The classification of actual pronunciation of Quranic alphabets for non-Arab speaker

Idris, Sulbaqiah and Ahmad, Salmiah and Embong, Abd Halim and Altalmas, Tareq, M. (2021) The classification of actual pronunciation of Quranic alphabets for non-Arab speaker. PERINTIS E-Journal, 11 (1). pp. 70-83. E-ISSN 2232-0725

PDF (Article) - Published Version Restricted to Registered users only Download (2MB) | Request a copy

Abstract

Each Quranic alphabet has its unique sounds produced by uttering the Arabic language at their point of articulation (Makharij) and their characteristics (Sifaat), which is called Tajweed. Much research has been done related to the Tajweed, but there are limited sources associated with the analysis of Quranic pronunciation of non-Arab speakers from signal processing perspective with respect to both Makhraj and Sifaat. Therefore, this research focus on the identification and classification of the actual pronunciation of the Quranic alphabets on the audio signal obtained from non-Arab speakers. In this research, the features were best identified by the combinations of four formant frequencies (f1, f2, f3, f4), and three power spectral density (psd1, psd2, psd3) extracted from the sukoon pronunciation of the alphabets’ audio data. All features were combined and classified using both Linear and Quadratic Discriminant Analysis (LDA and QDA) to represent the actual pronunciation of each alphabet for both Arab and Non-Arab speaker categories. The findings indicate that there are 25 alphabets were correctly classified more than 83% threshold value thus indicates the correct pronunciation, where the other three alphabets which are أ ضْ, أ غْ and أ فْ are falling under misclassified vector. Later, the Graphical User Interface (GUI) was developed using the training data of 25 alphabets to evaluate the percentage of accuracy (%) with the new audio dataset. The results show that the developed GUI has managed to record, analyze, and evaluate the pronunciation interactively.

Item Type:	Article (Journal)
Additional Information:	4113/93169
Uncontrolled Keywords:	Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), Formant Frequency, Power Spectral Density (PSD), Tajweed, Makhraj, Sifaat
Subjects:	T Technology > T Technology (General) > T173.5 Technology and Islam
Kulliyyahs/Centres/Divisions/Institutes (Can select more than one option. Press CONTROL button):	Kulliyyah of Engineering > Department of Mechanical Engineering Kulliyyah of Engineering
Depositing User:	Ir. Dr. Salmiah Ahmad
Date Deposited:	20 Oct 2021 15:16
Last Modified:	20 Oct 2021 15:16
URI:	http://irep.iium.edu.my/id/eprint/93169

Actions (login required)

View Item