An improved feature extraction method for Malay vowel recognition based on spectrum delta
Malay speech recognition is becoming popular among Malaysian researchers. In Malaysia, more local researchers are focusing on noise robust and accurate independent speaker speech recognition systems that use Malay language.The performance of speech recognition application under adverse noisy conditi...
Saved in:
Main Author: | |
---|---|
Format: | Article |
Language: | English |
Published: |
2014
|
Subjects: | |
Online Access: | http://repo.uum.edu.my/20612/1/IJSEIT%208%201%202014%20413%20426.pdf http://repo.uum.edu.my/20612/ http://doi.org/10.14257/ijseia.2014.8.1.35 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Universiti Utara Malaysia |
Language: | English |
id |
my.uum.repo.20612 |
---|---|
record_format |
eprints |
spelling |
my.uum.repo.206122017-01-16T08:30:34Z http://repo.uum.edu.my/20612/ An improved feature extraction method for Malay vowel recognition based on spectrum delta Mohd Yusof, Shahrul Azmi QA75 Electronic computers. Computer science Malay speech recognition is becoming popular among Malaysian researchers. In Malaysia, more local researchers are focusing on noise robust and accurate independent speaker speech recognition systems that use Malay language.The performance of speech recognition application under adverse noisy condition often becomes the topic of interest among speech recognition researchers in any languages.This paper presents a study of noise robust capability of an improved vowel feature extraction method called Spectrum Delta (SpD).The features are extracted from both original data and noise-added data and classified using three classifiers; (i) Linear Discriminant Analysis (LDA), (ii) K-Nearest Neighbors (k-NN) and (iii) Multinomial Logistic Regression (MLR). Most of the dependent and independent speaker systems which use mostly multi-framed analysis, yielded accuracy between 89% to 100% for dependent speaker system and between 70% to 94% for an independent speaker. This study shows that SpD features obtained an accuracy of 92.42% to 95.11% using all the four classifiers on a single framed analysis which makes this result comparable to those analysed with multi-framed approach. 2014 Article PeerReviewed application/pdf en http://repo.uum.edu.my/20612/1/IJSEIT%208%201%202014%20413%20426.pdf Mohd Yusof, Shahrul Azmi (2014) An improved feature extraction method for Malay vowel recognition based on spectrum delta. International Journal of Software Engineering and Its Applications, 8 (1). pp. 413-426. ISSN 1738-9984 http://doi.org/10.14257/ijseia.2014.8.1.35 doi:10.14257/ijseia.2014.8.1.35 |
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 |
QA75 Electronic computers. Computer science |
spellingShingle |
QA75 Electronic computers. Computer science Mohd Yusof, Shahrul Azmi An improved feature extraction method for Malay vowel recognition based on spectrum delta |
description |
Malay speech recognition is becoming popular among Malaysian researchers. In Malaysia, more local researchers are focusing on noise robust and accurate independent speaker speech recognition systems that use Malay language.The performance of speech recognition application under adverse noisy condition often becomes the topic of interest among speech recognition researchers in any languages.This paper presents a study of noise robust capability of an improved vowel feature extraction method called Spectrum Delta (SpD).The features are extracted from both original data and noise-added data and classified using three classifiers; (i) Linear Discriminant Analysis (LDA), (ii) K-Nearest Neighbors (k-NN) and (iii) Multinomial Logistic Regression (MLR). Most of the dependent and independent speaker systems which use mostly multi-framed analysis, yielded accuracy between 89% to 100% for dependent speaker system and between 70% to 94% for an independent speaker. This study shows that SpD features obtained an accuracy of 92.42% to 95.11% using all the four classifiers on a single framed analysis which makes this result comparable to those analysed with multi-framed approach. |
format |
Article |
author |
Mohd Yusof, Shahrul Azmi |
author_facet |
Mohd Yusof, Shahrul Azmi |
author_sort |
Mohd Yusof, Shahrul Azmi |
title |
An improved feature extraction method for Malay vowel recognition based on spectrum delta |
title_short |
An improved feature extraction method for Malay vowel recognition based on spectrum delta |
title_full |
An improved feature extraction method for Malay vowel recognition based on spectrum delta |
title_fullStr |
An improved feature extraction method for Malay vowel recognition based on spectrum delta |
title_full_unstemmed |
An improved feature extraction method for Malay vowel recognition based on spectrum delta |
title_sort |
improved feature extraction method for malay vowel recognition based on spectrum delta |
publishDate |
2014 |
url |
http://repo.uum.edu.my/20612/1/IJSEIT%208%201%202014%20413%20426.pdf http://repo.uum.edu.my/20612/ http://doi.org/10.14257/ijseia.2014.8.1.35 |
_version_ |
1644283005834887168 |