Cover Image

Neural network based detection of voice disorders using energy spectrum and equal-loudness contours

Organized by Universiti Teknologi MARA (UiTM) Shah Alam, 7th - 9th March 2008 at Royale Bintang Hotel, Kuala Lumpur, Malaysia.

Saved in:
Bibliographic Details
Main Authors: Murugesa Pandian, Paulraj, Prof. Madya Dr., Sazali, Yaacob, Prof. Dr., Sivanandam, S. N., Muthusamy, Hariharan, Dr.
Other Authors: paul@unimap.edu.my
Format: Working Paper
Language:English
Published: Universiti Teknologi MARA (UiTM) 2011
Subjects:
Band energy spectrum
Equal-loudness contours
Elman recurrent network
Online Access:http://dspace.unimap.edu.my/xmlui/handle/123456789/15126
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.unimap-15126
record_format dspace
spelling my.unimap-151262013-11-20T03:28:32Z Neural network based detection of voice disorders using energy spectrum and equal-loudness contours Murugesa Pandian, Paulraj, Prof. Madya Dr. Sazali, Yaacob, Prof. Dr. Sivanandam, S. N. Muthusamy, Hariharan, Dr. paul@unimap.edu.my Band energy spectrum Equal-loudness contours Elman recurrent network Organized by Universiti Teknologi MARA (UiTM) Shah Alam, 7th - 9th March 2008 at Royale Bintang Hotel, Kuala Lumpur, Malaysia. Impairment of vocal function can have a major impact on the quality of life, severely limiting communication at work and affecting all social aspect of daily life. In the recent years, voice disease are increasing dramatically due to unhealthy social habits and voice abuse. Acoustic analysis is a non-invasive technique to detect and diagnose the voice disorders. In this paper, a simple feature extraction method based on band energy spectrum and weighing factor of its center frequency derived from Equal-loudness contours is proposed. A simple Elman recurrent network models is developed for testing the proposed features. The simulation results indicate that the proposed algorithm can be distinguish the voice as pathological or non-pathological voice and provides the mean classification accuracy of above 90%. The proposed method has been potential for diagnosing the voice disorders. 2011-10-28T08:01:56Z 2011-10-28T08:01:56Z 2008-03-07 Working Paper p. 105-109 978-983-42747-9-5 http://hdl.handle.net/123456789/15126 en Proceedings 4th International Colloquium in Signal Processing and its Application 2008 (CSPA 2008) Universiti Teknologi MARA (UiTM) Faculti of Electrical Engineering
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 Band energy spectrum
Equal-loudness contours
Elman recurrent network
spellingShingle Band energy spectrum
Equal-loudness contours
Elman recurrent network
Murugesa Pandian, Paulraj, Prof. Madya Dr.
Sazali, Yaacob, Prof. Dr.
Sivanandam, S. N.
Muthusamy, Hariharan, Dr.
Neural network based detection of voice disorders using energy spectrum and equal-loudness contours
description Organized by Universiti Teknologi MARA (UiTM) Shah Alam, 7th - 9th March 2008 at Royale Bintang Hotel, Kuala Lumpur, Malaysia.
author2 paul@unimap.edu.my
author_facet paul@unimap.edu.my
Murugesa Pandian, Paulraj, Prof. Madya Dr.
Sazali, Yaacob, Prof. Dr.
Sivanandam, S. N.
Muthusamy, Hariharan, Dr.
format Working Paper
author Murugesa Pandian, Paulraj, Prof. Madya Dr.
Sazali, Yaacob, Prof. Dr.
Sivanandam, S. N.
Muthusamy, Hariharan, Dr.
author_sort Murugesa Pandian, Paulraj, Prof. Madya Dr.
title Neural network based detection of voice disorders using energy spectrum and equal-loudness contours
title_short Neural network based detection of voice disorders using energy spectrum and equal-loudness contours
title_full Neural network based detection of voice disorders using energy spectrum and equal-loudness contours
title_fullStr Neural network based detection of voice disorders using energy spectrum and equal-loudness contours
title_full_unstemmed Neural network based detection of voice disorders using energy spectrum and equal-loudness contours
title_sort neural network based detection of voice disorders using energy spectrum and equal-loudness contours
publisher Universiti Teknologi MARA (UiTM)
publishDate 2011
url http://dspace.unimap.edu.my/xmlui/handle/123456789/15126
_version_ 1643790616576917504
score 13.222552

Similar Items