Malay speech recognition in normal and noise condition

Link to publisher's homepage at http://ieeexplore.ieee.org/

Saved in:
Bibliographic Details
Main Authors: Fook, C. Y., Hariharan, Muthusamy, Dr., Sazali, Yaacob, Prof. Dr., Abdul Hamid, Adom, Prof. Dr.
Other Authors: fook1987@gmail.com
Format: Working Paper
Language:English
Published: Institute of Electrical and Electronics Engineers (IEEE) 2013
Subjects:
Online Access:http://dspace.unimap.edu.my/xmlui/handle/123456789/26053
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.unimap-26053
record_format dspace
spelling my.unimap-260532017-11-29T04:28:27Z Malay speech recognition in normal and noise condition Fook, C. Y. Hariharan, Muthusamy, Dr. Sazali, Yaacob, Prof. Dr. Abdul Hamid, Adom, Prof. Dr. fook1987@gmail.com End-point detection Features extraction k-NN classifier Weighted Linear Predictive Cepstral Coefficient (WLPCC) Linear Predictive Cepstral Coefficients (LPCC) Linear Predictive Coding (LPC) Link to publisher's homepage at http://ieeexplore.ieee.org/ Automatic speech recognition (ASR) is an area of research which deals with the recognition of speech by machine in several conditions. ASR performs well under restricted conditions (quiet environment), but performance degrades in noisy environments. This paper presents a simple experiment by using famous feature extraction method (LPC, LPCC and WLPCC) and simple kNN classifier to investigate the sensitivity of Malay speech digits to noise by adding 5dB white Gaussian noise. There are four steps to design and develop the Malay speech digits recognition system. They are Digit syllable structure and Malay speech corpus, end-point detection processing, feature extraction and classification method. The highest average recognition rates for Malays digits recognition is 96.22% that the feature vectors were derived from LPCC. The objective of this paper is to shown the occurrence of noise during Malay speech recognition. 2013-06-25T05:15:25Z 2013-06-25T05:15:25Z 2012-03 Working Paper p. 409-412 978-146730961-5 http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6194759 http://hdl.handle.net/123456789/26053 en Proceedings of the 8th International Colloquium on Signal Processing and Its Applications (CSPA) 2012 Institute of Electrical and Electronics Engineers (IEEE)
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 End-point detection
Features extraction
k-NN classifier
Weighted Linear Predictive Cepstral Coefficient (WLPCC)
Linear Predictive Cepstral Coefficients (LPCC)
Linear Predictive Coding (LPC)
spellingShingle End-point detection
Features extraction
k-NN classifier
Weighted Linear Predictive Cepstral Coefficient (WLPCC)
Linear Predictive Cepstral Coefficients (LPCC)
Linear Predictive Coding (LPC)
Fook, C. Y.
Hariharan, Muthusamy, Dr.
Sazali, Yaacob, Prof. Dr.
Abdul Hamid, Adom, Prof. Dr.
Malay speech recognition in normal and noise condition
description Link to publisher's homepage at http://ieeexplore.ieee.org/
author2 fook1987@gmail.com
author_facet fook1987@gmail.com
Fook, C. Y.
Hariharan, Muthusamy, Dr.
Sazali, Yaacob, Prof. Dr.
Abdul Hamid, Adom, Prof. Dr.
format Working Paper
author Fook, C. Y.
Hariharan, Muthusamy, Dr.
Sazali, Yaacob, Prof. Dr.
Abdul Hamid, Adom, Prof. Dr.
author_sort Fook, C. Y.
title Malay speech recognition in normal and noise condition
title_short Malay speech recognition in normal and noise condition
title_full Malay speech recognition in normal and noise condition
title_fullStr Malay speech recognition in normal and noise condition
title_full_unstemmed Malay speech recognition in normal and noise condition
title_sort malay speech recognition in normal and noise condition
publisher Institute of Electrical and Electronics Engineers (IEEE)
publishDate 2013
url http://dspace.unimap.edu.my/xmlui/handle/123456789/26053
_version_ 1643802733565706240
score 13.214268