Pronunciation modeling using a finite-state transducer representation

The MIT summit speech recognition system models pronunciation using a phonemic baseform dictionary along with rewrite rules for modeling phonological variation and multi-word reductions. Each pronunciation component is encoded within a finite-state transducer (FST) representation whose transition we...

Full description

Saved in:
Bibliographic Details
Published in:Speech communication 2005-06, Vol.46 (2), p.189-203
Main Authors: Hazen, Timothy J., Hetherington, I. Lee, Shu, Han, Livescu, Karen
Format: Article
Language:English
Subjects:
Applied sciences
Exact sciences and technology
Information, signal and communications theory
Signal processing
Speech processing
Telecommunications and information theory
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The MIT summit speech recognition system models pronunciation using a phonemic baseform dictionary along with rewrite rules for modeling phonological variation and multi-word reductions. Each pronunciation component is encoded within a finite-state transducer (FST) representation whose transition weights can be trained using an EM algorithm for finite-state networks. This paper explains the modeling approach we use and the details of its realization. We demonstrate the benefits and weaknesses of the approach both conceptually and empirically using the recognizer for our jupiter weather information system. Our experiments demonstrate that the use of phonological rewrite rules within our system achieves word error rate reductions between 4% and 9% over different test sets when compared against a system using no phonological rewrite rules.
ISSN:0167-6393
1872-7182
DOI:10.1016/j.specom.2005.03.004