Cover Image

Performance of adapting non-native speech in isolated speech recognizer

This paper presents the pronunciation performance between native and non-native speakers of Malay sounds in isolated speech recognizer (ISR). Speaker adaptation methods are combined to solve the performance decrease that recognizers are faced with native and non-native speech of speaker-independent...

Full description

Saved in:
Bibliographic Details
Main Authors: N., Seman, Jusoff, Kamaruzaman
Format: Article
Language:English
Published: Praise Worthy Prize 2008
Online Access:http://psasir.upm.edu.my/id/eprint/16136/1/Performance%20of%20adapting%20non.pdf
http://psasir.upm.edu.my/id/eprint/16136/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.upm.eprints.16136
record_format eprints
spelling my.upm.eprints.161362015-12-22T02:32:09Z http://psasir.upm.edu.my/id/eprint/16136/ Performance of adapting non-native speech in isolated speech recognizer N., Seman Jusoff, Kamaruzaman This paper presents the pronunciation performance between native and non-native speakers of Malay sounds in isolated speech recognizer (ISR). Speaker adaptation methods are combined to solve the performance decrease that recognizers are faced with native and non-native speech of speaker-independent (SI) models. Often, speech recognition performance degrades drastically if the recognizer which has been trained with native speech is exposed to non-native speech even though speech recognition systems have reached a certain level of maturity. Two experiments was performed to show the recognition accuracy of the baseline models trained with native dataset was drastically low for the non-native speakers from non-Malay group than for the native ones. Acoustic deviation has been discovered as one of important factors affecting the performance of the ISR. In this experiment, an acoustic technique has been implemented to compare the performance on native and non-native speech. We explore how acoustic models can be adapted to better recognize the non-native speech. The experiments show that there are many problems arise such as adaptation methods and the non-native pronunciation pattern that remains to be investigated. In future, it will be necessary to improve speaker adaptation methods by incorporating more extensive knowledge of speaker variation at both the acoustic and the pronunciation level. Praise Worthy Prize 2008-05 Article PeerReviewed application/pdf en http://psasir.upm.edu.my/id/eprint/16136/1/Performance%20of%20adapting%20non.pdf N., Seman and Jusoff, Kamaruzaman (2008) Performance of adapting non-native speech in isolated speech recognizer. International Review on Computers and Software, 3 (3). ISSN 1828-6003; ESSN: 1828-6011
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 the pronunciation performance between native and non-native speakers of Malay sounds in isolated speech recognizer (ISR). Speaker adaptation methods are combined to solve the performance decrease that recognizers are faced with native and non-native speech of speaker-independent (SI) models. Often, speech recognition performance degrades drastically if the recognizer which has been trained with native speech is exposed to non-native speech even though speech recognition systems have reached a certain level of maturity. Two experiments was performed to show the recognition accuracy of the baseline models trained with native dataset was drastically low for the non-native speakers from non-Malay group than for the native ones. Acoustic deviation has been discovered as one of important factors affecting the performance of the ISR. In this experiment, an acoustic technique has been implemented to compare the performance on native and non-native speech. We explore how acoustic models can be adapted to better recognize the non-native speech. The experiments show that there are many problems arise such as adaptation methods and the non-native pronunciation pattern that remains to be investigated. In future, it will be necessary to improve speaker adaptation methods by incorporating more extensive knowledge of speaker variation at both the acoustic and the pronunciation level.
format Article
author N., Seman
Jusoff, Kamaruzaman
spellingShingle N., Seman
Jusoff, Kamaruzaman
Performance of adapting non-native speech in isolated speech recognizer
author_facet N., Seman
Jusoff, Kamaruzaman
author_sort N., Seman
title Performance of adapting non-native speech in isolated speech recognizer
title_short Performance of adapting non-native speech in isolated speech recognizer
title_full Performance of adapting non-native speech in isolated speech recognizer
title_fullStr Performance of adapting non-native speech in isolated speech recognizer
title_full_unstemmed Performance of adapting non-native speech in isolated speech recognizer
title_sort performance of adapting non-native speech in isolated speech recognizer
publisher Praise Worthy Prize
publishDate 2008
url http://psasir.upm.edu.my/id/eprint/16136/1/Performance%20of%20adapting%20non.pdf
http://psasir.upm.edu.my/id/eprint/16136/
_version_ 1643826121957965824
score 13.211869

Similar Items