{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T15:44:05Z","timestamp":1778600645435,"version":"3.51.4"},"reference-count":82,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Interdisciplinary Research Center for Intelligent Secure Systems (IRC-ISS) at the King Fahd University of Petroleum and Minerals","award":["INSS2211"],"award-info":[{"award-number":["INSS2211"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3616335","type":"journal-article","created":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T17:40:01Z","timestamp":1759340401000},"page":"175047-175068","source":"Crossref","is-referenced-by-count":2,"title":["Mispronunciation Detection and Diagnosis for Young Arabic Learners Using Transfer Learning"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-0783-9005","authenticated-orcid":false,"given":"Taha","family":"Fanoush","sequence":"first","affiliation":[{"name":"Computer Science Department, University of Benghazi, Benghazi, Libya"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6760-3506","authenticated-orcid":false,"given":"Wasfi G.","family":"Al-Khatib","sequence":"additional","affiliation":[{"name":"Information and Computer Science Department, King Fahd University of Petroleum and Minerals, Dhahran, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7624-1491","authenticated-orcid":false,"given":"Mohammad","family":"Amro","sequence":"additional","affiliation":[{"name":"Information and Computer Science Department, King Fahd University of Petroleum and Minerals, Dhahran, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2642-9525","authenticated-orcid":false,"given":"Abdulkareem","family":"Alzahrani","sequence":"additional","affiliation":[{"name":"Interdisciplinary Research Center for Intelligent Secure Systems, King Fahd University of Petroleum and Minerals, Dhahran, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8205-666X","authenticated-orcid":false,"given":"Moustafa","family":"Elshafei","sequence":"additional","affiliation":[{"name":"Department of Communications and Information Engineering, Zewail City University of Science and Technology, 6th of October City, Egypt"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1558\/cj.35173"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/iccspa.2013.6487246"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.4018\/ijcallt.2020010105"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/app12010238"},{"key":"ref5","first-page":"27","article-title":"Validity of oral tasks testing in Arabic L2 teaching","volume":"18","author":"Hasan","year":"2017","journal-title":"Linguistica Communicatio"},{"key":"ref6","volume-title":"The 10 Most Spoken Languages in the World","author":"Lane","year":"2019"},{"key":"ref7","volume-title":"What Are the Most Spoken Languages in the World?","author":"Julian","year":"2020"},{"issue":"2","key":"ref8","first-page":"1","article-title":"Comparative performance of ensemble machine learning for Arabic cyberbullying and offensive language detection","volume":"58","author":"Khairy","year":"2024","journal-title":"Lang. Resources Eval."},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1093\/jis\/etad017"},{"key":"ref10","first-page":"281","article-title":"The use of modern standard Arabic and Arabic dialects in Oman for internal cohesion and external distinction","volume-title":"Modern Arabic Sociolinguistics","author":"AlMahrooqi","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/knowledge2030022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.jksuci.2023.101570"},{"key":"ref13","first-page":"37","article-title":"A novel minimal Arabic script for preparing databases and benchmarks for Arabic text recognition research","volume-title":"Proc. Int. conferences. Math. Comput. Sci. Eng. (WSEAS)","author":"Al-Muhtaseb"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ivtta.1998.727712"},{"key":"ref15","first-page":"1","article-title":"Word stress and vowel neutralization in modern standard Arabic","volume-title":"Proc. 2nd Int. Conf. Arabic Language Resour. Tools","author":"Halpern"},{"key":"ref16","article-title":"Transformers in speech processing: A survey","author":"Latif","year":"2023","journal-title":"arXiv:2303.11607"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1076\/call.15.5.441.13473"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3390\/app13116793"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-11039"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3390\/math10152727"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/access.2019.2912648"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/access.2023.3317236"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3390\/info14070413"},{"key":"ref24","first-page":"1","article-title":"A study on fine-tuning wav2vec2.0 model for the task of mispronunciation detection and diagnosis","volume-title":"Proc. INTERSPEECH","author":"Peng"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/taslpro.2025.3559344"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3390\/s20071809"},{"issue":"1","key":"ref27","doi-asserted-by":"crossref","first-page":"5","DOI":"10.2307\/522070","article-title":"On defining the phoneme","volume":"11","author":"Twaddell","year":"1935","journal-title":"Language"},{"issue":"1","key":"ref28","first-page":"936","article-title":"Classification of Arabic fricative consonants according to their places of articulation","volume":"12","author":"Elfahm","year":"2022","journal-title":"Int. J. Electr. Comput. Eng."},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.5121\/csit.2020.101812"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2023.109593"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/SLaTE.2013-21"},{"key":"ref32","first-page":"1","article-title":"An Arabic mispronunciation detection system by means of automatic speech recognition technology","volume-title":"Proc. ACIT","author":"Necibi"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3390\/electronics9060963"},{"key":"ref34","article-title":"QVoice: Arabic speech pronunciation learning application","author":"El Kheir","year":"2023","journal-title":"arXiv:2305.07445"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-02139-8"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1017\/s0267190508070098"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1093\/elt\/ccs025"},{"key":"ref38","volume-title":"eEnglish by Pronunciation Power","year":"2024"},{"key":"ref39","volume-title":"Tell Me More Language Learning Software","year":"2013"},{"key":"ref40","volume-title":"Duolingo Language Learning Platform","year":"2024"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1057\/978-1-137-47677-7_5"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-50729-9_48"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/access.2022.3212417"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.eij.2016.04.002"},{"key":"ref45","first-page":"242","article-title":"An efficient mispronunciation detection system using discriminative acoustic phonetic features for Arabic consonants","volume":"16","author":"Maqsood","year":"2019","journal-title":"Int. Arab J. Inf. Technol."},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-014-9248-2"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/2816839.2816866"},{"key":"ref48","article-title":"Goodness of pronunciation algorithm in the speech analysis and assessment for detecting errors in acoustic phonetics: An exploratory review","author":"Anzola","year":"2023","journal-title":"TechRxiv"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-931"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10245"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2023.109711"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-777"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2025.103249"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10887601"},{"key":"ref55","article-title":"Towards a unified benchmark for Arabic pronunciation assessment: Quranic recitation as case study","author":"El Kheir","year":"2025","journal-title":"arXiv:2506.07722"},{"key":"ref56","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020","journal-title":"arXiv:2006.11477"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/jstsp.2022.3188113"},{"key":"ref59","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref60","article-title":"Arabic speech emotion recognition employing Wav2vec2.0 and HuBERT based on BAVED dataset","author":"Mohamed","year":"2021","journal-title":"arXiv:2110.04425"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-78"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-60"},{"key":"ref63","volume-title":"Hugging Face: The AI Community Building the Future","year":"2023"},{"key":"ref64","volume-title":"Wav2vec2-XLSR-53","year":"2021"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2015.7178964"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-2371"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.iwslt-1.28"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-329"},{"key":"ref70","volume-title":"Wav2vec2-Large-XLSR-53-Arabic","author":"El-Geish","year":"2020"},{"key":"ref71","volume-title":"Fine-Tuned XLSR-53 Large Model for Speech Recognition in Arabic","author":"Grosman","year":"2021"},{"key":"ref72","article-title":"Modern standard Arabic phonetics for speech synthesis","author":"Halabi","year":"2016"},{"key":"ref73","first-page":"4211","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"Proc. LREC","author":"Ardila"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12081775"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2016.2621675"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-71429-0_3"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4020-6046-5_2"},{"issue":"4","key":"ref78","doi-asserted-by":"crossref","first-page":"67","DOI":"10.4018\/jitr.2009062905","article-title":"Arabic phonetic dictionaries for speech recognition","volume":"2","author":"Ali","year":"2009","journal-title":"J. Inf. Technol. Res."},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-00560-7_13"},{"key":"ref80","first-page":"1","volume-title":"The needleman-wunsch algorithm for sequence alignment","author":"Likic","year":"2008"},{"key":"ref81","article-title":"SpeechBrain: A general-purpose speech toolkit","author":"Ravanelli","year":"2021","journal-title":"arXiv:2106.04624"},{"key":"ref82","first-page":"120","article-title":"Syllable-based Arabic speech recognition using Wav2vec","volume":"2024","author":"Abdalaal","year":"2024","journal-title":"J. Comput. Linguistics Arabic Lang. Process."}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11186198.pdf?arnumber=11186198","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T05:35:41Z","timestamp":1760506541000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11186198\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":82,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3616335","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}