Improved Malay vowel feature extraction method based on first and second formants
There are many speech recognition applications that use vowels phonemes.Among them are speech therapy systems that improve utterances of word pronunciation especially to children.There are also systems that teach hearing impaired person to speak properly by pronouncing words with a good degree of in...
Saved in:
Main Authors: | , , , , |
---|---|
Format: | Conference or Workshop Item |
Language: | English |
Published: |
2010
|
Subjects: | |
Online Access: | http://repo.uum.edu.my/8688/1/I.pdf http://repo.uum.edu.my/8688/ http://dx.doi.org/10.1109/CIMSiM.2010.59 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.uum.repo.8688 |
---|---|
record_format |
eprints |
spelling |
my.uum.repo.86882013-08-19T08:56:06Z http://repo.uum.edu.my/8688/ Improved Malay vowel feature extraction method based on first and second formants Mohd Yusof, Shahrul Azmi Siraj, Fadzillah Yaacob, S. M.P., Paulraj Nazri, Ahmad QA76 Computer software There are many speech recognition applications that use vowels phonemes.Among them are speech therapy systems that improve utterances of word pronunciation especially to children.There are also systems that teach hearing impaired person to speak properly by pronouncing words with a good degree of intelligibility.All of these systems require high degree of vowel recognition capability.This paper presents a new method of Malay vowel feature extraction based on formant and spectrum envelope called First Formant Bandwidth (F1BW).It is an effort to increase Malay vowel recognition capability by using a new speech database that consist of words uttered by Malaysian speakers from the three major races, Malay, Chinese and Indians.Based on single frame analysis, F1BW performs better than MFCC by more than 9% based on four classifiers of Levenberg-Marquart trained Neural Network, K-Nearest Neighbours, Multinomial Logistic Regression and Linear Discriminant Analysis. 2010 Conference or Workshop Item PeerReviewed application/pdf en http://repo.uum.edu.my/8688/1/I.pdf Mohd Yusof, Shahrul Azmi and Siraj, Fadzillah and Yaacob, S. and M.P., Paulraj and Nazri, Ahmad (2010) Improved Malay vowel feature extraction method based on first and second formants. In: Second International Conference on Computational Intelligence, Modelling and Simulation (CIMSiM), 2010 , 28-30 Sept. 2010 , Bali, Indonesia. http://dx.doi.org/10.1109/CIMSiM.2010.59 doi:10.1109/CIMSiM.2010.59 |
institution |
Universiti Utara Malaysia |
building |
UUM Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Utara Malaysia |
content_source |
UUM Institutionali Repository |
url_provider |
http://repo.uum.edu.my/ |
language |
English |
topic |
QA76 Computer software |
spellingShingle |
QA76 Computer software Mohd Yusof, Shahrul Azmi Siraj, Fadzillah Yaacob, S. M.P., Paulraj Nazri, Ahmad Improved Malay vowel feature extraction method based on first and second formants |
description |
There are many speech recognition applications that use vowels phonemes.Among them are speech therapy systems that improve utterances of word pronunciation especially to children.There are also systems that teach hearing impaired person to speak properly by pronouncing words with a good degree of intelligibility.All of these systems require high degree of vowel recognition capability.This paper presents a new method of Malay vowel feature extraction based on formant and spectrum envelope called First Formant Bandwidth (F1BW).It is an effort to increase Malay vowel recognition capability by using a new speech database that consist of words uttered by Malaysian speakers from the three major races, Malay, Chinese and Indians.Based on single frame analysis, F1BW performs better than MFCC by more than 9% based on four classifiers of Levenberg-Marquart trained Neural Network, K-Nearest Neighbours, Multinomial Logistic Regression and Linear Discriminant Analysis. |
format |
Conference or Workshop Item |
author |
Mohd Yusof, Shahrul Azmi Siraj, Fadzillah Yaacob, S. M.P., Paulraj Nazri, Ahmad |
author_facet |
Mohd Yusof, Shahrul Azmi Siraj, Fadzillah Yaacob, S. M.P., Paulraj Nazri, Ahmad |
author_sort |
Mohd Yusof, Shahrul Azmi |
title |
Improved Malay vowel feature extraction method based on first and second formants |
title_short |
Improved Malay vowel feature extraction method based on first and second formants |
title_full |
Improved Malay vowel feature extraction method based on first and second formants |
title_fullStr |
Improved Malay vowel feature extraction method based on first and second formants |
title_full_unstemmed |
Improved Malay vowel feature extraction method based on first and second formants |
title_sort |
improved malay vowel feature extraction method based on first and second formants |
publishDate |
2010 |
url |
http://repo.uum.edu.my/8688/1/I.pdf http://repo.uum.edu.my/8688/ http://dx.doi.org/10.1109/CIMSiM.2010.59 |
_version_ |
1644279898673512448 |
score |
13.149126 |