BUILDING A SCALABLE DATASET FOR FRIDAY SERMONS OF AUDIO AND TEXT (SAT)
DOI:
https://doi.org/10.15588/1607-3274-2024-2-10Keywords:
Friday Sermons, Khutbah, Arabic speech recognition, Audio and text dataset, Machine translationAbstract
Context. Today, collecting and creating datasets in various sectors has become increasingly prevalent. Despite this widespread data production, a gap still exists in specialized domains, particularly in the Islamic Friday Sermons (IFS) domain. It is rich with theological, cultural, and linguistic studies that are relevant to Arab and Muslim countries, not just religious discourses.
Objective. The goal of this research is to bridge this lack by introducing a comprehensive Sermon Audio and Text (SAT) dataset with its metadata. It seeks to provide an extensive resource for religion, linguistics, and sociology studies. Moreover, it aims to support advancements in Artificial Intelligence (AI), such as Natural Language Processing and Speech Recognition technologies.
Method. The development of the SAT dataset was conducted through four distinct phases: planning, creation and processing, measurement, and deployment. The SAT dataset contains a collection of 21,253 audio and corresponding transcript files that were successfully created. Advanced audio processing techniques were used to enhance speech recognition and provide a dataset that is suitable for wide-range use.
Results. The fine-tuned SAT dataset achieved a 5.13% Word Error Rate (WER), indicating a significant improvement in accuracy compared to the baseline model of Microsoft Azure Speech. This achievement indicates the dataset’s quality and the employed processing techniques’ effectiveness. In light of this, a novel Closest Matching Phrase (CMP) algorithm was developed to enhance the high confidence of equivalent speech-to-text by adjusting lower ratio phrases.
Conclusions. This research contributes significant impact and insight into different studies, such as religion, linguistics, and sociology, providing invaluable insights and resources. In addition, it is demonstrating its potential in Artificial Intelligence (AI) and supporting its applications. In future research, we will focus on enriching this dataset expansion by adding a sign language video corpus, using advanced alignment techniques. It will support ongoing Machine Translation (MT) developments for a broader understanding of Islamic Friday Sermons across different linguistics and cultures.
References
Chen H., Xie W., Vedaldi A., Zisserman A. VGGSound: A Large-Scale Audio-Visual Dataset, 2020.
Cohn N., Cardoso B., Klomberg B., Hacımusaoğlu I. The Visual Language Research Corpus (VLRC), An Annotated Corpus of Comics from Asia, Europe, and the United States. Lang Resources & Evaluation, 2023, DOI:10.1007/s10579023-09673-0.
Mounsef J., Hasib M., Raza A. Building an Arabic Dialectal Diagnostic Dataset for Healthcare, IJACSA, 2022, No.13, DOI:10.14569/IJACSA.2022.01307100.
Alfraidi T., Abdeen M. A. R., Yatimi A., Alluhaibi R., AlThubaity A. The Saudi Novel Corpus, Design and Compilation. Applied Sciences, 2022, No. 12, P. 6648, DOI:10.3390/app12136648.
Abdelhay M., Mohammed A., Hefny H.A. Deep Learning for Arabic Healthcare, MedicalBot. Soc. Netw. Anal. Min. 2023, No. 13, P. 71. DOI:10.1007/s13278-023-01077-w.
Abbas S., Al-Barhamtoshy H., Alotaibi F. Towards an Arabic Sign Language (ArSL) Corpus for Deaf Drivers. PeerJ Comput. Sci., 2021, No. 7, e741, DOI:10.7717/peerj-cs.741.
Asyafie M. A., Harun M., Shapiai M. I., Khalid P. I. Identification of Phoneme and Its Distribution of Malay Language Derived from Friday Sermon Transcripts. In Proceedings of the 2014 IEEE Student Conference on Research and Development, 2014, December, pp. 1–6.
Saddhono K., Rakhmawati A. Sociolinguistic Studies of Friday Sermon Using Javanese as an Effort to Preserves Indigenous Language in Java Island, In Proceedings of the 2nd International Conference on Sociology Education, SCITEPRESS – Science and Technology Publications. Bandung, Indonesia, 2017, pp. 829–833.
Alkhawaldeh A. A. Deixis in English Islamic Friday Sermons, A Pragma-Discourse Analysis. Studies in English Language and Education, 2022, No. 9, pp. 418–437, DOI:10.24815/siele.v9i1.21415.
Aksoy O. Preaching to Social Media: Turkey’s Friday Khutbas and Their Effects on Twitter, SocArXiv, 2021, May, No. 12.
Usman A. H., Iskandar A. Analysis of Friday Sermon Duration, Intellectual Reflection of Classical and Contemporary Islamic Scholars. Journal of Religious & Theological Information, 2022, No. 21, pp. 68–81, doi:10.1080/10477845.2021.1928349.
Gürlesin Ö. F. Understanding the Political and Religious Implications of Turkish Civil Religion in The Netherlands: A Critical Discourse Analysis of ISN Friday Sermons. Religions, 2023, No. 14, P. 990, DOI:10.3390/rel14080990.
Nor M.R.M. Multicultural Discourse from the Minbar: A Study on Khutbah Texts Prepared by Jakim Malaysia. In; Fukami N., Sato S., Eds.; JSPS Asia and Africa Science Platform Program. Organization of Islamic Area Studies, Waseda University. Tokyo, Japan, 2012, pp. 55–62 ISBN 978-4-904039-52-6.
Ismail Ali Mohammed Art of Oratory and Skills of Orator. Researches in the preparation of preacher preacher. Fifth edition, Dar Alkalema, Cairo-Egypt, 2016.
Mahmood I., Kasim Z. Metadiscourse Resources across Themes of Islamic Friday Sermon, 2021, No. 21, pp. 45–61, DOI: 10.17576/gema-2021-2101-01-03.
Sukarno S., Salikin H. The The Generic Structure Potential of Friday Sermons in Jember, International Journal of Linguistics and Translation Studies. Indonesia, 2022, No. 3, pp. 56–73. DOI:10.36892/ijlts.v3i1.207.
Mohammed Saleh Al-Hamzi A., Sumarlam, Santosa R., Jamal M. A Pragmatic and Discourse Study of Common Deixis Used by Yemeni-Arab Preachers in Friday Islamic Sermons at Yemeni Mosques, Cogent Arts & Humanities 2023, No. 10, P. 2177241, doi:10.1080/23311983.2023.2177241.
Mahmood I., Kasim Z. Interpersonal Metadiscursive Features in Contemporary Islamic Friday Sermon, 3L: Language, Linguistics, Literature, 2019, No. 25, pp. 85–99. DOI:10.17576/3L-2019-2501-06.
Wardoyo C. Directive Speech Acts Performed in Khutbah (Islamic Friday Sermon), 2017.
Fahruroji F., Rakhmat M., Shodiq M. The Understanding of Friday Prayer Attendees (Mustamik) Towards Friday Sermon Discourse, 2017, P. 779.
Carol S., Hofheinz L. A Content Analysis of the Friday Sermons of the Turkish-Islamic Union for Religious Affairs in Germany (DİTİB), Politics and Religion, 2022, DOI:10.1017/S1755048321000353.
Jafilus M., Asha’ari M. F., Rasit R. Thematic Analysis of the Content of the Friday Sermon in Negeri Sembilan, IJARBSS, 2021, No. 11, pp. 84–98, DOI:10.6007/IJARBSS/v11-i6/10087.
Numeracy, Maths and Statistics – Academic Skills Kit Available online: https://www.ncl.ac.uk/webtemplate/askassets/external/maths-resources/statistics/regression-andcorrelation/strength-of-correlation.html (accessed on 19 February 2024).
Moslem S., Ghorbanzadeh O., Blaschke T., Duleba S. Analysing Stakeholder Consensus for a Sustainable Transport Development Decision by the Fuzzy AHP and Interval AHP, Sustainability, 2019, No. 11, P. 3271, DOI:10.3390/su11123271.
Encyclopedia of Statistics in Behavioral Science; Everitt B., Howell D. C., Eds. John Wiley & Sons. Hoboken, N. J, 2005, ISBN 978-0-470-86080-9.
MNARAT AL-HARAMAIN Available online: https://manaratalharamain.gov.sa/home (accessed on 25 June 2023).
Khutaba Forum Available online: https://khutabaa.com/en (accessed on 25 June 2023).
Beatman A. Improve Speech-to-Text Accuracy with Azure Custom Speech | Azure Blog | Microsoft Azure Available online: https://azure.microsoft.com/en-us/blog/improvespeechtotext-accuracy-with-azure-custom-speech/ (accessed on 23 September 2023).
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 A. A. Samah, H. A. Dimah, M. A. Hassanin
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Creative Commons Licensing Notifications in the Copyright Notices
The journal allows the authors to hold the copyright without restrictions and to retain publishing rights without restrictions.
The journal allows readers to read, download, copy, distribute, print, search, or link to the full texts of its articles.
The journal allows to reuse and remixing of its content, in accordance with a Creative Commons license СС BY -SA.
Authors who publish with this journal agree to the following terms:
-
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License CC BY-SA that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
-
Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
-
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
