{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T14:02:34Z","timestamp":1779890554078,"version":"3.53.1"},"reference-count":56,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T00:00:00Z","timestamp":1774569600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T00:00:00Z","timestamp":1774569600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1007\/s00521-025-11717-1","type":"journal-article","created":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T10:18:42Z","timestamp":1774606722000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Transformer-based and ensemble learning approaches for Qira\u2019at identification in the Holy Qur\u2019an"],"prefix":"10.1007","volume":"38","author":[{"given":"Hebat-Allah","family":"Saber","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmed","family":"Younes","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohamed","family":"Osman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Islam","family":"Elkabani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,27]]},"reference":[{"key":"11717_CR1","doi-asserted-by":"publisher","first-page":"9411","DOI":"10.1007\/s11042-020-10073-7","volume":"80","author":"M Malik","year":"2021","unstructured":"Malik M, Malik MK, Mehmood K, Makhdoom I (2021) Automatic speech recognition: a survey. Multimed Tools Appl 80:9411\u20139457","journal-title":"Multimed Tools Appl"},{"key":"11717_CR2","doi-asserted-by":"publisher","first-page":"131858","DOI":"10.1109\/ACCESS.2021.3112535","volume":"9","author":"S Alharbi","year":"2021","unstructured":"Alharbi S et al (2021) Automatic speech recognition: systematic literature review. Ieee Access 9:131858\u2013131876","journal-title":"Ieee Access"},{"key":"11717_CR3","doi-asserted-by":"crossref","unstructured":"Han W, Chan C-F, Choy C-S, and Pun K-P (2006) An efficient MFCC extraction method in speech recognition. In 2006 IEEE International Symposium on Circuits and Systems (ISCAS), IEEE, 4-pp","DOI":"10.1109\/ISCAS.2006.1692543"},{"key":"11717_CR4","doi-asserted-by":"crossref","unstructured":"Al-Fadhli S, Al-Harbi H, Cherif A (2023) Speech recognition models for holy quran recitation based on modern approaches and tajweed rules: a comprehensive overview. Int J Adv Comput Sci Appl, 14(12)","DOI":"10.14569\/IJACSA.2023.0141297"},{"issue":"5","key":"11717_CR5","doi-asserted-by":"publisher","first-page":"497","DOI":"10.1016\/j.jksuci.2019.02.006","volume":"33","author":"I Guellil","year":"2021","unstructured":"Guellil I, Sa\u00e2dane H, Azouaou F, Gueni B, Nouvel D (2021) Arabic natural language processing: an overview. J King Saud University-Computer Inf Sci 33(5):497\u2013507","journal-title":"J King Saud University-Computer Inf Sci"},{"key":"11717_CR6","doi-asserted-by":"crossref","unstructured":"Shaiakhmetov D, Gimaletdinova G, Cankurt S, and Momunov K (2025) Evaluation of the pronunciation of tajweed rules based on DNN as a step towards interactive recitation learning. arXiv preprint arXiv:2503.23470","DOI":"10.1109\/CompSysTech65493.2025.11137272"},{"issue":"4","key":"11717_CR7","first-page":"1","volume":"2","author":"DM Omran","year":"2023","unstructured":"Omran DM, Kandil AH, ElBialy A, Samy S, Fawzy S (2023) CNN for speech recognition case study: recitation rules of the holy Quran. MSA Eng J 2(4):1\u201312","journal-title":"MSA Eng J"},{"key":"11717_CR8","unstructured":"Al Harere A, and Al Jallad K (2023) Quran recitation recognition using end-to-end deep learning. arXiv preprint arXiv:2305.07034"},{"key":"11717_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.eij.2025.100640","volume":"30","author":"E Hassan","year":"2025","unstructured":"Hassan E, Saber A, Alqahtani O, El-Rashidy N, Elbedwehy S (2025) An innovative approach to advanced voice classification of sacred Quranic recitations through multimodal fusion. Egyptian Inf J 30:100640","journal-title":"Egyptian Inf J"},{"issue":"12","key":"11717_CR10","doi-asserted-by":"publisher","first-page":"6559","DOI":"10.1007\/s00521-023-09392-1","volume":"36","author":"H-A Saber","year":"2024","unstructured":"Saber H-A, Younes A, Osman M, Elkabani I (2024) Quran reciter identification using NASNetLarge. Neural Comput Appl 36(12):6559\u20136573","journal-title":"Neural Comput Appl"},{"key":"11717_CR11","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4700\u20134708","DOI":"10.1109\/CVPR.2017.243"},{"key":"11717_CR12","doi-asserted-by":"crossref","unstructured":"M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, \u201cMobilenetv2: Inverted residuals and linear bottlenecks,\u201d in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 4510\u20134520","DOI":"10.1109\/CVPR.2018.00474"},{"key":"11717_CR13","doi-asserted-by":"crossref","unstructured":"Zoph B, Vasudevan V, Shlens J, and Le QV (2018) Learning transferable architectures for scalable image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 8697\u20138710","DOI":"10.1109\/CVPR.2018.00907"},{"key":"11717_CR14","doi-asserted-by":"publisher","first-page":"99129","DOI":"10.1109\/ACCESS.2022.3207287","volume":"10","author":"ID Mienye","year":"2022","unstructured":"Mienye ID, Sun Y (2022) A survey of ensemble learning: Concepts, algorithms, applications, and prospects. Ieee Access 10:99129\u201399149","journal-title":"Ieee Access"},{"key":"11717_CR15","doi-asserted-by":"crossref","unstructured":"Chen T and Guestrin C (2016) Xgboost: a scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, pp. 785\u2013794","DOI":"10.1145\/2939672.2939785"},{"key":"11717_CR16","unstructured":"Dosovitskiy A et al (2020) An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929"},{"key":"11717_CR17","doi-asserted-by":"crossref","unstructured":"Yun S, and Ro Y (2024) Shvit: Single-head vision transformer with memory efficient macro design. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 5756\u20135767","DOI":"10.1109\/CVPR52733.2024.00550"},{"key":"11717_CR18","doi-asserted-by":"crossref","unstructured":"Touvron H, Cord M, and J\u00e9gou H (2022) Deit iii: Revenge of the vit. In European conference on computer vision, Springer, pp. 516\u2013533","DOI":"10.1007\/978-3-031-20053-3_30"},{"key":"11717_CR19","unstructured":"Tan M, Le Q (2019) Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning, PMLR, 2019, pp. 6105\u20136114"},{"key":"11717_CR20","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, and Sun G (2018) Squeeze-and-excitation networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 7132\u20137141","DOI":"10.1109\/CVPR.2018.00745"},{"issue":"1","key":"11717_CR21","first-page":"1","volume":"9","author":"HM Osman","year":"2021","unstructured":"Osman HM, Mustafa BS, Faisal Y (2021) (2021) QDAT: a data set for reciting the Quran. Int J Islamic Appl Comput Sci Technol 9(1):1\u20139","journal-title":"Int J Islamic Appl Comput Sci Technol"},{"issue":"12","key":"11717_CR22","doi-asserted-by":"publisher","first-page":"6999","DOI":"10.1109\/TNNLS.2021.3084827","volume":"33","author":"Z Li","year":"2021","unstructured":"Li Z, Liu F, Yang W, Peng S, Zhou J (2021) A survey of convolutional neural networks: analysis, applications, and prospects. IEEE Trans Neural Netw Learn Syst 33(12):6999\u20137019","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"11717_CR23","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1016\/j.ins.2020.05.035","volume":"541","author":"X Liu","year":"2020","unstructured":"Liu X et al (2020) Attention-based bidirectional GRU networks for efficient HTTPS traffic classification. Inf Sci (NY) 541:297\u2013315","journal-title":"Inf Sci (NY)"},{"key":"11717_CR24","doi-asserted-by":"crossref","unstructured":"Graves A, Fern\u00e1ndez S, Gomez F, and Schmidhuber J (2006) Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In Proceedings of the 23rd international conference on Machine learning, pp. 369\u2013376","DOI":"10.1145\/1143844.1143891"},{"key":"11717_CR25","first-page":"231","volume-title":"\u201cEnd-to-end lexicon free Arabic speech recognition using recurrent neural networks\u201d, in Computational Linguistics","author":"A Ahmed","year":"2019","unstructured":"Ahmed A, Hifny Y, Shaalan K, Toral S (2019) \u201cEnd-to-end lexicon free Arabic speech recognition using recurrent neural networks\u201d, in Computational Linguistics. World Scientific, Speech and Image Processing for Arabic Language, pp 231\u2013248"},{"key":"11717_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2020.106503","volume":"33","author":"M Lataifeh","year":"2020","unstructured":"Lataifeh M, Elnagar A (2020) Ar-DAD: Arabic diversified audio dataset. Data Brief 33:106503","journal-title":"Data Brief"},{"key":"11717_CR27","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1007\/s00530-010-0182-0","volume":"16","author":"PK Atrey","year":"2010","unstructured":"Atrey PK, Hossain MA, El Saddik A, Kankanhalli MS (2010) Multimodal fusion for multimedia analysis: a survey. Multimed Syst 16:345\u2013379","journal-title":"Multimed Syst"},{"key":"11717_CR28","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, and Sun J (2016) Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"11717_CR29","doi-asserted-by":"publisher","first-page":"122136","DOI":"10.1109\/ACCESS.2022.3223444","volume":"10","author":"ZK Abdul","year":"2022","unstructured":"Abdul ZK, Al-Talabani AK (2022) Mel frequency cepstral coefficient and its applications: a review. IEEE Access 10:122136\u2013122158","journal-title":"IEEE Access"},{"key":"11717_CR30","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1016\/j.eng.2022.04.024","volume":"25","author":"H Wang","year":"2023","unstructured":"Wang H, Li J, Wu H, Hovy E, Sun Y (2023) Pre-trained language models and their applications. Engineering 25:51\u201365","journal-title":"Engineering"},{"key":"11717_CR31","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li L-J, Li K, and Fei-Fei L (2009) Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, IEEE, pp. 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"11717_CR32","doi-asserted-by":"crossref","unstructured":"Chollet F (2017) Xception: Deep learning with depthwise separable convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 1251\u20131258","DOI":"10.1109\/CVPR.2017.195"},{"key":"11717_CR33","unstructured":"Tan M and Le Q (2021) Efficientnetv2: Smaller models and faster training. In International conference on machine learning, PMLR, pp. 10096\u201310106"},{"key":"11717_CR34","unstructured":"Howard AG (2017) Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861"},{"key":"11717_CR35","doi-asserted-by":"crossref","unstructured":"Knapheide J, Stabernack B, and Kuhnke M (2020) A high throughput MobileNetV2 FPGA implementation based on a flexible architecture for depthwise separable convolution. In 2020 30th International Conference on Field-Programmable Logic and Applications (FPL), IEEE, 2020, pp. 277\u2013283","DOI":"10.1109\/FPL50879.2020.00053"},{"issue":"2","key":"11717_CR36","first-page":"18","volume":"1","author":"N Rane","year":"2024","unstructured":"Rane N, Choudhary SP, Rane J (2024) Ensemble deep learning and machine learning: applications, opportunities, challenges, and future directions. Stud Med Health Sci 1(2):18\u201341","journal-title":"Stud Med Health Sci"},{"key":"11717_CR37","doi-asserted-by":"crossref","unstructured":"Shah M, Gandhi K, Patel KA, Kantawala H, Patel R, and Kothari A (2023) Theoretical evaluation of ensemble machine learning techniques. In 2023 5th International Conference on Smart Systems and Inventive Technology (ICSSIT), IEEE pp. 829\u2013837.","DOI":"10.1109\/ICSSIT55814.2023.10061139"},{"issue":"5","key":"11717_CR38","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1049\/htl2.12085","volume":"11","author":"AK Al-Bashir","year":"2024","unstructured":"Al-Bashir AK, Al-Bataiha DH, Hafsa M, Al-Abed MA, Kanoun O (2024) Electrical impedance tomography image reconstruction for lung monitoring based on ensemble learning algorithms 1. Healthc Technol Lett 11(5):271\u2013282","journal-title":"Healthc Technol Lett"},{"key":"11717_CR39","unstructured":"Vaswani A et al (2017) Attention is all you need. Adv Neural Inf Process Syst, 30"},{"key":"11717_CR40","unstructured":"Touvron H, Cord M, Douze M, Massa F, Sablayrolles A, and J\u00e9gou H (2021) Training data-efficient image transformers & distillation through attention. In International conference on machine learning, PMLR, pp. 10347\u201310357"},{"key":"11717_CR41","unstructured":"Muda L, Begam M, and Elamvazuthi I (2010) Voice recognition algorithms using mel frequency cepstral coefficient (MFCC) and dynamic time warping (DTW) techniques. arXiv preprint arXiv:1003.4083"},{"key":"11717_CR42","unstructured":"Lu R (1989) Algorithms for discrete Fourier transform and convolution. Springer"},{"key":"11717_CR43","unstructured":"Shannon BJ and Paliwal KK (2003) A comparative study of filter bank spacing for speech recognition. In Microelectronic engineering research conference, Citeseer, pp. 310\u2013312"},{"key":"11717_CR44","doi-asserted-by":"publisher","first-page":"122238","DOI":"10.1109\/ACCESS.2023.3327898","volume":"11","author":"MSH Shovon","year":"2023","unstructured":"Shovon MSH, Mridha MF, Hasib KM, Alfarhood S, Safran M, Che D (2023) Addressing uncertainty in imbalanced histopathology image classification of her2 breast cancer: an interpretable ensemble approach with threshold filtered single instance evaluation (sie). IEEe Access 11:122238\u2013122251","journal-title":"IEEe Access"},{"key":"11717_CR45","unstructured":"Yang S, Xiao W, Zhang M, Guo S, Zhao J, and Shen F (2022) Image data augmentation for deep learning: A survey,\u201d arXiv preprint arXiv:2204.08610"},{"key":"11717_CR46","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2020.106759","volume":"97","author":"M Saini","year":"2020","unstructured":"Saini M, Susan S (2020) Deep transfer with minority data augmentation for imbalanced breast cancer dataset. Appl Soft Comput 97:106759","journal-title":"Appl Soft Comput"},{"issue":"11","key":"11717_CR47","doi-asserted-by":"publisher","first-page":"8259","DOI":"10.1007\/s00521-022-08099-z","volume":"35","author":"JA Prakash","year":"2023","unstructured":"Prakash JA, Ravi V, Sowmya V, Soman KP (2023) Stacked ensemble learning based on deep convolutional neural networks for pediatric pneumonia diagnosis using chest X-ray images. Neural Comput Appl 35(11):8259\u20138279","journal-title":"Neural Comput Appl"},{"issue":"1","key":"11717_CR48","first-page":"17","volume":"2","author":"D Lavanya","year":"2012","unstructured":"Lavanya D, Rani KU (2012) Ensemble decision tree classifier for breast cancer data. Int J Inf Technol Convergence Services 2(1):17\u201324","journal-title":"Int J Inf Technol Convergence Services"},{"issue":"21","key":"11717_CR49","doi-asserted-by":"publisher","first-page":"13998","DOI":"10.3390\/su142113998","volume":"14","author":"M Kumar","year":"2022","unstructured":"Kumar M, Singhal S, Shekhar S, Sharma B, Srivastava G (2022) Optimized stacking ensemble learning model for breast cancer detection and classification using machine learning. Sustainability 14(21):13998","journal-title":"Sustainability"},{"issue":"7","key":"11717_CR50","doi-asserted-by":"publisher","first-page":"1443","DOI":"10.3390\/cancers16071443","volume":"16","author":"I Miller","year":"2024","unstructured":"Miller I et al (2024) Performance of commercial dermatoscopic systems that incorporate artificial intelligence for the identification of melanoma in general practice: a systematic review. Cancers (Basel) 16(7):1443","journal-title":"Cancers (Basel)"},{"key":"11717_CR51","doi-asserted-by":"crossref","unstructured":"Mu X and Min C-H (2023) MFCC as features for speaker classification using machine learning. In 2023 IEEE world AI IoT congress (AIIoT), IEEEs, pp. 566\u2013570","DOI":"10.1109\/AIIoT58121.2023.10174566"},{"issue":"6","key":"11717_CR52","doi-asserted-by":"publisher","first-page":"1057","DOI":"10.47974\/JIOS-1431","volume":"44","author":"P Rawat","year":"2023","unstructured":"Rawat P, Bajaj M, Vats S, Sharma V (2023) A comprehensive study based on MFCC and spectrogram for audio classification. J Inf Optimization Sci 44(6):1057\u20131074","journal-title":"J Inf Optimization Sci"},{"key":"11717_CR53","doi-asserted-by":"crossref","unstructured":"Mohmmad S and Sanampudi SK (2023) Tree cutting sound detection using deep learning techniques based on mel spectrogram and MFCC features. In Proceedings of Third International Conference on Advances in Computer Engineering and Communication Systems: ICACECS 2022, Springer, 2023, pp. 497\u2013512","DOI":"10.1007\/978-981-19-9228-5_42"},{"issue":"32","key":"11717_CR54","doi-asserted-by":"publisher","first-page":"77327","DOI":"10.1007\/s11042-024-18602-4","volume":"83","author":"MK Singh","year":"2024","unstructured":"Singh MK (2024) Multimedia application for forensic automatic speaker recognition from disguised voices using MFCC feature extraction and classification techniques. Multimed Tools Appl 83(32):77327\u201377345","journal-title":"Multimed Tools Appl"},{"key":"11717_CR55","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2024.101713","volume":"89","author":"SJ Joysingh","year":"2025","unstructured":"Joysingh SJ, Vijayalakshmi P, Nagarajan T (2025) Significance of chirp MFCC as a feature in speech and audio applications. Comput Speech Lang 89:101713","journal-title":"Comput Speech Lang"},{"issue":"1","key":"11717_CR56","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s43926-023-00049-y","volume":"4","author":"MK Gourisaria","year":"2024","unstructured":"Gourisaria MK, Agrawal R, Sahni M, Singh PK (2024) Comparative analysis of audio classification with MFCC and STFT features using machine learning techniques. Discover Internet Things 4(1):1","journal-title":"Discover Internet Things"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-025-11717-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-025-11717-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-025-11717-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T13:06:35Z","timestamp":1779887195000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-025-11717-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,27]]},"references-count":56,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["11717"],"URL":"https:\/\/doi.org\/10.1007\/s00521-025-11717-1","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,27]]},"assertion":[{"value":"23 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors state that there are no conflicts of interest or funding involved.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"237"}}