Cover Image

Feature space reduction in ethnically diverse Malaysian English accents classification

Proceeding of the 7th International Conference on Intelligent Systems and Control, (ISCO) 2013 at Coimbatore, Tamilnadu, India on 4 January 2013 through 5 January 2013. Link to publisher's homepage at http://ezproxy.unimap.edu.my:2080/Xplore/dynhome.jsp

Saved in:
Bibliographic Details
Main Authors: Yusnita, Mohd Ali, Pandiyan, Paulraj Murugesa , Prof. Dr., Sazali, Yaacob, Prof. Dr., Shahriman, Abu Bakar, Dr.
Other Authors: yusnita082@ppinang.uitm.edu.my
Format: Working Paper
Language:English
Published: IEEE Conference Publications 2014
Subjects:
Accent classification
K-nearest neighbors
Malaysian English
Mel-band energys
Mel-frequency cepstral coefficients
Principle component analysis
Online Access:http://dspace.unimap.edu.my:80/dspace/handle/123456789/35444
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.unimap-35444
record_format dspace
spelling my.unimap-354442014-06-12T09:11:22Z Feature space reduction in ethnically diverse Malaysian English accents classification Yusnita, Mohd Ali Pandiyan, Paulraj Murugesa , Prof. Dr. Sazali, Yaacob, Prof. Dr. Shahriman, Abu Bakar, Dr. yusnita082@ppinang.uitm.edu.my paul@unimap.edu.my s.yaacob@unimap.edu.my shahriman@unimap.edu.my Accent classification K-nearest neighbors Malaysian English Mel-band energys Mel-frequency cepstral coefficients Principle component analysis Proceeding of the 7th International Conference on Intelligent Systems and Control, (ISCO) 2013 at Coimbatore, Tamilnadu, India on 4 January 2013 through 5 January 2013. Link to publisher's homepage at http://ezproxy.unimap.edu.my:2080/Xplore/dynhome.jsp In this paper we propose a reduced dimensional space of statistical descriptors of mel-bands spectral energy (MBSE) vectors for accent classification of Malaysian English (MalE) speakers caused by diverse ethnics. Principle component analysis (PCA) with eigenvector decomposition approach was utilized to project this high-dimensional dataset into uncorrelated space through the interesting covariance structure of a set of variables. This delimitates the size of feature vector necessary for good classification task once significant coordinate system is revealed. The objectives of this paper have three-fold. Firstly, to generate reduced size feature vector in order to decrease the memory requirement and the computational time. Secondly, to improve the classification accuracy. Thirdly, to replace the state-of-the-art mel-frequency cepstral coefficients (MFCC) method that is more susceptible to noisy environment. The system was designed using K-nearest neighbors algorithm and evaluated on 20% independent test dataset. The proposed PCA-transformed mel-bands spectral energy (PCA-MBSE) on MalE database has proven to be more efficient in terms of space and robust over the baselines MFCC and MBSE. PCA-MBSE achieved the same accuracy as the original MBSE at 66.67% reduced feature vector and tested to be superiorly robust under various noisy conditions with only 10.48% drop in the performance as compared to 16.81% and 48.01% using MBSE and MFCC respectively. 2014-06-12T09:11:22Z 2014-06-12T09:11:22Z 2013 Working Paper p. 72-78 978-1-4673-4359-6 http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6481125 http://dspace.unimap.edu.my:80/dspace/handle/123456789/35444 http://dx.doi.org/10.1109/ISCO.2013.6481125 en Proceeding of the 7th International Conference on Intelligent Systems and Control (ISCO 2013); IEEE Conference Publications
institution Universiti Malaysia Perlis
building UniMAP Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Malaysia Perlis
content_source UniMAP Library Digital Repository
url_provider http://dspace.unimap.edu.my/
language English
topic Accent classification
K-nearest neighbors
Malaysian English
Mel-band energys
Mel-frequency cepstral coefficients
Principle component analysis
spellingShingle Accent classification
K-nearest neighbors
Malaysian English
Mel-band energys
Mel-frequency cepstral coefficients
Principle component analysis
Yusnita, Mohd Ali
Pandiyan, Paulraj Murugesa , Prof. Dr.
Sazali, Yaacob, Prof. Dr.
Shahriman, Abu Bakar, Dr.
Feature space reduction in ethnically diverse Malaysian English accents classification
description Proceeding of the 7th International Conference on Intelligent Systems and Control, (ISCO) 2013 at Coimbatore, Tamilnadu, India on 4 January 2013 through 5 January 2013. Link to publisher's homepage at http://ezproxy.unimap.edu.my:2080/Xplore/dynhome.jsp
author2 yusnita082@ppinang.uitm.edu.my
author_facet yusnita082@ppinang.uitm.edu.my
Yusnita, Mohd Ali
Pandiyan, Paulraj Murugesa , Prof. Dr.
Sazali, Yaacob, Prof. Dr.
Shahriman, Abu Bakar, Dr.
format Working Paper
author Yusnita, Mohd Ali
Pandiyan, Paulraj Murugesa , Prof. Dr.
Sazali, Yaacob, Prof. Dr.
Shahriman, Abu Bakar, Dr.
author_sort Yusnita, Mohd Ali
title Feature space reduction in ethnically diverse Malaysian English accents classification
title_short Feature space reduction in ethnically diverse Malaysian English accents classification
title_full Feature space reduction in ethnically diverse Malaysian English accents classification
title_fullStr Feature space reduction in ethnically diverse Malaysian English accents classification
title_full_unstemmed Feature space reduction in ethnically diverse Malaysian English accents classification
title_sort feature space reduction in ethnically diverse malaysian english accents classification
publisher IEEE Conference Publications
publishDate 2014
url http://dspace.unimap.edu.my:80/dspace/handle/123456789/35444
_version_ 1643797800945713152
score 13.211869

Similar Items