{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T15:56:48Z","timestamp":1783526208484,"version":"3.55.0"},"reference-count":79,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,1,6]],"date-time":"2025-01-06T00:00:00Z","timestamp":1736121600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,1,6]],"date-time":"2025-01-06T00:00:00Z","timestamp":1736121600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Discov Computing"],"DOI":"10.1007\/s10791-024-09489-8","type":"journal-article","created":{"date-parts":[[2025,1,6]],"date-time":"2025-01-06T11:49:47Z","timestamp":1736164187000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Improving mispronunciation detection and diagnosis for non- native learners of the Arabic language"],"prefix":"10.1007","volume":"28","author":[{"given":"Norah","family":"Alrashoudi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hend","family":"Al-Khalifa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yousef","family":"Alotaibi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,1,6]]},"reference":[{"key":"9489_CR1","unstructured":"\u201cWorld Arabic Language Day-UNESCO Digital Library.\u201d Accessed: Mar. 29, 2022. [Online]. Available: https:\/\/unesdoc.unesco.org\/ark:\/48223\/pf0000217912."},{"issue":"2\u20133","key":"9489_CR2","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1016\/S0167-6393(99)00044-8","volume":"30","author":"SM Witt","year":"2000","unstructured":"Witt SM, Young SJ. Phone-level pronunciation scoring and assessment for interactive language learning. Speech Commun. 2000;30(2\u20133):95\u2013108. https:\/\/doi.org\/10.1016\/S0167-6393(99)00044-8.","journal-title":"Speech Commun"},{"key":"9489_CR3","unstructured":"Fu K, Lin J, Ke D, Xie Y, Zhang J, Lin B. A Full Text-Dependent End to End Mispronunciation Detection and Diagnosis with Easy Data Augmentation Techniques. ArXiv210408428 Cs, Apr. 2021, Accessed: Mar. 28, 2022. [Online]. Available: http:\/\/arxiv.org\/abs\/2104.08428."},{"key":"9489_CR4","doi-asserted-by":"publisher","first-page":"45","DOI":"10.21437\/SLaTE.2009-12","volume":"2009","author":"AM Harrison","year":"2009","unstructured":"Harrison AM, Lo W, Qian X, Meng H. Implementation of an extended recognition network for mispronunciation detection and diagnosis in computer-assisted pronunciation training. SLaTE Conf. 2009;2009:45\u20138.","journal-title":"SLaTE Conf"},{"key":"9489_CR5","unstructured":"Yan B-C, Chen B. End-to-End Mispronunciation Detection and Diagnosis From Raw Waveforms. ArXiv210303023 Cs Eess, Jun. 2021, Accessed: Jan. 15, 2022. [Online]. Available: http:\/\/arxiv.org\/abs\/2103.03023."},{"key":"9489_CR6","doi-asserted-by":"publisher","unstructured":"Leung W-K, Liu X, Meng H. CNN-RNN-CTC Based End-to-end Mispronunciation Detection and Diagnosis. In: ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, United Kingdom: IEEE, 2019; pp. 8132\u20138136. https:\/\/doi.org\/10.1109\/ICASSP.2019.8682654.","DOI":"10.1109\/ICASSP.2019.8682654"},{"key":"9489_CR7","doi-asserted-by":"publisher","unstructured":"Yan B-C, Wu M-C, Hung H-T, Chen B. An End-to-End Mispronunciation Detection System for L2 English Speech Leveraging Novel Anti-Phone Modeling. In: Interspeech 2020, ISCA, 2020; pp. 3032\u20133036. https:\/\/doi.org\/10.21437\/Interspeech.2020-1616.","DOI":"10.21437\/Interspeech.2020-1616"},{"key":"9489_CR8","doi-asserted-by":"publisher","unstructured":"Wu M, Li K, Leung W-K, Meng H. Transformer Based End-to-End Mispronunciation Detection and Diagnosis. In: Interspeech 2021, ISCA, 2021, pp. 3954\u20133958. https:\/\/doi.org\/10.21437\/Interspeech.2021-1467.","DOI":"10.21437\/Interspeech.2021-1467"},{"key":"9489_CR9","unstructured":"Vaswani A et al. Attention is All you Need. In: Advances in Neural Information Processing Systems, Curran Associates, Inc., 2017. Accessed: Mar. 27, 2022. [Online]. Available: https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html."},{"key":"9489_CR10","doi-asserted-by":"crossref","unstructured":"Schneider S, Baevski A, Collobert R, Auli M. wav2vec: Unsupervised Pre-training for Speech Recognition. ArXiv190405862 Cs, 2019, Accessed: Apr. 06, 2022. [Online]. Available: http:\/\/arxiv.org\/abs\/1904.05862.","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"9489_CR11","unstructured":"Baevski A, Zhou Y, Mohamed A, Auli M. wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations. In: Advances in Neural Information Processing Systems, Curran Associates, Inc., 2020, pp. 12449\u201312460. Accessed: Apr. 06, 2022. [Online]. Available: https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/92d1e1eb1cd6f9fba3227870bb6d7f07-Abstract.html."},{"key":"9489_CR12","doi-asserted-by":"publisher","first-page":"3451","DOI":"10.1109\/TASLP.2021.3122291","volume":"29","author":"W-N Hsu","year":"2021","unstructured":"Hsu W-N, Bolte B, Tsai Y-HH, Lakhotia K, Salakhutdinov R, Mohamed A. HuBERT: self-supervised speech representation learning by masked prediction of hidden units. IEEEACM Trans Audio Speech Lang Process. 2021;29:3451\u201360. https:\/\/doi.org\/10.1109\/TASLP.2021.3122291.","journal-title":"IEEEACM Trans Audio Speech Lang Process"},{"key":"9489_CR13","unstructured":"Radford A, Kim JW, Xu T, Brockman G, McLeavey C, Sutskever I. Robust Speech Recognition via Large-Scale Weak Supervision. 2022, arXiv: arXiv:2212.04356. Accessed: Nov. 05, 2023. [Online]. Available: http:\/\/arxiv.org\/abs\/2212.04356."},{"issue":"1","key":"9489_CR14","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1109\/TASLP.2016.2621675","volume":"25","author":"K Li","year":"2017","unstructured":"Li K, Qian X, Meng H. Mispronunciation detection and diagnosis in L2 english speech using multidistribution deep neural networks. IEEEACM Trans Audio Speech Lang Process. 2017;25(1):193\u2013207. https:\/\/doi.org\/10.1109\/TASLP.2016.2621675.","journal-title":"IEEEACM Trans Audio Speech Lang Process"},{"key":"9489_CR15","first-page":"2009","volume":"1715\u20131718","author":"H Meng","year":"2009","unstructured":"Meng H, Tseng C, Kondo M, Harrison A, Viscelgia T. Studying L2 suprasegmental features in Asian Englishes: a position paper. Interspeech. 2009;1715\u20131718:2009.","journal-title":"Interspeech"},{"key":"9489_CR16","doi-asserted-by":"publisher","unstructured":"Tamburini F. Prosodic prominence detection in speech. In: Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings., Paris, France: IEEE, 2003, pp. 385\u2013388 1. https:\/\/doi.org\/10.1109\/ISSPA.2003.1224721.","DOI":"10.1109\/ISSPA.2003.1224721"},{"key":"9489_CR17","doi-asserted-by":"publisher","unstructured":"Li K, Zhang S, Li M, Lo W-K, Meng H. Prominence model for prosodic features in automatic lexical stress and pitch accent detection. In: Interspeech 2011, ISCA, 2011, pp. 2009\u20132012. https:\/\/doi.org\/10.21437\/Interspeech.2011-528.","DOI":"10.21437\/Interspeech.2011-528"},{"key":"9489_CR18","doi-asserted-by":"crossref","unstructured":"Imoto K, Tsubota Y, Raux A, Kawahara T, Dantsuji M. Modeling and automatic detection of English sentence stress for computer-assisted English prosody learning system. In: Interspeech, interspeech, 2002.","DOI":"10.21437\/ICSLP.2002-244"},{"key":"9489_CR19","doi-asserted-by":"publisher","unstructured":"Li K, Zhang S, Li M, Lo W-K, Meng H. Detection of intonation in L2 English speech of native Mandarin learners. In: 2010 7th International Symposium on Chinese Spoken Language Processing, 2010, pp. 69\u201374. https:\/\/doi.org\/10.1109\/ISCSLP.2010.5684846.","DOI":"10.1109\/ISCSLP.2010.5684846"},{"key":"9489_CR20","unstructured":"Lo T-H, Sung Y-T, Chen B. Improving End-To-End Modeling for Mispronunciation Detection with Effective Augmentation Mechanisms. In: 2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), 2021, pp. 1049\u20131055. Accessed: Oct. 11, 2024. [Online]. Available: https:\/\/ieeexplore.ieee.org\/abstract\/document\/9689243."},{"key":"9489_CR21","doi-asserted-by":"publisher","unstructured":"Bengio Y, Frasconi P, Simard P. The problem of learning long-term dependencies in recurrent networks. In: IEEE International Conference on Neural Networks, 1993, pp. 1183\u20131188 3. https:\/\/doi.org\/10.1109\/ICNN.1993.298725.","DOI":"10.1109\/ICNN.1993.298725"},{"key":"9489_CR22","doi-asserted-by":"publisher","unstructured":"Kamath U, Liu J, Whitaker J. Deep Learning for NLP and Speech Recognition. Cham: Springer International Publishing, 2019. https:\/\/doi.org\/10.1007\/978-3-030-14596-5.","DOI":"10.1007\/978-3-030-14596-5"},{"key":"9489_CR23","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1016\/j.aiopen.2022.10.001","volume":"3","author":"T Lin","year":"2022","unstructured":"Lin T, Wang Y, Liu X, Qiu X. A survey of transformers. AI Open. 2022;3:111\u201332. https:\/\/doi.org\/10.1016\/j.aiopen.2022.10.001.","journal-title":"AI Open"},{"key":"9489_CR24","unstructured":"Alghamdi M. Arabic phonetics. Al-Toubah Bookshop Riyadh, 2001, Accessed: Nov. 15, 2023. [Online]. Available: https:\/\/scholar.google.com\/scholar?cluster=11129280024605089009&hl=en&oi=scholarr."},{"key":"9489_CR25","doi-asserted-by":"crossref","unstructured":"Davenport M, Hannahs SJ. Introducing Phonetics and Phonology. Routledge, 2013.","DOI":"10.4324\/9780203785447"},{"key":"9489_CR26","doi-asserted-by":"crossref","unstructured":"Ashby P. Understanding Phonetics. Routledge, 2013.","DOI":"10.1093\/obo\/9780199772810-0082"},{"key":"9489_CR27","first-page":"1","volume":"2010","author":"M Abushariah","year":"2010","unstructured":"Abushariah M, Ainon RN, Zainuddin R, Elshafei M, Khalifa O. Natural speaker independent arabic speech recognition system based on HMM using sphinx tools. Proc Int Conf Comput Commun Eng. 2010;2010:1\u20136.","journal-title":"Proc Int Conf Comput Commun Eng."},{"issue":"3","key":"9489_CR28","doi-asserted-by":"publisher","first-page":"715","DOI":"10.1007\/s10772-017-9440-2","volume":"20","author":"FS Al-Anzi","year":"2017","unstructured":"Al-Anzi FS, AbuZeina D. The impact of phonological rules on Arabic speech recognition. Int J Speech Technol. 2017;20(3):715\u201323. https:\/\/doi.org\/10.1007\/s10772-017-9440-2.","journal-title":"Int J Speech Technol"},{"key":"9489_CR29","doi-asserted-by":"publisher","DOI":"10.14569\/IJACSA.2021.0120378","author":"A Jafri","year":"2021","unstructured":"Jafri A. Concatenative speech recognition using morphemes. Int J Adv Comput Sci Appl. 2021. https:\/\/doi.org\/10.14569\/IJACSA.2021.0120378.","journal-title":"Int J Adv Comput Sci Appl"},{"issue":"11","key":"9489_CR30","doi-asserted-by":"publisher","first-page":"9043","DOI":"10.1007\/s13369-019-04024-0","volume":"44","author":"S Abed","year":"2019","unstructured":"Abed S, Alshayeji M, Sultan S. Diacritics effect on arabic speech recognition. Arab J Sci Eng. 2019;44(11):9043\u201356. https:\/\/doi.org\/10.1007\/s13369-019-04024-0.","journal-title":"Arab J Sci Eng"},{"key":"9489_CR31","doi-asserted-by":"publisher","unstructured":"Kuo H-K, Mangu L, Emami A, Zitouni I, Lee Y-S. Syntactic Features for Arabic Speech Recognition. 2010, p. 332. https:\/\/doi.org\/10.1109\/ASRU.2009.5373470.","DOI":"10.1109\/ASRU.2009.5373470"},{"key":"9489_CR32","doi-asserted-by":"publisher","first-page":"81348","DOI":"10.1109\/ACCESS.2023.3300972","volume":"11","author":"SS Alrumiah","year":"2023","unstructured":"Alrumiah SS, Al-Shargabi AA. A deep diacritics-based recognition model for arabic speech: quranic verses as case study. IEEE Access. 2023;11:81348\u201360. https:\/\/doi.org\/10.1109\/ACCESS.2023.3300972.","journal-title":"IEEE Access"},{"key":"9489_CR33","doi-asserted-by":"publisher","first-page":"3471","DOI":"10.32604\/cmc.2023.033457","volume":"74","author":"M Hadwan","year":"2022","unstructured":"Hadwan M, Alsayadi H, Al-Hagree S. An end-to-end transformer-based automatic speech recognition for Qur\u2019an Reciters. Comput Mater Contin. 2022;74:3471\u201387. https:\/\/doi.org\/10.32604\/cmc.2023.033457.","journal-title":"Comput Mater Contin"},{"issue":"1","key":"9489_CR34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.48129\/kjs.v49i1.11231","volume":"49","author":"SL Marie-Sainte","year":"2022","unstructured":"Marie-Sainte SL. Samee\u2019a: a new system for Arabic recitation using speech recognition and Jaro Winkler algorithm: samee\u2019a Arabic Recitation. Kuwait J Sci. 2022;49(1):1. https:\/\/doi.org\/10.48129\/kjs.v49i1.11231.","journal-title":"Kuwait J Sci"},{"key":"9489_CR35","unstructured":"Speech-to-Text: Automatic Speech Recognition. Google Cloud. Accessed: 2022. [Online]. Available: https:\/\/cloud.google.com\/speech-to-text."},{"key":"9489_CR36","doi-asserted-by":"publisher","DOI":"10.1088\/1757-899X\/434\/1\/012044","volume":"434","author":"YA Gerhana","year":"2018","unstructured":"Gerhana YA, et al. Computer speech recognition to text for recite Holy Quran. IOP Conf Ser Mater Sci Eng. 2018;434: 012044. https:\/\/doi.org\/10.1088\/1757-899X\/434\/1\/012044.","journal-title":"IOP Conf Ser Mater Sci Eng"},{"key":"9489_CR37","doi-asserted-by":"crossref","unstructured":"Kanters R, Cucchiarini C, Strik H. The Goodness of Pronunciation Algorithm\u202f: a Detailed Performance Study. In: In SLaTE 2009-2009 ISCA Workshop on Speech and Language Technology in Education, 2009, pp. 2\u20135.","DOI":"10.21437\/SLaTE.2009-13"},{"key":"9489_CR38","doi-asserted-by":"crossref","unstructured":"Luo D, Yang X, Wang L. Improvement of Segmental Mispronunciation Detection with Prior Knowledge Extracted from Large L2 Speech Corpus. 2011, p. 1596.","DOI":"10.21437\/Interspeech.2011-478"},{"key":"9489_CR39","doi-asserted-by":"publisher","unstructured":"Ye W et al. An Approach to Mispronunciation Detection and Diagnosis with Acoustic, Phonetic and Linguistic (APL) Embeddings. In: ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Singapore, Singapore: IEEE, 2022, pp. 6827\u20136831. https:\/\/doi.org\/10.1109\/ICASSP43922.2022.9746604.","DOI":"10.1109\/ICASSP43922.2022.9746604"},{"issue":"5","key":"9489_CR40","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1187\/5\/052068","volume":"1187","author":"S Wang","year":"2019","unstructured":"Wang S, Li G. Overview of end-to-end speech recognition. J Phys Conf Ser. 2019;1187(5): 052068. https:\/\/doi.org\/10.1088\/1742-6596\/1187\/5\/052068.","journal-title":"J Phys Conf Ser"},{"issue":"1","key":"9489_CR41","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1109\/TASL.2011.2134090","volume":"20","author":"GE Dahl","year":"2012","unstructured":"Dahl GE, Yu D, Deng L, Acero A. Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition. IEEE Trans Audio Speech Lang Process. 2012;20(1):30\u201342. https:\/\/doi.org\/10.1109\/TASL.2011.2134090.","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"9489_CR42","doi-asserted-by":"publisher","unstructured":"Feng Y, Fu G, Chen Q, Chen K. SED-MDD: Towards Sentence Dependent End-To-End Mispronunciation Detection and Diagnosis. In: ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain: IEEE, 2020, pp. 3492\u20133496. https:\/\/doi.org\/10.1109\/ICASSP40776.2020.9052975.","DOI":"10.1109\/ICASSP40776.2020.9052975"},{"key":"9489_CR43","unstructured":"Mohamed A, Okhonko D, Zettlemoyer L. Transformers with convolutional context for ASR. ArXiv190411660 Cs, 2020, Accessed: Feb. 10, 2022. [Online]. Available: http:\/\/arxiv.org\/abs\/1904.11660."},{"issue":"11","key":"9489_CR44","doi-asserted-by":"publisher","first-page":"11","DOI":"10.3390\/app13116793","volume":"13","author":"L Peng","year":"2023","unstructured":"Peng L, Gao Y, Bao R, Li Y, Zhang J. End-to-End mispronunciation detection and diagnosis using transfer learning. Appl Sci. 2023;13(11):11. https:\/\/doi.org\/10.3390\/app13116793.","journal-title":"Appl Sci"},{"key":"9489_CR45","doi-asserted-by":"publisher","first-page":"66245","DOI":"10.1109\/ACCESS.2023.3278837","volume":"11","author":"S Guo","year":"2023","unstructured":"Guo S, Kadeer Z, Wumaier A, Wang L, Fan C. Multi-Feature and Multi-Modal Mispronunciation Detection and Diagnosis Method Based on the Squeezeformer Encoder. IEEE Access. 2023;11:66245\u201356. https:\/\/doi.org\/10.1109\/ACCESS.2023.3278837.","journal-title":"IEEE Access"},{"key":"9489_CR46","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3434497","author":"A Das","year":"2024","unstructured":"Das A, Gutierrez-Osuna R. Improving mispronunciation detection using speech reconstruction. IEEEACM Trans Audio Speech Lang Process. 2024. https:\/\/doi.org\/10.1109\/TASLP.2024.3434497.","journal-title":"IEEEACM Trans Audio Speech Lang Process."},{"key":"9489_CR47","doi-asserted-by":"publisher","unstructured":"Wan Y, Shi Y, Lin B, Xie Y. A Study of Mispronunciation Detection and Diagnosis Based on Meta-Learning. In: ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024, pp. 12792\u201312796. https:\/\/doi.org\/10.1109\/ICASSP48485.2024.10447007.","DOI":"10.1109\/ICASSP48485.2024.10447007"},{"key":"9489_CR48","doi-asserted-by":"publisher","unstructured":"Soundarya M, Anusuya S. Analysis of Mispronunciation Detection and Diagnosis Based on Conventional Deep Learning Techniques. In: Gunjan VK, Zurada JM, (Eds.) Proceedings of 4th International Conference on Recent Trends in Machine Learning, IoT, Smart Cities and Applications, Singapore: Springer Nature, 2024, pp. 367\u2013391. https:\/\/doi.org\/10.1007\/978-981-99-9442-7_31.","DOI":"10.1007\/978-981-99-9442-7_31"},{"issue":"23","key":"9489_CR49","doi-asserted-by":"publisher","first-page":"62793","DOI":"10.1007\/s11042-023-17899-x","volume":"83","author":"M Lounis","year":"2024","unstructured":"Lounis M, Dendani B, Bahi H. Mispronunciation detection and diagnosis using deep neural networks: a systematic review. Multimed Tools Appl. 2024;83(23):62793\u2013827. https:\/\/doi.org\/10.1007\/s11042-023-17899-x.","journal-title":"Multimed Tools Appl"},{"key":"9489_CR50","doi-asserted-by":"publisher","first-page":"52589","DOI":"10.1109\/ACCESS.2019.2912648","volume":"7","author":"F Nazir","year":"2019","unstructured":"Nazir F, Majeed MN, Ghazanfar MA, Maqsood M. Mispronunciation detection using deep convolutional neural network features and transfer learning-based model for arabic phonemes. IEEE Access. 2019;7:52589\u2013608. https:\/\/doi.org\/10.1109\/ACCESS.2019.2912648.","journal-title":"IEEE Access"},{"issue":"6","key":"9489_CR51","doi-asserted-by":"publisher","first-page":"6","DOI":"10.3390\/electronics9060963","volume":"9","author":"S Akhtar","year":"2020","unstructured":"Akhtar S, et al. Improving mispronunciation detection of arabic words for non-native learners using deep convolutional neural network features. Electronics. 2020;9(6):6. https:\/\/doi.org\/10.3390\/electronics9060963.","journal-title":"Electronics"},{"issue":"6","key":"9489_CR52","doi-asserted-by":"publisher","first-page":"2508","DOI":"10.3390\/app11062508","volume":"11","author":"N Ziafat","year":"2021","unstructured":"Ziafat N, Ahmad HF, Fatima I, Zia M, Alhumam A, Rajpoot K. Correct pronunciation detection of the arabic alphabet using deep learning. Appl Sci. 2021;11(6):2508. https:\/\/doi.org\/10.3390\/app11062508.","journal-title":"Appl Sci"},{"issue":"15","key":"9489_CR53","doi-asserted-by":"publisher","first-page":"15","DOI":"10.3390\/math10152727","volume":"10","author":"M Algabri","year":"2022","unstructured":"Algabri M, Mathkour H, Alsulaiman M, Bencherif MA. Mispronunciation detection and diagnosis with articulatory-level feedback generation for non-native arabic speech. Mathematics. 2022;10(15):15. https:\/\/doi.org\/10.3390\/math10152727.","journal-title":"Mathematics"},{"key":"9489_CR54","doi-asserted-by":"crossref","unstructured":"Ahmed A, Bader M, Shahin I, Bou Nassif A, Werghi N, Base M. Arabic Mispronunciation Recognition System Using LSTM Network. Information, 2023, Accessed: Sep. 07, 2023. [Online]. Available: https:\/\/www.mdpi.com\/2078-2489\/14\/7\/413.","DOI":"10.3390\/info14070413"},{"key":"9489_CR55","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2023.109593","volume":"212","author":"SS Cal\u0131k","year":"2023","unstructured":"Cal\u0131k SS, Kucukmanisa A, Kilimci ZH. An ensemble-based framework for mispronunciation detection of Arabic phonemes. Appl Acoust. 2023;212: 109593. https:\/\/doi.org\/10.1016\/j.apacoust.2023.109593.","journal-title":"Appl Acoust"},{"key":"9489_CR56","doi-asserted-by":"publisher","unstructured":"Kheir YE, Chowdhury SA, Ali A. L1-Aware Multilingual Mispronunciation Detection Framework. In: ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024, pp. 12752\u201312756. https:\/\/doi.org\/10.1109\/ICASSP48485.2024.10448480.","DOI":"10.1109\/ICASSP48485.2024.10448480"},{"key":"9489_CR57","doi-asserted-by":"publisher","unstructured":"Linkai P, Fu K, Lin B, Ke D, Zhang J. A Study on Fine-Tuning wav2vec2.0 Model for the Task of Mispronunciation Detection and Diagnosis. 2021, p. 4452. https:\/\/doi.org\/10.21437\/Interspeech.2021-1344.","DOI":"10.21437\/Interspeech.2021-1344"},{"key":"9489_CR58","unstructured":"Babu A et al. XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale. arXiv.org. Accessed: Aug. 08, 2023. [Online]. Available: https:\/\/arxiv.org\/abs\/2111.09296v3."},{"key":"9489_CR59","unstructured":"Lcvenshtcin V. Binary codes capable of correcting deletions, insertions and reversals. Sov Phys Dokl. 1966."},{"issue":"9","key":"9489_CR60","first-page":"341","volume":"5","author":"P Boersma","year":"2001","unstructured":"Boersma P. Praat, a system for doing phonetics by computer. Glot Int. 2001;5(9):341\u20135.","journal-title":"Glot Int"},{"key":"9489_CR61","unstructured":"PyTorch. Accessed: Nov. 05, 2023. [Online]. Available: https:\/\/pytorch.org\/."},{"key":"9489_CR62","unstructured":"\u25a1Transformers. Accessed: Nov. 05, 2023. [Online]. Available: https:\/\/huggingface.co\/docs\/transformers\/index."},{"issue":"11","key":"9489_CR63","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1609\/aaai.v37i11.26505","volume":"37","author":"Z Fu","year":"2023","unstructured":"Fu Z, Yang H, So AM-C, Lam W, Bing L, Collier N. On the effectiveness of parameter-efficient fine-tuning. Proc AAAI Conf Artif Intell. 2023;37(11):11. https:\/\/doi.org\/10.1609\/aaai.v37i11.26505.","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"9489_CR64","doi-asserted-by":"publisher","unstructured":"Dettmers T, Lewis M, Belkada Y, Zettlemoyer L. LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale. 2022, arXiv: arXiv:2208.07339. https:\/\/doi.org\/10.48550\/arXiv.2208.07339.","DOI":"10.48550\/arXiv.2208.07339"},{"key":"9489_CR65","unstructured":"Hu EJ et al. LoRA: low-Rank Adaptation of Large Language Models. 2021, arXiv: arXiv:2106.09685. Accessed: Nov. 06, 2023. [Online]. Available: http:\/\/arxiv.org\/abs\/2106.09685."},{"key":"9489_CR66","doi-asserted-by":"publisher","unstructured":"Ryu H, Kim S, Chung M. A Joint Model for Pronunciation Assessment and Mispronunciation Detection and Diagnosis with Multi-task Learning. In: INTERSPEECH 2023, ISCA, 2023, pp. 959\u2013963. https:\/\/doi.org\/10.21437\/Interspeech.2023-337.","DOI":"10.21437\/Interspeech.2023-337"},{"key":"9489_CR67","unstructured":"Young S et al. The HTK Book, vol. 3.4. 1995. Accessed: Nov. 05, 2023. [Online]. Available: https:\/\/www.inf.u-szeged.hu\/~tothl\/speech\/htkbook.pdf."},{"issue":"2","key":"9489_CR68","first-page":"753","volume":"18","author":"EH Jameel","year":"2010","unstructured":"Jameel EH. Difficult sounds in pronunciation and perception for learners of arabic as a non-native language: phonetic concepts and teaching techniques for pharyngeal and velar sounds. Islam Univ J Humanit Res. 2010;18(2):753\u201384.","journal-title":"Islam Univ J Humanit Res"},{"key":"9489_CR69","unstructured":"Abdulhameed AA. Challenges in Teaching Arabic Phonetics to Non-Native Speakers and Methods for Addressing Them. In: Proceedings of the 10th Annual Conference: Teaching Arabic to Non-Native Speakers in Global Universities and Institutes, \u0628\u0627\u0631\u064a\u0633: Ibn Sina Institute for Humanities and King Abdullah bin Abdulaziz International Center for the Arabic Language, 2016, pp. 11\u201333. Accessed: Mar. 22, 2023. [Online]. Available: http:\/\/search.mandumah.com\/Record\/917331."},{"key":"9489_CR70","unstructured":"Alajrami M. The Influence of the Arabic Language on Wolof Language. presented at the The International Conference on the Arabic Language, 2019. Accessed: Nov. 03, 2023. [Online]. Available: https:\/\/www.alarabiahconferences.org\/wp-content\/uploads\/2019\/04\/conference_research-864504424-1528095272-2017.pdf."},{"issue":"3","key":"9489_CR71","doi-asserted-by":"publisher","first-page":"3","DOI":"10.31436\/jlls.v9i3.646","volume":"9","author":"MA Abdulraheem","year":"2018","unstructured":"Abdulraheem MA. Contrastive Study for some of the sound features in Arabic and Yorba. J Linguist Lit Stud. 2018;9(3):3. https:\/\/doi.org\/10.31436\/jlls.v9i3.646.","journal-title":"J Linguist Lit Stud"},{"key":"9489_CR72","unstructured":"Demir F. The Arabic sounds and their teaching to adult non-native speakers. Buhuth.org. Accessed: Mar. 22, 2023. [Online]. Available: https:\/\/buhuth.org\/ar\/paper\/pSat082518060130r1009."},{"key":"9489_CR73","doi-asserted-by":"publisher","unstructured":"Zhao G et al. L2-ARCTIC: a non-native english speech corpus. In: Interspeech 2018, ISCA, 2018, pp. 2783\u20132787. https:\/\/doi.org\/10.21437\/Interspeech.2018-1110.","DOI":"10.21437\/Interspeech.2018-1110"},{"key":"9489_CR74","doi-asserted-by":"publisher","unstructured":"Zhang J et al. speechocean762: An Open-Source Non-Native English Speech Corpus for Pronunciation Assessment. In: Interspeech 2021, ISCA, 2021, pp. 3710\u20133714. https:\/\/doi.org\/10.21437\/Interspeech.2021-1259.","DOI":"10.21437\/Interspeech.2021-1259"},{"key":"9489_CR75","doi-asserted-by":"publisher","first-page":"106451","DOI":"10.1109\/ACCESS.2022.3212417","volume":"10","author":"Y Shen","year":"2022","unstructured":"Shen Y, Liu Q, Fan Z, Liu J, Wumaier A. Self-Supervised Pre-trained speech representation based end-to-end mispronunciation detection and diagnosis of mandarin. IEEE Access. 2022;10:106451\u201362. https:\/\/doi.org\/10.1109\/ACCESS.2022.3212417.","journal-title":"IEEE Access"},{"key":"9489_CR76","doi-asserted-by":"publisher","first-page":"72845","DOI":"10.1109\/ACCESS.2018.2881096","volume":"6","author":"AH Meftah","year":"2018","unstructured":"Meftah AH, Alotaibi YA, Selouani S-A. Evaluation of an arabic speech corpus of emotions: a perceptual and statistical analysis. IEEE Access. 2018;6:72845\u201361. https:\/\/doi.org\/10.1109\/ACCESS.2018.2881096.","journal-title":"IEEE Access"},{"key":"9489_CR77","doi-asserted-by":"publisher","unstructured":"Cohen J. A Coefficient of Agreement for Nominal Scales. 1960, Accessed: Oct. 11, 2024. [Online]. Available: https:\/\/doi.org\/10.1177\/001316446002000104.","DOI":"10.1177\/001316446002000104"},{"issue":"3","key":"9489_CR78","doi-asserted-by":"publisher","first-page":"276","DOI":"10.11613\/BM.2012.031","volume":"22","author":"ML McHugh","year":"2012","unstructured":"McHugh ML. Interrater reliability: the kappa statistic. Biochem Medica. 2012;22(3):276\u201382.","journal-title":"Biochem Medica"},{"key":"9489_CR79","doi-asserted-by":"publisher","unstructured":"Fleiss JL, Cohen J. The Equivalence of Weighted Kappa and the Intraclass Correlation Coefficient as Measures of Reliability. 1973, Accessed: Dec. 26, 2023. [Online]. Available: https:\/\/doi.org\/10.1177\/001316447303300309.","DOI":"10.1177\/001316447303300309"}],"container-title":["Discover Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10791-024-09489-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10791-024-09489-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10791-024-09489-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,6]],"date-time":"2025-01-06T12:08:32Z","timestamp":1736165312000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10791-024-09489-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,6]]},"references-count":79,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["9489"],"URL":"https:\/\/doi.org\/10.1007\/s10791-024-09489-8","relation":{},"ISSN":["2948-2992"],"issn-type":[{"value":"2948-2992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,6]]},"assertion":[{"value":"18 June 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 December 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 January 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study was conducted in accordance with ethical guidelines and regulations established by the Institutional Review Board (IRB) at the King Saud University. The data was collected from the participants after obtaining an ethical approval from the Standing Committee for Research Ethics at King Saud University, identified by the ERB number KSU-HE-22-732. In addition, the participants approved the informed consent form for participating in the speech data collection, as represented in Additional file .","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"1"}}