{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T21:20:00Z","timestamp":1776979200102,"version":"3.51.4"},"reference-count":60,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T00:00:00Z","timestamp":1774915200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T00:00:00Z","timestamp":1774915200000},"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":["SIViP"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1007\/s11760-026-05252-2","type":"journal-article","created":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T09:25:54Z","timestamp":1774949154000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Challenges and enhancements in Turkish automatic lip reading using deep learning models"],"prefix":"10.1007","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5021-7337","authenticated-orcid":false,"given":"Furkan","family":"Sabaz","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1576-9977","authenticated-orcid":false,"given":"\u00dcmit","family":"Atila","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1127-515X","authenticated-orcid":false,"given":"Murat","family":"D\u00f6rterler","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2493-4022","authenticated-orcid":false,"given":"Alaettin","family":"U\u00e7an","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,3,31]]},"reference":[{"issue":"5588","key":"5252_CR1","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1038\/264746a0","volume":"264","author":"H Mcgurk","year":"1976","unstructured":"Mcgurk, H., Macdonald, J.: Hearing lips and seeing voices. Nature 264(5588), 746\u2013748 (1976). https:\/\/doi.org\/10.1038\/264746a0","journal-title":"Nature"},{"issue":"9","key":"5252_CR2","doi-asserted-by":"publisher","first-page":"1306","DOI":"10.1109\/JPROC.2003.817150","volume":"91","author":"G Potamianos","year":"2003","unstructured":"Potamianos, G., Neti, C., Gravier, G., Garg, A., Senior, A.W.: Recent advances in the automatic recognition of audiovisual speech. Proc. IEEE 91(9), 1306\u20131326 (2003). https:\/\/doi.org\/10.1109\/JPROC.2003.817150","journal-title":"Proc. IEEE"},{"key":"5252_CR3","unstructured":"G. POTAMIANOS, \u2018Audio-visual automatic speech recognition\u202f: An over-view\u2019, Visual and Audio-Visual. Speech Processing, 2004, Accessed: Nov. 29, 2024. [Online]. Available: https:\/\/cir.nii.ac.jp\/crid\/1572261550687214976"},{"issue":"10","key":"5252_CR4","doi-asserted-by":"publisher","first-page":"2387","DOI":"10.1093\/cercor\/bhl147","volume":"17","author":"JI Skipper","year":"2007","unstructured":"Skipper, J.I., van Wassenhove, V., Nusbaum, H.C., Small, S.L.: Hearing lips and seeing voices: how cortical areas supporting speech production mediate audiovisual speech perception. Cereb. Cortex 17(10), 2387\u20132399 (2007). https:\/\/doi.org\/10.1093\/cercor\/bhl147","journal-title":"Cereb. Cortex"},{"key":"5252_CR5","doi-asserted-by":"publisher","unstructured":"Werda S., Mahdi W., and Hamadou A. B.: Lip Localization and Viseme Classification for Visual Speech Recognition\u2019, Jan. 19, 2013, arXiv: arXiv:1301.4558. https:\/\/doi.org\/10.48550\/arXiv.1301.4558.","DOI":"10.48550\/arXiv.1301.4558"},{"issue":"2","key":"5252_CR6","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1121\/1.1907309","volume":"26","author":"WH Sumby","year":"1954","unstructured":"Sumby, W.H., Pollack, I.: Visual contribution to speech intelligibility in noise. J. Acoust. Soc. Am. 26(2), 212\u2013215 (1954). https:\/\/doi.org\/10.1121\/1.1907309","journal-title":"J. Acoust. Soc. Am."},{"issue":"4","key":"5252_CR7","doi-asserted-by":"publisher","first-page":"481","DOI":"10.1044\/jshd.4004.481","volume":"40","author":"NP Erber","year":"1975","unstructured":"Erber, N.P.: Auditory-visual perception of speech. J. Speech Hear. Disord. 40(4), 481\u2013492 (1975). https:\/\/doi.org\/10.1044\/jshd.4004.481","journal-title":"J. Speech Hear. Disord."},{"key":"5252_CR8","unstructured":"Hilder S., Harvey R., and Theobald B.-J.: Comparison of human and machine-based lip-reading: AVSP 2009\u2019, pp. 86\u201389 (2009)"},{"issue":"6","key":"5252_CR9","doi-asserted-by":"publisher","first-page":"1601","DOI":"10.3758\/APP.72.6.1601","volume":"72","author":"RE Ronquest","year":"2010","unstructured":"Ronquest, R.E., Levi, S.V., Pisoni, D.B.: Language identification from visual-only speech signals. Atten. Percept. Psychophys. 72(6), 1601\u20131613 (2010). https:\/\/doi.org\/10.3758\/APP.72.6.1601","journal-title":"Atten. Percept. Psychophys."},{"key":"5252_CR10","doi-asserted-by":"publisher","unstructured":"R. Bowden et al., \u2018Recent developments in automated lip-reading\u2019, in Optics and Photonics for Counterterrorism, Crime Fighting and Defence IX; and Optical Materials and Biomaterials in Security and Defence Systems Technology X, SPIE, Oct. 2013, pp. 179\u2013191. https:\/\/doi.org\/10.1117\/12.2029464.","DOI":"10.1117\/12.2029464"},{"issue":"3","key":"5252_CR11","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1109\/6046.865479","volume":"2","author":"S Dupont","year":"2000","unstructured":"Dupont, S., Luettin, J.: Audio-visual speech modeling for continuous speech recognition. IEEE Trans. Multimed. 2(3), 141\u2013151 (2000). https:\/\/doi.org\/10.1109\/6046.865479","journal-title":"IEEE Trans. Multimed."},{"key":"5252_CR12","doi-asserted-by":"publisher","unstructured":"Antonakos E., Roussos A., and Zafeiriou S.: A survey on mouth modeling and analysis for Sign Language recognition. In: 2015 11th IEEE international conference and workshops on automatic face and gesture recognition (FG), May 2015, pp. 1\u20137. https:\/\/doi.org\/10.1109\/FG.2015.7163162.","DOI":"10.1109\/FG.2015.7163162"},{"key":"5252_CR13","doi-asserted-by":"publisher","unstructured":"A. Ephrat and S. Peleg, \u2018Vid2speech: Speech reconstruction from silent video\u2019, in 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Mar. 2017, pp. 5095\u20135099. https:\/\/doi.org\/10.1109\/ICASSP.2017.7953127.","DOI":"10.1109\/ICASSP.2017.7953127"},{"key":"5252_CR14","doi-asserted-by":"publisher","first-page":"794","DOI":"10.1109\/ACCESS.2017.2649838","volume":"5","author":"B-S Lin","year":"2017","unstructured":"Lin, B.-S., Yao, Y.-H., Liu, C.-F., Lien, C.-F., Lin, B.-S.: Development of novel lip-reading recognition algorithm. IEEE Access 5, 794\u2013801 (2017). https:\/\/doi.org\/10.1109\/ACCESS.2017.2649838","journal-title":"IEEE Access"},{"key":"5252_CR15","doi-asserted-by":"publisher","unstructured":"Jain A., and Rathna G. N.: Lip reading using simple dynamic features and a novel ROI for feature extraction. In: Proceedings of the 2018 International Conference on Signal Processing and Machine Learning, in SPML \u201918. New York, NY, USA: Association for Computing Machinery, Kas\u0131m (2018), pp. 73\u201377. https:\/\/doi.org\/10.1145\/3297067.3297083.","DOI":"10.1145\/3297067.3297083"},{"key":"5252_CR16","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1007\/978-3-319-14364-4_22","volume-title":"Advances in Visual Computing","author":"HL Bear","year":"2014","unstructured":"Bear, H.L., Harvey, R.W., Theobald, B.-J., Lan, Y.: \u2018Which phoneme-to-viseme maps best improve visual-only computer lip-reading?\u2019 In: Bebis, G., Boyle, R., Parvin, B., Koracin, D., McMahan, R., Jerald, J., Zhang, H., Drucker, S.M., Kambhamettu, C., Choubassi, M.E., Deng, Z., Carlson, M. (eds.) Advances in Visual Computing, pp. 230\u2013239. Springer International Publishing, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-14364-4_22"},{"issue":"2","key":"5252_CR17","doi-asserted-by":"publisher","first-page":"488","DOI":"10.1017\/S1138741600004492","volume":"11","author":"I de los R. R. Ortiz","year":"2008","unstructured":"de los R. R. Ortiz, I.: Lipreading in the prelingually deaf: what makes a skilled speechreader? Span. J. Psychol. 11(2), 488\u2013502 (2008). https:\/\/doi.org\/10.1017\/S1138741600004492","journal-title":"Span. J. Psychol."},{"key":"5252_CR18","unstructured":"Chitu A. and Rothkrantz L.,: The influence of video sampling rate on lipreading performance\u2019, Mar. 2012."},{"key":"5252_CR19","doi-asserted-by":"publisher","unstructured":"Aran L. R., Wong F., and Yi L. P.: A review on methods and classifiers in lip reading. In: 2017 IEEE 2nd International Conference on Automatic Control and Intelligent Systems (I2CACIS), Oct. 2017, pp. 196\u2013201. https:\/\/doi.org\/10.1109\/I2CACIS.2017.8239057.","DOI":"10.1109\/I2CACIS.2017.8239057"},{"key":"5252_CR20","unstructured":"Saitoh T. and Konishi R.: A study of influence of word lip reading by change of frame rate\u2019, presented at the AVSP .., 2010. Accessed: Nov. 29, 2024. [Online]. Available: https:\/\/www.semanticscholar.org\/paper\/A-study-of-influence-of-word-lip-reading-by-change-Saitoh-Konishi\/2ac33767a0d9a47845d4b7151362d67fa8b11fed"},{"key":"5252_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.jestch.2022.101206","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). https:\/\/doi.org\/10.1016\/j.jestch.2022.101206","journal-title":"Eng. Sci. Technol. Int. J."},{"issue":"4","key":"5252_CR22","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1016\/j.vrih.2023.06.011","volume":"6","author":"S Xue","year":"2024","unstructured":"Xue, S., Gao, L., Wan, L., Feng, W.: Multi-scale context-aware network for continuous sign language recognition. Virtual Real. Intell. Hardw. 6(4), 323\u2013337 (2024). https:\/\/doi.org\/10.1016\/j.vrih.2023.06.011","journal-title":"Virtual Real. Intell. Hardw."},{"issue":"2","key":"5252_CR23","doi-asserted-by":"publisher","DOI":"10.46238\/jobda.1100903","volume":"5","author":"H Pourmousa","year":"2022","unstructured":"Pourmousa, H., \u00d6zen, \u00dc.: Lip reading using CNN for Turkish numbers. JOBDA 5(2), 2 (2022). https:\/\/doi.org\/10.46238\/jobda.1100903","journal-title":"JOBDA"},{"issue":"1","key":"5252_CR24","doi-asserted-by":"publisher","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(1), 1 (2023). https:\/\/doi.org\/10.3390\/data8010015","journal-title":"Data"},{"issue":"4","key":"5252_CR25","doi-asserted-by":"publisher","first-page":"4477","DOI":"10.1016\/j.eswa.2010.09.119","volume":"38","author":"N Puviarasan","year":"2011","unstructured":"Puviarasan, N., Palanivel, S.: Lip reading of hearing impaired persons using HMM. Expert Syst. Appl. 38(4), 4477\u20134481 (2011). https:\/\/doi.org\/10.1016\/j.eswa.2010.09.119","journal-title":"Expert Syst. Appl."},{"issue":"18","key":"5252_CR26","doi-asserted-by":"publisher","first-page":"5181","DOI":"10.1016\/j.ijleo.2014.05.011","volume":"125","author":"SS Morade","year":"2014","unstructured":"Morade, S.S., Patnaik, S.: A novel lip reading algorithm by using localized ACM and HMM: tested for digit recognition. Optik 125(18), 5181\u20135186 (2014). https:\/\/doi.org\/10.1016\/j.ijleo.2014.05.011","journal-title":"Optik"},{"issue":"2","key":"5252_CR27","doi-asserted-by":"publisher","first-page":"1531","DOI":"10.32604\/cmc.2021.016509","volume":"68","author":"A Sarhan","year":"2021","unstructured":"Sarhan, A., Elshennawy, N., Ibrahim, D.: HLR-Net: a hybrid lip-reading model based on deep convolutional neural networks. CMC 68(2), 1531\u20131549 (2021). https:\/\/doi.org\/10.32604\/cmc.2021.016509","journal-title":"CMC"},{"key":"5252_CR28","doi-asserted-by":"publisher","unstructured":"Stafylakis T., and Tzimiropoulos G.: Combining residual networks with LSTMs for Lipreading\u2019, Sep. 08, 2017, arXiv: arXiv:1703.04105. https:\/\/doi.org\/10.48550\/arXiv.1703.04105.","DOI":"10.48550\/arXiv.1703.04105"},{"key":"5252_CR29","doi-asserted-by":"publisher","first-page":"36","DOI":"10.21437\/AVSP.2017-8","volume":"2017","author":"S Petridis","year":"2017","unstructured":"Petridis, S., Wang, Y., Li, Z., Pantic, M.: \u2018End-to-End Audiovisual Fusion with LSTMs\u2019, presented at the Proc. AVSP 2017, 36\u201340 (2017). https:\/\/doi.org\/10.21437\/AVSP.2017-8","journal-title":"AVSP"},{"issue":"9","key":"5252_CR30","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-025-04178-5","volume":"19","author":"ABY Awan","year":"2025","unstructured":"Awan, A.B.Y., Zhang, T., Younas, N., Zhao, X., Fahad, M., Geng, Y.: Lips movement detection and conversion into text using deep learning-based CNN model. SIViP 19(9), 691 (2025). https:\/\/doi.org\/10.1007\/s11760-025-04178-5","journal-title":"SIViP"},{"issue":"8","key":"5252_CR31","doi-asserted-by":"publisher","DOI":"10.3390\/app15084142","volume":"15","author":"Y Ma","year":"2025","unstructured":"Ma, Y., Sun, X.: Spatiotemporal feature enhancement for lip-reading: A survey. Appl. Sci. 15(8), 4142 (2025). https:\/\/doi.org\/10.3390\/app15084142","journal-title":"Appl. Sci."},{"issue":"8","key":"5252_CR32","doi-asserted-by":"publisher","DOI":"10.3390\/s25082366","volume":"25","author":"X Zhang","year":"2025","unstructured":"Zhang, X., et al.: A novel approach for visual speech recognition using the partition-time masking and Swin Transformer 3D convolutional model. Sensors 25(8), 2366 (2025). https:\/\/doi.org\/10.3390\/s25082366","journal-title":"Sensors"},{"issue":"2","key":"5252_CR33","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-024-01627-y","volume":"31","author":"F Xue","year":"2025","unstructured":"Xue, F., Li, P., Li, Y., Li, S.: WPELip: enhance lip reading with word-prior information. Multim. Syst. 31(2), 84 (2025). https:\/\/doi.org\/10.1007\/s00530-024-01627-y","journal-title":"Multim. Syst."},{"key":"5252_CR34","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112430","volume":"304","author":"OE Ogri","year":"2024","unstructured":"Ogri, O.E., EL-Mekkaoui, J., Benslimane, M., Hjouji, A.: Automatic lip-reading classification using deep learning approaches and optimized quaternion Meixner moments by GWO algorithm. Knowl. Based Syst. 304, 112430 (2024). https:\/\/doi.org\/10.1016\/j.knosys.2024.112430","journal-title":"Knowl. Based Syst."},{"issue":"9","key":"5252_CR35","doi-asserted-by":"publisher","first-page":"6001","DOI":"10.1109\/TPAMI.2024.3376710","volume":"46","author":"C Sheng","year":"2024","unstructured":"Sheng, C., et al.: Deep learning for visual speech analysis: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 46(9), 6001\u20136022 (2024). https:\/\/doi.org\/10.1109\/TPAMI.2024.3376710","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"5252_CR36","doi-asserted-by":"publisher","first-page":"1957","DOI":"10.1007\/s00371-024-03515-y","volume":"41","author":"H Wang","year":"2025","unstructured":"Wang, H., Cui, B., Yuan, Q., Pu, G., Liu, X., Zhu, J.: Mini-3DCvT: a lightweight lip-reading method based on 3D convolution visual transformer. Vis. Comput. 41(3), 1957\u20131969 (2025). https:\/\/doi.org\/10.1007\/s00371-024-03515-y","journal-title":"Vis. Comput."},{"issue":"6","key":"5252_CR37","doi-asserted-by":"publisher","DOI":"10.3390\/a16060269","volume":"16","author":"T Arakane","year":"2023","unstructured":"Arakane, T., Saitoh, T.: Efficient DNN model for word lip-reading. Algorithms 16(6), 269 (2023). https:\/\/doi.org\/10.3390\/a16060269","journal-title":"Algorithms"},{"key":"5252_CR38","doi-asserted-by":"publisher","unstructured":"Wang H., Guo P., Wan X., Zhou H., and Xie L.: Enhancing lip reading with multi-scale video and multi-encoder. In: 2024 IEEE International Conference on Multimedia and Expo Workshops (ICMEW), Niagara Falls, ON, Canada: IEEE, Jul. 2024, pp. 1\u20136. https:\/\/doi.org\/10.1109\/ICMEW63481.2024.10645400.","DOI":"10.1109\/ICMEW63481.2024.10645400"},{"key":"5252_CR39","doi-asserted-by":"publisher","first-page":"3657","DOI":"10.21437\/Interspeech.2017-106","volume":"2017","author":"K Thangthai","year":"2017","unstructured":"Thangthai, K., Harvey, R.: \u2018Improving computer lipreading via DNN sequence discriminative training techniques\u2019, presented at the Proc. Interspeech 2017, 3657\u20133661 (2017). https:\/\/doi.org\/10.21437\/Interspeech.2017-106","journal-title":"Interspeech"},{"key":"5252_CR40","unstructured":"Huyen C.T.: German word level lip reading with deep learning. Thesis, Hochschule f\u00fcr angewandte Wissenschaften Hamburg, 2019. Accessed: Nov. 29, 2024. [Online]. Available: https:\/\/reposit.haw-hamburg.de\/handle\/20.500.12738\/8807"},{"issue":"5","key":"5252_CR41","doi-asserted-by":"publisher","first-page":"981","DOI":"10.1007\/s11760-019-01630-1","volume":"14","author":"X Chen","year":"2020","unstructured":"Chen, X., Du, J., Zhang, H.: Lipreading with DenseNet and resBi-LSTM. SIViP 14(5), 981\u2013989 (2020). https:\/\/doi.org\/10.1007\/s11760-019-01630-1","journal-title":"SIViP"},{"issue":"3","key":"5252_CR42","doi-asserted-by":"publisher","first-page":"559","DOI":"10.1016\/j.patcog.2010.09.011","volume":"44","author":"J Shin","year":"2011","unstructured":"Shin, J., Lee, J., Kim, D.: Real-time lip reading system for isolated Korean word recognition. Pattern Recogn. 44(3), 559\u2013571 (2011). https:\/\/doi.org\/10.1016\/j.patcog.2010.09.011","journal-title":"Pattern Recogn."},{"key":"5252_CR43","doi-asserted-by":"publisher","unstructured":"Kurniawan A. and Suyanto S.: Syllable-based Indonesian lip reading model. In: 2020 8th International Conference on Information and Communication Technology (ICoICT), Jun. (2020) pp. 1\u20136. https:\/\/doi.org\/10.1109\/ICoICT49345.2020.9166217.","DOI":"10.1109\/ICoICT49345.2020.9166217"},{"issue":"1","key":"5252_CR44","doi-asserted-by":"publisher","DOI":"10.1155\/mse\/2087573","volume":"2025","author":"PN Huu","year":"2025","unstructured":"Huu, P.N., Sy, T.H.: A novel sentence\u2010level visual speech recognition system for Vietnamese language using ResNet3D and Zipformer. Model. Simul. Eng. 2025(1), 2087573 (2025). https:\/\/doi.org\/10.1155\/mse\/2087573","journal-title":"Model. Simul. Eng."},{"key":"5252_CR45","doi-asserted-by":"publisher","first-page":"24906","DOI":"10.1109\/ACCESS.2025.3531640","volume":"13","author":"A Baloch","year":"2025","unstructured":"Baloch, A., Ali, M., Hussain, L., Sadiq, T., Alkahtani, B.S.: Urdu lip reading systems for digits in controlled and uncontrolled environment. IEEE Access 13, 24906\u201324927 (2025). https:\/\/doi.org\/10.1109\/ACCESS.2025.3531640","journal-title":"IEEE Access"},{"key":"5252_CR46","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2024.111254","volume":"58","author":"MTR Sahed","year":"2025","unstructured":"Sahed, M.T.R., et al.: LipBengal: pioneering Bengali lip-reading dataset for pronunciation mapping through lip gestures. Data Brief 58, 111254 (2025). https:\/\/doi.org\/10.1016\/j.dib.2024.111254","journal-title":"Data Brief"},{"issue":"4","key":"5252_CR47","doi-asserted-by":"publisher","first-page":"1519","DOI":"10.1007\/s40998-024-00756-4","volume":"48","author":"A Gholipour","year":"2024","unstructured":"Gholipour, A., Mohammadzade, H., Ghadami, A., Taheri, A.: Automatic lip reading of Persian words by a robotic system using deep learning algorithms. Iran. J. Sci. Technol. Trans. E Electr. Eng. 48(4), 1519\u20131538 (2024). https:\/\/doi.org\/10.1007\/s40998-024-00756-4","journal-title":"Iran. J. Sci. Technol. Trans. E Electr. Eng."},{"issue":"10","key":"5252_CR48","doi-asserted-by":"publisher","first-page":"2645","DOI":"10.1049\/ipr2.13123","volume":"18","author":"Y Xiao","year":"2024","unstructured":"Xiao, Y., Liu, X., Teng, L., Zhu, A., Tian, P., Huang, J.: Cantonese sentence dataset for lip\u2010reading. IET Image Process. 18(10), 2645\u20132664 (2024). https:\/\/doi.org\/10.1049\/ipr2.13123","journal-title":"IET Image Process."},{"issue":"1","key":"5252_CR49","doi-asserted-by":"publisher","first-page":"6479124","DOI":"10.1155\/2024\/6479124","volume":"2024","author":"Aripin","year":"2024","unstructured":"Aripin, Setiawan A.: Indonesian lip-reading detection and recognition based on lip shape using face mesh and long-term recurrent convolutional network. Appl. Comput. Intell. Soft Comput. 2024(1), 6479124 (2024). https:\/\/doi.org\/10.1155\/2024\/6479124","journal-title":"Appl. Comput. Intell. Soft Comput."},{"issue":"27","key":"5252_CR50","doi-asserted-by":"publisher","first-page":"69989","DOI":"10.1007\/s11042-024-18237-5","volume":"83","author":"A Baaloul","year":"2024","unstructured":"Baaloul, A., Benblidia, N., Reguieg, F.Z., Bouakkaz, M., Felouat, H.: An Arabic visual speech recognition framework with CNN and vision transformers for lipreading. Multimed. Tools Appl. 83(27), 69989\u201370023 (2024). https:\/\/doi.org\/10.1007\/s11042-024-18237-5","journal-title":"Multimed. Tools Appl."},{"key":"5252_CR51","doi-asserted-by":"publisher","unstructured":"Yao Y.: Study on Chinese lip reading recognition algorithm based on mixed decoding strategy with conformer architecture. In: 2024 5th International Conference on Artificial Intelligence and Computer Engineering (ICAICE), Wuhu, China: IEEE, Nov. 2024, pp. 426\u2013430. https:\/\/doi.org\/10.1109\/ICAICE63571.2024.10864299.","DOI":"10.1109\/ICAICE63571.2024.10864299"},{"key":"5252_CR52","doi-asserted-by":"publisher","first-page":"111611","DOI":"10.1109\/ACCESS.2024.3440646","volume":"12","author":"Z Jabr","year":"2024","unstructured":"Jabr, Z., Etemadi, S., Mozayani, N.: Arabic lip reading with limited data using deep learning. IEEE Access 12, 111611\u2013111626 (2024). https:\/\/doi.org\/10.1109\/ACCESS.2024.3440646","journal-title":"IEEE Access"},{"key":"5252_CR53","doi-asserted-by":"publisher","unstructured":"Yarg\u0131\u00e7 A., Do\u011fan M.: A lip reading application on MS Kinect camera. In: 2013 IEEE INISTA, pp. 1\u20135 (2013). https:\/\/doi.org\/10.1109\/INISTA.2013.6577656.","DOI":"10.1109\/INISTA.2013.6577656"},{"issue":"3","key":"5252_CR54","doi-asserted-by":"publisher","DOI":"10.35378\/gujs.1239207","volume":"37","author":"A Berkol","year":"2024","unstructured":"Berkol, A., Sivri, T.T., Erdem, H.: Lip reading using various deep learning models with visual Turkish data. Gazi Univ. J. Sci. 37(3), 3 (2024). https:\/\/doi.org\/10.35378\/gujs.1239207","journal-title":"Gazi Univ. J. Sci."},{"issue":"2","key":"5252_CR55","doi-asserted-by":"publisher","DOI":"10.3390\/app15020563","volume":"15","author":"A Erbey","year":"2025","unstructured":"Erbey, A., Bar\u0131\u015f\u00e7\u0131, N.: Lip-reading classification of Turkish digits using ensemble learning architecture based on 3DCNN. Appl. Sci. 15(2), 563 (2025). https:\/\/doi.org\/10.3390\/app15020563","journal-title":"Appl. Sci."},{"key":"5252_CR56","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/j.imavis.2018.07.002","volume":"78","author":"A Fernandez-Lopez","year":"2018","unstructured":"Fernandez-Lopez, A., Sukno, F.M.: Survey on automatic lip-reading in the era of deep learning. Image Vis. Comput. 78, 53\u201372 (2018). https:\/\/doi.org\/10.1016\/j.imavis.2018.07.002","journal-title":"Image Vis. Comput."},{"key":"5252_CR57","doi-asserted-by":"publisher","first-page":"204518","DOI":"10.1109\/ACCESS.2020.3036865","volume":"8","author":"M Hao","year":"2020","unstructured":"Hao, M., Mamut, M., Yadikar, N., Aysa, A., Ubul, K.: A survey of research on lipreading technology. IEEE Access 8, 204518\u2013204544 (2020). https:\/\/doi.org\/10.1109\/ACCESS.2020.3036865","journal-title":"IEEE Access"},{"key":"5252_CR58","doi-asserted-by":"publisher","first-page":"2679","DOI":"10.21437\/Interspeech.2008-664","volume":"2008","author":"P Lucey","year":"2008","unstructured":"Lucey, P., Sridharan, S., Dean, D.: \u2018Continuous pose-invariant lipreading\u2019, presented at the Proc. Interspeech 2008, 2679\u20132682 (2008). https:\/\/doi.org\/10.21437\/Interspeech.2008-664","journal-title":"Interspeech"},{"issue":"4","key":"5252_CR59","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1016\/j.ipm.2009.03.002","volume":"45","author":"M Sokolova","year":"2009","unstructured":"Sokolova, M., Lapalme, G.: A systematic analysis of performance measures for classification tasks. Inf. Process. Manag. 45(4), 427\u2013437 (2009). https:\/\/doi.org\/10.1016\/j.ipm.2009.03.002","journal-title":"Inf. Process. Manag."},{"key":"5252_CR60","unstructured":"Dursuno\u011flu H.: Adlandirma, Terimler ve S\u0131n\u0131fland\u0131rma A\u00e7\u0131s\u0131ndan T\u00fcrkiye T\u00fcrk\u00e7esinde \u00dcns\u00fczlere Bir Bak\u0131\u015f\u2019, TDAY - Belleten, vol. 65, no. 1, Art. no. 1, (2017)"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-026-05252-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-026-05252-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-026-05252-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T20:32:19Z","timestamp":1776976339000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-026-05252-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,31]]},"references-count":60,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["5252"],"URL":"https:\/\/doi.org\/10.1007\/s11760-026-05252-2","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,31]]},"assertion":[{"value":"31 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 December 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 February 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 March 2026","order":4,"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":"Conflict of interest"}}],"article-number":"237"}}