Cover Image

Acoustic Pronunciation Variations Modeling for Standard Malay Speech Recognition

This paper presents different methods of handling pronunciation variations in Standard Malay (SM) speech recognition. Pronunciation variation can be handled by explicitly modifying the knowledge sources or improving the decoding method. Two types of pronunciation variations are defined, namely, co...

Full description

Saved in:
Bibliographic Details
Main Authors: Seman, Noraini, Jusoff, Kamaruzaman
Format: Article
Language:English
Published: 2008
Online Access:http://psasir.upm.edu.my/id/eprint/7628/
http://ccsenet.org/journal/index.php/cis/article/view/1157
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.upm.eprints.7628
record_format eprints
spelling my.upm.eprints.76282010-08-03T06:44:12Z http://psasir.upm.edu.my/id/eprint/7628/ Acoustic Pronunciation Variations Modeling for Standard Malay Speech Recognition Seman, Noraini Jusoff, Kamaruzaman This paper presents different methods of handling pronunciation variations in Standard Malay (SM) speech recognition. Pronunciation variation can be handled by explicitly modifying the knowledge sources or improving the decoding method. Two types of pronunciation variations are defined, namely, complete or phone changes and partial or sound changes. Complete or phone change means that one phoneme is realized as another phoneme. Meanwhile, a partial or sound change happens when the acoustic realization is ambiguous between two phonemes. Complete or phone changes can be handled by constructing a pronunciation variation dictionary to include alternative pronunciations at the lexical level or dynamically expanding the search space to include those pronunciation variants. Sound or partial changes can be handled by adjusting the acoustic models through sharing or adaptation of the Gaussian mixture components. Experimental results show that the use of a pronunciation variation dictionary and the method of dynamic search space expansion can improve speech recognition performance substantially. The methods of acoustic model refinement were found to be relatively less effective in our experiments. 2008 Article PeerReviewed Seman, Noraini and Jusoff, Kamaruzaman (2008) Acoustic Pronunciation Variations Modeling for Standard Malay Speech Recognition. Computer and Information Science, 1 (4). pp. 112-120. ISSN 1913-8989 http://ccsenet.org/journal/index.php/cis/article/view/1157 English
institution Universiti Putra Malaysia
building UPM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Putra Malaysia
content_source UPM Institutional Repository
url_provider http://psasir.upm.edu.my/
language English
description This paper presents different methods of handling pronunciation variations in Standard Malay (SM) speech recognition. Pronunciation variation can be handled by explicitly modifying the knowledge sources or improving the decoding method. Two types of pronunciation variations are defined, namely, complete or phone changes and partial or sound changes. Complete or phone change means that one phoneme is realized as another phoneme. Meanwhile, a partial or sound change happens when the acoustic realization is ambiguous between two phonemes. Complete or phone changes can be handled by constructing a pronunciation variation dictionary to include alternative pronunciations at the lexical level or dynamically expanding the search space to include those pronunciation variants. Sound or partial changes can be handled by adjusting the acoustic models through sharing or adaptation of the Gaussian mixture components. Experimental results show that the use of a pronunciation variation dictionary and the method of dynamic search space expansion can improve speech recognition performance substantially. The methods of acoustic model refinement were found to be relatively less effective in our experiments.
format Article
author Seman, Noraini
Jusoff, Kamaruzaman
spellingShingle Seman, Noraini
Jusoff, Kamaruzaman
Acoustic Pronunciation Variations Modeling for Standard Malay Speech Recognition
author_facet Seman, Noraini
Jusoff, Kamaruzaman
author_sort Seman, Noraini
title Acoustic Pronunciation Variations Modeling for Standard Malay Speech Recognition
title_short Acoustic Pronunciation Variations Modeling for Standard Malay Speech Recognition
title_full Acoustic Pronunciation Variations Modeling for Standard Malay Speech Recognition
title_fullStr Acoustic Pronunciation Variations Modeling for Standard Malay Speech Recognition
title_full_unstemmed Acoustic Pronunciation Variations Modeling for Standard Malay Speech Recognition
title_sort acoustic pronunciation variations modeling for standard malay speech recognition
publishDate 2008
url http://psasir.upm.edu.my/id/eprint/7628/
http://ccsenet.org/journal/index.php/cis/article/view/1157
_version_ 1643823779986538496
score 13.211869

Similar Items