Beta
310085

CNN for speech recognition case study: Recitation Rules of the holy Quran

Article

Last updated: 28 Dec 2024

Subjects

-

Tags

Mechatronics Engineering

Abstract

This work focused on applying the Convolutional Neural Networks (CNN) to recognize one recitation rule of the Holy Quran, the Qalqala recitation rule which is applied to letters (Ba/Dal/Jem/Qaf/Ta) of the Arabic Alphabet and it implies vibration of these letters when there is absence of vowels on them with sukun. The feature extraction technique used in the suggested system was the Mel Frequency Cepstral Coefficients (MFCC) its output was pre-processed then fed to the CNN as input to start the recognition process. Recognition process consists of two stages, the first stage was assigned with letter identification and it achieved 92% accuracy, the second stage was responsible of recognizing whether or not the identified letter is in Qalqalah status, it scored 99% for Baa, 93% for Daal, 95% for Jeem, 92% for Qaaf and 83% for Taa. The above mentioned Alphabet with sukun were used as the main dataset and they were annotated out of continuous audio signals for professional reader Ayman Swayed, each sample represent one of the Qalqalah letters with length of 300ms.

DOI

10.21608/msaeng.2023.225120.1335

Keywords

speech recognition, Convolutional Neural Networks CNN, Tajweed Rules, Qalqalah, Mel Frequency Cepstral Coefficients MFCC

Authors

First Name

Dahlia

Last Name

Omran

MiddleName

Mohammad

Affiliation

Systems and Biomedical Engineering Faculty of Engineering, Cairo university Giza, Egypt

Email

dmoran@msa.edu.eg

City

Cairo

Orcid

-

First Name

Ahmed

Last Name

Kandil

MiddleName

Hisham

Affiliation

Systems and Biomedical Engineering Faculty of Engineering, Cairo university Giza, Egypt

Email

ahkandil@eng1.cu.edu.eg

City

Cairo

Orcid

-

First Name

Ahmed

Last Name

ElBialy

MiddleName

-

Affiliation

Systems and Biomedical Engineering Faculty of Engineering, Cairo university Giza, Egypt

Email

abialy_86@yahoo.com

City

Cairo

Orcid

-

First Name

Sherif

Last Name

Samy

MiddleName

-

Affiliation

Systems and Biomedical Engineering Faculty of Engineering, Cairo university Giza, Egypt

Email

shsamy@eng1.cu.edu.eg

City

Cairo

Orcid

-

First Name

Sahar

Last Name

fawzy

MiddleName

-

Affiliation

Information Technology & Computer Science ,Nile university Giza, Egypt

Email

sfawzi@nu.edu.eg

City

Cairo

Orcid

-

Volume

2

Article Issue

4

Related Issue

44144

Issue Date

2023-12-01

Receive Date

2023-07-25

Publish Date

2023-12-01

Page Start

1

Page End

12

Print ISSN

2812-5339

Online ISSN

2812-4928

Link

https://msaeng.journals.ekb.eg/article_310085.html

Detail API

https://msaeng.journals.ekb.eg/service?article_code=310085

Order

1

Type

Original Article

Type Code

2,183

Publication Type

Journal

Publication Title

MSA Engineering Journal

Publication Link

https://msaeng.journals.ekb.eg/

MainTitle

CNN for speech recognition case study: Recitation Rules of the holy Quran

Details

Type

Article

Created At

28 Dec 2024