wordboundary context markers provide a powerful method to enhance graphemic systems by implicit phonetic information, improving the modelling capability of graphemic systems. In addition, a robust technique for full covariance Gaussian modelling in the Minimum Phone Error (MPE) training framework is introduced. This reduces the full covariance training to a diagonal covariance training problem, thereby solving related robustness problems. The full system results show that the combined use of these and other techniques within a multi-branch combination framework reduces the Word Error Rate (WER) of the complete system by up to 5.9% relative. Copyright © 2011 ISCA.

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