Feature extraction using spectral centroid and mel frequency cepstral coefficient for Quranic accent automatic identification

This paper presents the process of Quranic Accent Automatic Identification. Recent feature extraction technique that is used for Quranic verse rule identification/Tajweed include Mel Frequency Cepstral Coefficients (MFCC) which prone to additive noise and may reduce the classification result. Theref...

Full description

Bibliographic Details
Main Authors: Kamarudin, Noraziahtulhidayu, Syed Mohamed, Syed Abdul Rahman Al-Haddad, Hashim, Shaiful Jahari, Nematollahi, Mohammad Ali, Hassan, Abd Rauf
Format: Conference or Workshop Item
Language:English
Published: IEEE 2014
Online Access:http://psasir.upm.edu.my/id/eprint/68279/
http://psasir.upm.edu.my/id/eprint/68279/1/Feature%20extraction%20using%20spectral%20centroid%20and%20mel%20frequency%20cepstral%20coefficient%20for%20Quranic%20accent%20automatic%20identification.pdf
_version_ 1848856082004312064
author Kamarudin, Noraziahtulhidayu
Syed Mohamed, Syed Abdul Rahman Al-Haddad
Hashim, Shaiful Jahari
Nematollahi, Mohammad Ali
Hassan, Abd Rauf
author_facet Kamarudin, Noraziahtulhidayu
Syed Mohamed, Syed Abdul Rahman Al-Haddad
Hashim, Shaiful Jahari
Nematollahi, Mohammad Ali
Hassan, Abd Rauf
author_sort Kamarudin, Noraziahtulhidayu
building UPM Institutional Repository
collection Online Access
description This paper presents the process of Quranic Accent Automatic Identification. Recent feature extraction technique that is used for Quranic verse rule identification/Tajweed include Mel Frequency Cepstral Coefficients (MFCC) which prone to additive noise and may reduce the classification result. Therefore, to improve the performance of MFCC with addition of Spectral Centroid features and is proposed for used in feature extraction of Quranic accents. Through implementing the Spectral Centroid Feature, it complements in improving the accuracy result of identifying the Quranic accents. The pattern classification algorithm here used the dimensional reduced technique from Probabilistic Principal Component Analysis (PPCA) on the features and Gaussian Mixture Model, in purpose to model the effectiveness of both combination of feature extraction. The accuracy of automatic identification for such Quranic Accents are found increasing from 96.9% to 100% with the application of SCF.
first_indexed 2025-11-15T11:36:00Z
format Conference or Workshop Item
id upm-68279
institution Universiti Putra Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T11:36:00Z
publishDate 2014
publisher IEEE
recordtype eprints
repository_type Digital Repository
spelling upm-682792019-05-10T08:29:30Z http://psasir.upm.edu.my/id/eprint/68279/ Feature extraction using spectral centroid and mel frequency cepstral coefficient for Quranic accent automatic identification Kamarudin, Noraziahtulhidayu Syed Mohamed, Syed Abdul Rahman Al-Haddad Hashim, Shaiful Jahari Nematollahi, Mohammad Ali Hassan, Abd Rauf This paper presents the process of Quranic Accent Automatic Identification. Recent feature extraction technique that is used for Quranic verse rule identification/Tajweed include Mel Frequency Cepstral Coefficients (MFCC) which prone to additive noise and may reduce the classification result. Therefore, to improve the performance of MFCC with addition of Spectral Centroid features and is proposed for used in feature extraction of Quranic accents. Through implementing the Spectral Centroid Feature, it complements in improving the accuracy result of identifying the Quranic accents. The pattern classification algorithm here used the dimensional reduced technique from Probabilistic Principal Component Analysis (PPCA) on the features and Gaussian Mixture Model, in purpose to model the effectiveness of both combination of feature extraction. The accuracy of automatic identification for such Quranic Accents are found increasing from 96.9% to 100% with the application of SCF. IEEE 2014 Conference or Workshop Item PeerReviewed text en http://psasir.upm.edu.my/id/eprint/68279/1/Feature%20extraction%20using%20spectral%20centroid%20and%20mel%20frequency%20cepstral%20coefficient%20for%20Quranic%20accent%20automatic%20identification.pdf Kamarudin, Noraziahtulhidayu and Syed Mohamed, Syed Abdul Rahman Al-Haddad and Hashim, Shaiful Jahari and Nematollahi, Mohammad Ali and Hassan, Abd Rauf (2014) Feature extraction using spectral centroid and mel frequency cepstral coefficient for Quranic accent automatic identification. In: 2014 IEEE Student Conference on Research and Development (SCOReD), 16-17 Dec. 2014, Penang, Malaysia. . 10.1109/SCORED.2014.7072945
spellingShingle Kamarudin, Noraziahtulhidayu
Syed Mohamed, Syed Abdul Rahman Al-Haddad
Hashim, Shaiful Jahari
Nematollahi, Mohammad Ali
Hassan, Abd Rauf
Feature extraction using spectral centroid and mel frequency cepstral coefficient for Quranic accent automatic identification
title Feature extraction using spectral centroid and mel frequency cepstral coefficient for Quranic accent automatic identification
title_full Feature extraction using spectral centroid and mel frequency cepstral coefficient for Quranic accent automatic identification
title_fullStr Feature extraction using spectral centroid and mel frequency cepstral coefficient for Quranic accent automatic identification
title_full_unstemmed Feature extraction using spectral centroid and mel frequency cepstral coefficient for Quranic accent automatic identification
title_short Feature extraction using spectral centroid and mel frequency cepstral coefficient for Quranic accent automatic identification
title_sort feature extraction using spectral centroid and mel frequency cepstral coefficient for quranic accent automatic identification
url http://psasir.upm.edu.my/id/eprint/68279/
http://psasir.upm.edu.my/id/eprint/68279/
http://psasir.upm.edu.my/id/eprint/68279/1/Feature%20extraction%20using%20spectral%20centroid%20and%20mel%20frequency%20cepstral%20coefficient%20for%20Quranic%20accent%20automatic%20identification.pdf