Wavelet cesptral coefficients for isolated speech recognition
The study proposes an improved feature extraction method that is called Wavelet Cepstral Coefficients (WCC). In traditional cepstral analysis, the cepstrums are calculated with the use of the Discrete Fourier Transform (DFT). Owing to the fact that the DFT calculation assumes signal stationary betwe...
Saved in:
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
UAD and IAES
2013
|
Subjects: | |
Online Access: | http://irep.iium.edu.my/32110/1/Adam2013_Telkomnika_Wavelet_Cepstral_Coefficients_for_Isolated_Speech_Recognition.pdf http://irep.iium.edu.my/32110/ http://www.iaesjournal.com/online/index.php/TELKOMNIKA/article/view/2510 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.iium.irep.32110 |
---|---|
record_format |
dspace |
spelling |
my.iium.irep.321102013-10-02T03:47:30Z http://irep.iium.edu.my/32110/ Wavelet cesptral coefficients for isolated speech recognition Adam, Tarmizi Salam, Md Sah Gunawan, Teddy Surya TK Electrical engineering. Electronics Nuclear engineering The study proposes an improved feature extraction method that is called Wavelet Cepstral Coefficients (WCC). In traditional cepstral analysis, the cepstrums are calculated with the use of the Discrete Fourier Transform (DFT). Owing to the fact that the DFT calculation assumes signal stationary between frames which in practice is not quite true, the WCC replaces the DFT block in the traditional cepstrum calculation with the Discrete Wavelet Transform (DWT) hence producing the WCC. To evaluate the proposed WCC, speech recognition task of recognizing the 26 English alphabets were conducted. Comparisons with the traditional Mel-Frequency Cepstral Coefficients (MFCC) are done to further analyze the effectiveness of the WCCs. It is found that the WCCs showed some comparable results when compared to the MFCCs considering the WCCs small vector dimension when compared to the MFCCs. The best recognition was found from WCCs at level 5 of the DWT decomposition with a small difference of 1.19% and 3.21% when compared to the MFCCs for speaker independent and speaker dependent tasks respectively. UAD and IAES 2013-05 Article REM application/pdf en http://irep.iium.edu.my/32110/1/Adam2013_Telkomnika_Wavelet_Cepstral_Coefficients_for_Isolated_Speech_Recognition.pdf Adam, Tarmizi and Salam, Md Sah and Gunawan, Teddy Surya (2013) Wavelet cesptral coefficients for isolated speech recognition. TELKOMNIKA Indonesian Journal of Electrical Engineering, 11 (5). pp. 2731-2738. ISSN 2302-4046 http://www.iaesjournal.com/online/index.php/TELKOMNIKA/article/view/2510 DOI: 10.11591/telkomnika.v11i5.2510 |
institution |
Universiti Islam Antarabangsa Malaysia |
building |
IIUM Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
International Islamic University Malaysia |
content_source |
IIUM Repository (IREP) |
url_provider |
http://irep.iium.edu.my/ |
language |
English |
topic |
TK Electrical engineering. Electronics Nuclear engineering |
spellingShingle |
TK Electrical engineering. Electronics Nuclear engineering Adam, Tarmizi Salam, Md Sah Gunawan, Teddy Surya Wavelet cesptral coefficients for isolated speech recognition |
description |
The study proposes an improved feature extraction method that is called Wavelet Cepstral Coefficients (WCC). In traditional cepstral analysis, the cepstrums are calculated with the use of the Discrete Fourier Transform (DFT). Owing to the fact that the DFT calculation assumes signal stationary between frames which in practice is not quite true, the WCC replaces the DFT block in the traditional
cepstrum calculation with the Discrete Wavelet Transform (DWT) hence producing the WCC. To evaluate the proposed WCC, speech recognition task of recognizing the 26 English alphabets were conducted. Comparisons with the traditional Mel-Frequency Cepstral Coefficients (MFCC) are done to further analyze the effectiveness of the WCCs. It is found that the WCCs showed some comparable results when compared to the MFCCs considering the WCCs small vector dimension when compared to the MFCCs. The best recognition was found from WCCs at level 5 of the DWT decomposition with a small difference of 1.19% and 3.21% when compared to the MFCCs for speaker independent and speaker dependent tasks respectively. |
format |
Article |
author |
Adam, Tarmizi Salam, Md Sah Gunawan, Teddy Surya |
author_facet |
Adam, Tarmizi Salam, Md Sah Gunawan, Teddy Surya |
author_sort |
Adam, Tarmizi |
title |
Wavelet cesptral coefficients for isolated speech recognition |
title_short |
Wavelet cesptral coefficients for isolated speech recognition |
title_full |
Wavelet cesptral coefficients for isolated speech recognition |
title_fullStr |
Wavelet cesptral coefficients for isolated speech recognition |
title_full_unstemmed |
Wavelet cesptral coefficients for isolated speech recognition |
title_sort |
wavelet cesptral coefficients for isolated speech recognition |
publisher |
UAD and IAES |
publishDate |
2013 |
url |
http://irep.iium.edu.my/32110/1/Adam2013_Telkomnika_Wavelet_Cepstral_Coefficients_for_Isolated_Speech_Recognition.pdf http://irep.iium.edu.my/32110/ http://www.iaesjournal.com/online/index.php/TELKOMNIKA/article/view/2510 |
_version_ |
1643610153546678272 |
score |
13.160551 |