CUED Publications database

Morphological decomposition in Arabic ASR systems

Diehl, F and Gales, MJF and Tomalin, M and Woodland, PC (2012) Morphological decomposition in Arabic ASR systems. Computer Speech and Language, 26. pp. 229-243. ISSN 0885-2308

Full text not available from this repository.

Abstract

In recent years, the use of morphological decomposition strategies for Arabic Automatic Speech Recognition (ASR) has become increasingly popular. Systems trained on morphologically decomposed data are often used in combination with standard word-based approaches, and they have been found to yield consistent performance improvements. The present article contributes to this ongoing research endeavour by exploring the use of the 'Morphological Analysis and Disambiguation for Arabic' (MADA) tools for this purpose. System integration issues concerning language modelling and dictionary construction, as well as the estimation of pronunciation probabilities, are discussed. In particular, a novel solution for morpheme-to-word conversion is presented which makes use of an N-gram Statistical Machine Translation (SMT) approach. System performance is investigated within a multi-pass adaptation/combination framework. All the systems described in this paper are evaluated on an Arabic large vocabulary speech recognition task which includes both Broadcast News and Broadcast Conversation test data. It is shown that the use of MADA-based systems, in combination with word-based systems, can reduce the Word Error Rates by up to 8.1 relative. © 2012 Elsevier Ltd. All rights reserved.

Item Type: Article
Uncontrolled Keywords: Arabic Automatic Speech Recognition Morphology Pronunciation probabilities
Subjects: UNSPECIFIED
Divisions: Div F > Machine Intelligence
Depositing User: Cron Job
Date Deposited: 07 Mar 2014 12:15
Last Modified: 30 Nov 2014 10:45
DOI: 10.1016/j.csl.2011.12.001