|
" Neural Networks-Based Automatic Audio Classification for Al-Quran Chapters "
Wael Radwan
Yang, Yin
| Document Type
|
:
|
Latin Dissertation
|
| Language of Document
|
:
|
English
|
| Record Number
|
:
|
805177
|
| Doc. No
|
:
|
TL50029
|
| Call number
|
:
|
2234775422; 13858706
|
| Main Entry
|
:
|
Viswanathan, Arun A.
|
| Title & Author
|
:
|
Neural Networks-Based Automatic Audio Classification for Al-Quran Chapters\ Wael RadwanYang, Yin
|
| College
|
:
|
Hamad Bin Khalifa University (Qatar)
|
| Date
|
:
|
2018
|
| Degree
|
:
|
M.S.
|
| field of study
|
:
|
Science and Engineering
|
| student score
|
:
|
2018
|
| Page No
|
:
|
70
|
| Note
|
:
|
Committee members: Abdallah, Mohamed; Al Fagih, Luluwah; Al Thani, Dena A.
|
| Note
|
:
|
Place of publication: United States, Ann Arbor; ISBN=978-1-392-18757-9
|
| Abstract
|
:
|
Al-Quran Audio classification is one example of content-based analysis of audio signals. This study aims to design a neural network that is able to classify Al-Quran audio files to the correct chapter <b>[special characters omitted]</b> and this requires implementing state of the art Convolutional Neural Network (CNN) to train Al-Quran Dataset and predict the correct chapter (سورة ). In order to achieve this aim, a critical evaluation of the current state of the automatic based reciting classification of Al-Quran was conducted, and the principles, assumptions and methods at the field were used to present a prototype based on this evaluation. Special focus is placed upon creating a suitable robust Quranic dataset and on discovering the features of that dataset that make it possible for an automated recognition of Al-Quran chapters and recitation. In addition, it sets out principles that should be kept in mind when designing Al-Quran reciting recognition and learning systems, and a prototype based on these features is presented. The thesis provides a framework for the auditory classification of Al-Quran chapters, as the final results shows that the use of a newly created IQRA-15 dataset and CNN as a model architecture produced in excess of 90% accuracy on unseen data. This is a proof of concept that deep learning can achieve good results when applied to Al-Quran. This knowledge can be used to design an AI based system for self-correcting Al-Quran recitation for Arabs and non-native Arabic speakers.
|
| Subject
|
:
|
Computer science
|
| Descriptor
|
:
|
Applied sciences;Al-quran audio classification;Al-quran dataset;Deep learning
|
| Added Entry
|
:
|
Yang, Yin
|
| Added Entry
|
:
|
Science and EngineeringHamad Bin Khalifa University (Qatar)
|
| |