{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T06:53:08Z","timestamp":1789714388485,"version":"4.0.1"},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"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":["Sci Data"],"DOI":"10.1038\/s41597-025-06193-0","type":"journal-article","created":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T12:16:07Z","timestamp":1764764167000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Kazakh language Dataset of Lip Movements for Command Recognition"],"prefix":"10.1038","volume":"12","author":[{"given":"Batyr","family":"Kenzheakhmetov","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alissultan","family":"Amankos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Beibut","family":"Amirgaliyev","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhanel","family":"Zhanibekova","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aidana","family":"Zhalgas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Didar","family":"Yedilkhan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,12,3]]},"reference":[{"key":"6193_CR1","unstructured":"Assael, Y. M., Shillingford, B., Whiteson, S. & De Freitas, N. Lipnet: End-to-end sentence-level lipreading. arXiv1611.01599 (2016)."},{"key":"6193_CR2","first-page":"87","volume":"10112","author":"JS Chung","year":"2017","unstructured":"Chung, J. S. & Zisserman, A. Lip reading in the wild. Computer Vision\u2013ACCV 2016. Lect. Notes Comput. Sci. 10112, 87\u2013103 (2017).","journal-title":"Computer Vision\u2013ACCV 2016. Lect. Notes Comput. Sci."},{"key":"6193_CR3","doi-asserted-by":"publisher","first-page":"121184","DOI":"10.1109\/ACCESS.2021.3107946","volume":"9","author":"S Fenghour","year":"2021","unstructured":"Fenghour, S., Chen, D., Guo, K., Li, B. & Xiao, P. Deep learning-based automated lip-reading: A survey. IEEE Access 9, 121184\u2013121205 (2021).","journal-title":"IEEE Access"},{"key":"6193_CR4","doi-asserted-by":"publisher","first-page":"276","DOI":"10.1017\/S0025100319000185","volume":"51","author":"AG McCollum","year":"2021","unstructured":"McCollum, A. G. & Chen, S. Kazakh. J. Int. Phon. Assoc. 51, 276\u2013298 (2021).","journal-title":"J. Int. Phon. Assoc."},{"key":"6193_CR5","unstructured":"Moran, Steven & McCloy, Daniel (eds.) PHOIBLE2.0. Jena: Max Planck Institute for the Science of Human History. (Available online at http:\/\/phoible.org, Accessed on 2025-09-15.) (2019)."},{"key":"6193_CR6","doi-asserted-by":"publisher","first-page":"15","DOI":"10.3390\/data8010015","volume":"8","author":"A Berkol","year":"2023","unstructured":"Berkol, A., T\u00fcmer-Sivri, T., Pervan-Akman, N., \u00c7olak, M. & Erdem, H. Visual lip reading dataset in Turkish. Data 8, 15 (2023).","journal-title":"Data"},{"key":"6193_CR7","doi-asserted-by":"crossref","unstructured":"Yang, S. et al. LRW-1000: A naturally-distributed large-scale benchmark for lip reading in the wild. In Proc. 14th IEEE Int. Conf. Autom. Face Gesture Recognit. 1\u20138 (2019).","DOI":"10.1109\/FG.2019.8756582"},{"key":"6193_CR8","doi-asserted-by":"crossref","unstructured":"Chung, J. S., Senior, A., Vinyals, O. & Zisserman, A. Lip reading sentences in the wild. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit. 6447\u20136456 (2017).","DOI":"10.1109\/CVPR.2017.367"},{"key":"6193_CR9","first-page":"2645","volume":"34","author":"Y Kumar","year":"2020","unstructured":"Kumar, Y. et al. Harnessing GANs for zero-shot learning of new classes in visual speech recognition. In Proc. AAAI Conf. Artif. Intell. 34, 2645\u20132652 (2020).","journal-title":"In Proc. AAAI Conf. Artif. Intell."},{"key":"6193_CR10","unstructured":"Garg, A., Noyola, J. & Bagadia, S. Lip reading using CNN and LSTM. Stanford University CS231n Project Report (2016)."},{"key":"6193_CR11","unstructured":"Vosk. Vosk speech recognition toolkit (Version 0.3.45) [Software]. https:\/\/alphacephei.com\/vosk\/ (2023)."},{"key":"6193_CR12","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"S Ji","year":"2012","unstructured":"Ji, S., Xu, W., Yang, M. & Yu, K. 3D convolutional neural networks for human action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35, 221\u2013231 (2012).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"6193_CR13","doi-asserted-by":"crossref","unstructured":"Prashanth, B. S. et al. Lip Reading with 3D Convolutional and Bidirectional LSTM Networks on the GRID Corpus. In Proc. 2nd Int. Conf. Netw. Multimedia Inf. Technol. (NMITCON) 1\u20138 (2024).","DOI":"10.1109\/NMITCON62075.2024.10699241"},{"key":"6193_CR14","unstructured":"Afouras, T., Chung, J. S. & Zisserman, A. LRS3-TED: A large-scale dataset for visual speech recognition. arXiv1809.00496 (2018)."},{"key":"6193_CR15","first-page":"1","volume":"1","author":"I Anina","year":"2015","unstructured":"Anina, I., Zhou, Z., Zhao, G. & Pietik\u00e4inen, M. OuluVS2: A multi-view audiovisual database for non-rigid mouth motion analysis. Proc. 11th IEEE Int. Conf. Workshops Autom. Face Gesture Recognit. 1, 1\u20135 (2015).","journal-title":"Proc. 11th IEEE Int. Conf. Workshops Autom. Face Gesture Recognit."},{"key":"6193_CR16","doi-asserted-by":"crossref","unstructured":"Chung, J. S., Nagrani, A. & Zisserman, A. VoxCeleb2: Deep speaker recognition. arXiv 1806.05622 (2018).","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"6193_CR17","doi-asserted-by":"crossref","unstructured":"T\u00fcmer Sivri, T., Berkol, A. & Erdem, H. Lip reading using various deep learning models with visual Turkish data. Gazi Univ. J. Sci. 37 (2024).","DOI":"10.35378\/gujs.1239207"},{"key":"6193_CR18","first-page":"3251","volume":"2252","author":"H Pourmousa","year":"2024","unstructured":"Pourmousa, H. & \u00d6zen, \u00dc. Lip reading using deep learning in Turkish language. Int. J. Artif. Intell. 2252, 3251 (2024).","journal-title":"Int. J. Artif. Intell."},{"key":"6193_CR19","unstructured":"Lie, W.-N. & Hsieh, H.-C. Lips detection by morphological image processing. In Proceedings of the International Conference on Signal Processing (ICSP), pp. 1084\u20131086. (1998)."},{"key":"6193_CR20","unstructured":"Stork, D., Wolff, G. & Levine, E. Neural network lipreading system for improved speech recognition. IJCNN-92 (1992)."},{"key":"6193_CR21","doi-asserted-by":"crossref","unstructured":"Duchnowski, P., Hunke, M., B\u00fcsching, D., Meier, U. & Waibel, A. Toward movement-invariant automatic lip-reading and speech recognition. In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 109\u2013112 (1995).","DOI":"10.1109\/ICASSP.1995.479285"},{"issue":"no. 5","key":"6193_CR22","doi-asserted-by":"publisher","first-page":"3275","DOI":"10.11591\/eei.v13i5.7803","volume":"13","author":"Y Amirgaliyev","year":"2024","unstructured":"Amirgaliyev, Y. et al. Application of neural networks ensemble method for the Kazakh sign language recognition. Bulletin of Electrical Engineering and Informatics 13(no. 5), 3275\u20133287, https:\/\/doi.org\/10.11591\/eei.v13i5.7803 (2024).","journal-title":"Bulletin of Electrical Engineering and Informatics"},{"key":"6193_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1515\/comp-2017-0001","volume":"7","author":"Y Amirgaliyev","year":"2017","unstructured":"Amirgaliyev, Y., Hahn, M. & Mussabayev, T. The speech signal segmentation algorithm using pitch synchronous analysis. Open Computer Science 7, 1\u20138, https:\/\/doi.org\/10.1515\/comp-2017-0001 (2017).","journal-title":"Open Computer Science"},{"key":"6193_CR24","doi-asserted-by":"publisher","unstructured":"Zhalgas, A. et al. QazLip: A Dataset of Lip Movements for Command Recognition, https:\/\/doi.org\/10.7910\/DVN\/VIP1J8, Harvard Dataverse, V1 (2025).","DOI":"10.7910\/DVN\/VIP1J8"},{"key":"6193_CR25","first-page":"101206","volume":"35","author":"\u00dc Atila","year":"2022","unstructured":"Atila, \u00dc. & Sabaz, F. Turkish lip-reading using Bi-LSTM and deep learning models. Eng. Sci. Technol. Int. J. 35, 101206 (2022).","journal-title":"Eng. Sci. Technol. Int. J."},{"key":"6193_CR26","unstructured":"Mamiyeva, G. et al. Kazakh National Corpus. Akhmet Baitursynov Institute of Linguistics. Retrieved from http:\/\/qazcorpus.kz\/ (2016)."}],"container-title":["Scientific Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41597-025-06193-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41597-025-06193-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41597-025-06193-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T12:16:11Z","timestamp":1764764171000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41597-025-06193-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,3]]},"references-count":26,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["6193"],"URL":"https:\/\/doi.org\/10.1038\/s41597-025-06193-0","relation":{},"ISSN":["2052-4463"],"issn-type":[{"value":"2052-4463","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,3]]},"assertion":[{"value":"15 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 December 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"1900"}}