{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,29]],"date-time":"2026-10-29T21:33:26Z","timestamp":1793309606040,"version":"4.5.0"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,6,16]],"date-time":"2025-06-16T00:00:00Z","timestamp":1750032000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,6,16]],"date-time":"2025-06-16T00:00:00Z","timestamp":1750032000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/501100019345","name":"King Salman Center for Disability Research","doi-asserted-by":"publisher","award":["KSRG-2022-136"],"award-info":[{"award-number":["KSRG-2022-136"]}],"id":[{"id":"10.13039\/501100019345","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-025-02042-7","type":"journal-article","created":{"date-parts":[[2025,6,16]],"date-time":"2025-06-16T04:16:08Z","timestamp":1750047368000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["A novel Swin transformer based framework for speech recognition for dysarthria"],"prefix":"10.1038","volume":"15","author":[{"given":"Rabbia","family":"Mahum","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ismaila","family":"Ganiyu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lotfi","family":"Hidri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmed M.","family":"El-Sherbeeny","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haseeb","family":"Hassan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,6,16]]},"reference":[{"key":"2042_CR1","doi-asserted-by":"publisher","first-page":"36990","DOI":"10.1109\/ACCESS.2024.3374874","volume":"12","author":"R Takashima","year":"2024","unstructured":"Takashima, R. et al. Dysarthric speech recognition using pseudo-labeling, self-supervised feature learning, and a joint multi-task learning approach. IEEE Access 12, 36990\u201336999 (2024).","journal-title":"IEEE Access"},{"key":"2042_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s13369-024-08919-5","volume":"49","author":"R Kumar","year":"2024","unstructured":"Kumar, R. et al. Residual convolutional neural network-based dysarthric speech recognition. Arab. J. Sci. Eng. 49, 1\u201311 (2024).","journal-title":"Arab. J. Sci. Eng."},{"key":"2042_CR3","doi-asserted-by":"publisher","DOI":"10.1080\/10400435.2024.2328082","author":"E Howarth","year":"2024","unstructured":"Howarth, E., Vabulas, G., Connolly, S., Green, D. & Smolley, S. Developing accessible speech technology with users with dysarthric speech. Assist. Technol. https:\/\/doi.org\/10.1080\/10400435.2024.2328082 (2024).","journal-title":"Assist. Technol."},{"key":"2042_CR4","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1109\/JTEHM.2024.3375323","volume":"12","author":"SA Naeini","year":"2024","unstructured":"Naeini, S. A. et al. Improving dysarthric speech segmentation with emulated and synthetic augmentation. IEEE J. Transl. Eng. Health Med. 12, 382\u2013389 (2024).","journal-title":"IEEE J. Transl. Eng. Health Med."},{"key":"2042_CR5","doi-asserted-by":"publisher","first-page":"134701","DOI":"10.1109\/ACCESS.2023.3332561","volume":"11","author":"R Mahum","year":"2023","unstructured":"Mahum, R., Irtaza, A. & Javed, A. EDL-Det: A robust TTS synthesis detector using VGG19-based YAMNet and ensemble learning block. IEEE Access 11, 134701\u2013134716 (2023).","journal-title":"IEEE Access"},{"issue":"1","key":"2042_CR6","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1186\/s13636-024-00335-9","volume":"2024","author":"R Mahum","year":"2024","unstructured":"Mahum, R. et al. DeepDet: YAMNet with BottleNeck attention module (BAM) TTS synthesis detection. EURASIP J. Audio Speech Music Process. 2024(1), 18 (2024).","journal-title":"EURASIP J. Audio Speech Music Process."},{"key":"2042_CR7","doi-asserted-by":"publisher","first-page":"53850","DOI":"10.1109\/ACCESS.2023.3281259","volume":"11","author":"R Mahum","year":"2023","unstructured":"Mahum, R. & AlSalman, A. Lung-RetinaNet: Lung cancer detection using a RetinaNet with multi-scale feature fusion and context module. IEEE Access 11, 53850\u201353861 (2023).","journal-title":"IEEE Access"},{"issue":"21","key":"2042_CR8","doi-asserted-by":"publisher","first-page":"3425","DOI":"10.3390\/electronics11213425","volume":"11","author":"MJ Akhtar","year":"2022","unstructured":"Akhtar, M. J. et al. A robust framework for object detection in a traffic surveillance system. Electronics 11(21), 3425 (2022).","journal-title":"Electronics"},{"key":"2042_CR9","doi-asserted-by":"crossref","unstructured":"Wisesty, U. N. & Astuti, W. Feature extraction analysis on Indonesian speech recognition system. In 2015 3rd International Conference on Information and Communication Technology (ICoICT) (IEEE, 2015).","DOI":"10.1109\/ICoICT.2015.7231396"},{"key":"2042_CR10","unstructured":"Rughani, M. & Shivakrishna, D. Hybridized Feature Extraction and Acoustic Modelling Approach for Dysarthric Speech Recognition. arXiv preprint https:\/\/arxiv.org\/abs\/1506.02170 (2015)."},{"key":"2042_CR11","doi-asserted-by":"crossref","unstructured":"Ijitona, T. B., Soraghan, J. J., Lowit, A. Di-Caterina, G. & Yue, H. Automatic Detection of Speech Disorder in Dysarthria Using Extended Speech Feature Extraction and Neural Networks Classification, 15\u20136 (2017).","DOI":"10.1049\/cp.2017.0360"},{"key":"2042_CR12","doi-asserted-by":"publisher","first-page":"3824","DOI":"10.1109\/TASLP.2023.3319276","volume":"31","author":"Y Lin","year":"2023","unstructured":"Lin, Y., Wang, L., Yang, Y. & Dang, J. CFDRN: A cognition-inspired feature decomposition and recombination network for dysarthric speech recognition. IEEE\/ACM Trans. Audio Speech Lang. Process. 31, 3824\u20133836 (2023).","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"2042_CR13","doi-asserted-by":"crossref","unstructured":"Gurugubelli, K. & Vuppala, A. K. Perceptually enhanced single frequency filtering for dysarthric speech detection and intelligibility assessment. In ICASSP 2019\u20132019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (IEEE, 2019).","DOI":"10.1109\/ICASSP.2019.8683314"},{"key":"2042_CR14","doi-asserted-by":"publisher","first-page":"1912","DOI":"10.1109\/TNSRE.2023.3262001","volume":"31","author":"C Yu","year":"2023","unstructured":"Yu, C., Su, X. & Qian, Z. Multi-stage audio-visual fusion for dysarthric speech recognition with pre-trained models. IEEE Trans. Neural Syst. Rehabil. Eng. 31, 1912\u20131921 (2023).","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"2042_CR15","doi-asserted-by":"crossref","unstructured":"Baali, M. et al. Arabic Dysarthric Speech Recognition Using Adversarial and Signal-Based Augmentation. arXiv preprint https:\/\/arxiv.org\/abs\/2306.04368 (2023).","DOI":"10.21437\/Interspeech.2023-1541"},{"key":"2042_CR16","doi-asserted-by":"crossref","unstructured":"Yue, Z., Loweimi, E. & Cvetkovic, Z. Dysarthric Speech Recognition, Detection and Classification using Raw Phase and Magnitude Spectra, 1533\u20131537 (2023).","DOI":"10.21437\/Interspeech.2023-222"},{"key":"2042_CR17","doi-asserted-by":"publisher","unstructured":"Padmanaban, S. & Mohan, V. Comparative Analysis of Deep Learning Models for Dysarthric Speech Detection. PREPRINT (Version 1) available at Research Square https:\/\/doi.org\/10.21203\/rs.3.rs-1916239\/v1 (2023).","DOI":"10.21203\/rs.3.rs-1916239\/v1"},{"key":"2042_CR18","doi-asserted-by":"crossref","unstructured":"Bhat, C., Das, B., Vachhani, B. & Kopparapu, S. K. Dysarthric speech recognition using time-delay neural network based denoising autoencoder. In Interspeech, 451\u2013455 (2018).","DOI":"10.21437\/Interspeech.2018-1754"},{"key":"2042_CR19","unstructured":"Hu, S., Liu, S., Chang, H. F., Geng, M., Chen, J., Chung, L. W., Hei, T. K. et al. The CUHK dysarthric speech recognition systems for English and Cantonese. In INTERSPEECH, 3669\u20133670 (2019)."},{"key":"2042_CR20","doi-asserted-by":"crossref","unstructured":"Vachhani, B., Bhat, C. & Kopparapu, S. K. Data augmentation using healthy speech for dysarthric speech recognition. In Interspeech, 471\u2013475 (2018).","DOI":"10.21437\/Interspeech.2018-1751"},{"key":"2042_CR21","doi-asserted-by":"crossref","unstructured":"Kim, E. et al. Debiased automatic speech recognition for dysarthric speech via sample reweighting with sample affinity test. In InterSpeech, Dublin, Ireland, 1508\u20131512. arXiv preprint https:\/\/arxiv.org\/abs\/2305.13108 (2023).","DOI":"10.21437\/Interspeech.2023-2421"},{"key":"2042_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13636-019-0169-5","volume":"2020","author":"M Sidi Yakoub","year":"2020","unstructured":"Sidi Yakoub, M. et al. Improving dysarthric speech recognition using empirical mode decomposition and convolutional neural network. EURASIP J. Audio Speech Music Process. 2020, 1\u20137 (2020).","journal-title":"EURASIP J. Audio Speech Music Process."},{"issue":"6","key":"2042_CR23","first-page":"384","volume":"13","author":"H Albaqshi","year":"2020","unstructured":"Albaqshi, H. & Sagheer, A. Dysarthric speech recognition using convolutional recurrent neural networks. Int. J. Intell. Eng. Syst. 13(6), 384\u2013392 (2020).","journal-title":"Int. J. Intell. Eng. Syst."},{"key":"2042_CR24","doi-asserted-by":"publisher","unstructured":"Vachhani, B., Bhat, C., Das, B. & Kopparapu, S. K. Deep autoencoder based speech features for improved dysarthric speech recognition. In Proc. Interspeech 2017, 1854\u20131858. https:\/\/doi.org\/10.21437\/Interspeech.2017-1318 (2017).","DOI":"10.21437\/Interspeech.2017-1318"},{"key":"2042_CR25","doi-asserted-by":"crossref","unstructured":"Shih, D.-H. et al. Dysarthria speech detection using convolutional neural networks with gated recurrent unit. In Healthcare (MDPI, 2022).","DOI":"10.3390\/healthcare10101956"},{"key":"2042_CR26","doi-asserted-by":"publisher","first-page":"852","DOI":"10.1109\/TNSRE.2021.3076778","volume":"29","author":"SR Shahamiri","year":"2021","unstructured":"Shahamiri, S. R. Speech vision: An end-to-end deep learning-based dysarthric automatic speech recognition system. IEEE Trans. Neural Syst. Rehabil. Eng. 29, 852\u2013861 (2021).","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"issue":"1","key":"2042_CR27","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1007\/s11277-021-08899-x","volume":"122","author":"R Rajeswari","year":"2022","unstructured":"Rajeswari, R., Devi, T. & Shalini, S. Dysarthric speech recognition using variational mode decomposition and convolutional neural networks. Wirel. Pers. Commun. 122(1), 293\u2013307 (2022).","journal-title":"Wirel. Pers. Commun."},{"key":"2042_CR28","doi-asserted-by":"crossref","unstructured":"Korzekwa, D. et al. Interpretable Deep Learning Model for the Detection and Reconstruction of Dysarthric Speech. arXiv preprint https:\/\/arxiv.org\/abs\/1907.04743 (2019).","DOI":"10.21437\/Interspeech.2019-1206"},{"issue":"6","key":"2042_CR29","doi-asserted-by":"publisher","first-page":"2477","DOI":"10.3390\/app11062477","volume":"11","author":"Y-Y Lin","year":"2021","unstructured":"Lin, Y.-Y. et al. A speech command control-based recognition system for dysarthric patients based on deep learning technology. Appl. Sci. 11(6), 2477 (2021).","journal-title":"Appl. Sci."},{"key":"2042_CR30","doi-asserted-by":"publisher","unstructured":"Woszczyk, D., Petridis, S. & Millard, D. Domain adversarial neural networks for dysarthric speech recognition. In Proc. Interspeech 2020, 3875\u20133879. https:\/\/doi.org\/10.21437\/Interspeech.2020-2845 (2020).","DOI":"10.21437\/Interspeech.2020-2845"},{"key":"2042_CR31","doi-asserted-by":"publisher","unstructured":"Wang, Q. et al. Dysarthric speech conformer: Adaptation for sequence-to-sequence dysarthric speech recognition. In ICASSP 2025\u20142025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Hyderabad, India, 1\u20135. https:\/\/doi.org\/10.1109\/ICASSP49660.2025.10889046 (2025).","DOI":"10.1109\/ICASSP49660.2025.10889046"},{"key":"2042_CR32","doi-asserted-by":"crossref","unstructured":"Liu, Z. et al. Swin transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, 10012\u201310022 (2021).","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2042_CR33","unstructured":"Ioffe, S. & Szegedy, C. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In Proceedings of the 32nd International Conference on International Conference on Machine Learning, vol 37, 448\u20134 (2015)."},{"key":"2042_CR34","unstructured":"Patwardhan, N., Ingalhalikar, M. & Walambe, R. ARiA: Utilizing Richard\u2019s Curve for Controlling the Non-monotonicity of the Activation Function in Deep Neural Nets. arXiv preprint https:\/\/arxiv.org\/abs\/1805.08878 (2018)."},{"key":"2042_CR35","unstructured":"Vaswani, A. et al. Attention is all you need. Advances in neural information processing systems. In 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA (2017)."},{"key":"2042_CR36","doi-asserted-by":"crossref","unstructured":"Menendez-Pidal, X. et al. The Nemours database of dysarthric speech. In Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP\u201996 (IEEE, 1996).","DOI":"10.21437\/ICSLP.1996-503"},{"key":"2042_CR37","unstructured":"Perez, L. & Wang, J. The Effectiveness of Data Augmentation in Image Classification using Deep Learning. https:\/\/arxiv.org\/abs\/1712.04621 (2017)."},{"key":"2042_CR38","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101114","volume":"64","author":"X Wang","year":"2020","unstructured":"Wang, X. et al. ASVspoof 2019: A large-scale public database of synthesized, converted and replayed speech. Comput. Speech Lang. 64, 101114 (2020).","journal-title":"Comput. Speech Lang."},{"key":"2042_CR39","unstructured":"Loshchilov, I. & Hutter, F. Decoupled weight decay regularization. In Proceedings of the International Conference on Learning Representations (ICLR 2019), arXiv preprint https:\/\/arxiv.org\/abs\/1711.05101 (2019)."},{"key":"2042_CR40","unstructured":"Loshchilov, I. & Hutter, F. Sgdr: Stochastic gradient descent with warm restarts. In Proceedings of the International Conference on Learning Representations (ICLR 2018). arXiv preprint https:\/\/arxiv.org\/abs\/1608.03983 (2018)."},{"key":"2042_CR41","doi-asserted-by":"publisher","unstructured":"Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D. & Batra, D. Grad-CAM: Visual explanations from deep networks via gradient-based localization. In 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 618\u2013626. https:\/\/doi.org\/10.1109\/ICCV.2017.74 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"2042_CR42","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1007\/s10579-011-9145-0","volume":"46","author":"F Rudzicz","year":"2012","unstructured":"Rudzicz, F., Namasivayam, A. K. & Wolff, T. The TORGO database of acoustic and articulatory speech from speakers with dysarthria. Lang. Resour. Eval. 46, 523\u2013541 (2012).","journal-title":"Lang. Resour. Eval."},{"issue":"3","key":"2042_CR43","doi-asserted-by":"publisher","first-page":"23","DOI":"10.13064\/KSSS.2019.11.3.023","volume":"11","author":"A Hernandez","year":"2019","unstructured":"Hernandez, A., Lee, H.-Y. & Chung, M. Acoustic analysis of fricatives in dysarthric speakers with cerebral palsy. Phon. Speech Sci. 11(3), 23\u201329 (2019).","journal-title":"Phon. Speech Sci."},{"key":"2042_CR44","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1016\/j.specom.2019.04.003","volume":"110","author":"N Narendra","year":"2019","unstructured":"Narendra, N. & Alku, P. Dysarthric speech classification from coded telephone speech using glottal features. Speech Commun. 110, 47\u201355 (2019).","journal-title":"Speech Commun."},{"key":"2042_CR45","doi-asserted-by":"publisher","first-page":"67745","DOI":"10.1109\/ACCESS.2020.2986171","volume":"8","author":"N Narendra","year":"2020","unstructured":"Narendra, N. & Alku, P. Glottal source information for pathological voice detection. IEEE Access 8, 67745\u201367755 (2020).","journal-title":"IEEE Access"},{"key":"2042_CR46","doi-asserted-by":"publisher","first-page":"3407","DOI":"10.1109\/TNSRE.2023.3307020","volume":"31","author":"SR Shahamiri","year":"2023","unstructured":"Shahamiri, S. R., Lal, V. & Shah, D. Dysarthric speech transformer: A sequence-to-sequence dysarthric speech recognition system. IEEE Trans. Neural Syst. Rehabil. Eng. 31, 3407\u20133416 (2023).","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"2042_CR47","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.119797","volume":"222","author":"A Almadhor","year":"2023","unstructured":"Almadhor, A. et al. E2E-DASR: End-to-end deep learning-based dysarthric automatic speech recognition. Expert Syst. Appl. 222, 119797 (2023).","journal-title":"Expert Syst. Appl."},{"key":"2042_CR48","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11227-024-06015-x","volume":"80","author":"S Mehra","year":"2024","unstructured":"Mehra, S., Ranga, V. & Agarwal, R. A deep learning approach to dysarthric utterance classification with BiLSTM-GRU, speech cue filtering, and log mel spectrograms. J. Supercomput. 80, 1\u201328 (2024).","journal-title":"J. Supercomput."},{"key":"2042_CR49","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2024.110019","volume":"222","author":"R Mahum","year":"2024","unstructured":"Mahum, R., El-Sherbeeny, A. M., Alkhaledi, K. & Hassan, H. Tran-DSR: A hybrid model for dysarthric speech recognition using transformer encoder and ensemble learning. Appl. Acoust. 222, 110019 (2024).","journal-title":"Appl. Acoust."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-02042-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-02042-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-02042-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,16]],"date-time":"2025-06-16T04:16:18Z","timestamp":1750047378000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-02042-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,16]]},"references-count":49,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["2042"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-02042-7","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,16]]},"assertion":[{"value":"11 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 May 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 June 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":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"20070"}}