Malaysian vowel recognition based on spectral envelope using bandwidth approach
Automatic speech recognition (ASR) has made great strides with the development of digital signal processing hardware and software especially using English as the language of choice.In this paper, a new feature extraction method is presented to identify vowels recorded from 80 Malaysian speakers.The...
Saved in:
Main Authors: | , , , |
---|---|
Format: | Conference or Workshop Item |
Language: | English |
Published: |
2009
|
Subjects: | |
Online Access: | http://repo.uum.edu.my/8689/1/M.pdf http://repo.uum.edu.my/8689/ http://dx.doi.org/10.1109/AMS.2009.152 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.uum.repo.8689 |
---|---|
record_format |
eprints |
spelling |
my.uum.repo.86892013-08-04T02:12:56Z http://repo.uum.edu.my/8689/ Malaysian vowel recognition based on spectral envelope using bandwidth approach Siraj, Fadzilah Mohd Yusof, Shahrul Azmi M.P., Paulraj Yaacob, Sazali QA76 Computer software Automatic speech recognition (ASR) has made great strides with the development of digital signal processing hardware and software especially using English as the language of choice.In this paper, a new feature extraction method is presented to identify vowels recorded from 80 Malaysian speakers.The features are obtained from Vocal Tract Model based on Bandwidth (BW) approach.The bandwidth is determined by finding the frequency where the spectral energy is 3dB below the peak.Average gain was calculated from these bandwidths.Classification results from Bandwidth Approach were then compared with results from 14 MFCC Coefficients using BPNN (Backpropagation Neural Network), MLR (Multinomial Logistic Regression) and LDA (Linear Discriminative Analysis).Classification accuracy obtained shows Bandwidth Approach performs better than MFCC using all these classifiers. 2009 Conference or Workshop Item PeerReviewed application/pdf en http://repo.uum.edu.my/8689/1/M.pdf Siraj, Fadzilah and Mohd Yusof, Shahrul Azmi and M.P., Paulraj and Yaacob, Sazali (2009) Malaysian vowel recognition based on spectral envelope using bandwidth approach. In: Third Asia International Conference on Modelling & Simulation 2009 (AMS '09), 25-29 May 2009, Bali, Indonesia. http://dx.doi.org/10.1109/AMS.2009.152 doi:10.1109/AMS.2009.152 |
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 Siraj, Fadzilah Mohd Yusof, Shahrul Azmi M.P., Paulraj Yaacob, Sazali Malaysian vowel recognition based on spectral envelope using bandwidth approach |
description |
Automatic speech recognition (ASR) has made great strides with the development of digital signal processing hardware and software especially using English as the language of choice.In this paper, a new feature extraction method is presented to identify vowels recorded from 80 Malaysian speakers.The features are obtained from Vocal Tract Model based on Bandwidth (BW) approach.The bandwidth is determined by finding the frequency where the spectral energy is 3dB below the peak.Average gain was calculated from these bandwidths.Classification results from Bandwidth
Approach were then compared with results from 14 MFCC Coefficients using BPNN (Backpropagation Neural Network), MLR (Multinomial Logistic Regression) and LDA (Linear Discriminative Analysis).Classification accuracy obtained shows Bandwidth Approach performs better than MFCC using all these classifiers. |
format |
Conference or Workshop Item |
author |
Siraj, Fadzilah Mohd Yusof, Shahrul Azmi M.P., Paulraj Yaacob, Sazali |
author_facet |
Siraj, Fadzilah Mohd Yusof, Shahrul Azmi M.P., Paulraj Yaacob, Sazali |
author_sort |
Siraj, Fadzilah |
title |
Malaysian vowel recognition based on spectral envelope using bandwidth approach |
title_short |
Malaysian vowel recognition based on spectral envelope using bandwidth approach |
title_full |
Malaysian vowel recognition based on spectral envelope using bandwidth approach |
title_fullStr |
Malaysian vowel recognition based on spectral envelope using bandwidth approach |
title_full_unstemmed |
Malaysian vowel recognition based on spectral envelope using bandwidth approach |
title_sort |
malaysian vowel recognition based on spectral envelope using bandwidth approach |
publishDate |
2009 |
url |
http://repo.uum.edu.my/8689/1/M.pdf http://repo.uum.edu.my/8689/ http://dx.doi.org/10.1109/AMS.2009.152 |
_version_ |
1644279898966065152 |
score |
13.1944895 |