{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T23:28:51Z","timestamp":1771025331015,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,12,23]],"date-time":"2022-12-23T00:00:00Z","timestamp":1671753600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100019782","name":"North South University","doi-asserted-by":"publisher","award":["NSU-RP-18-072"],"award-info":[{"award-number":["NSU-RP-18-072"]}],"id":[{"id":"10.13039\/501100019782","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,12,23]]},"DOI":"10.1145\/3579654.3579677","type":"proceedings-article","created":{"date-parts":[[2023,3,14]],"date-time":"2023-03-14T16:09:40Z","timestamp":1678810180000},"page":"1-6","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Lip Reading Bengali Words"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9996-5165","authenticated-orcid":false,"given":"Md. Masudur","family":"Rahman","sequence":"first","affiliation":[{"name":"North South University, Bangladesh"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4561-2548","authenticated-orcid":false,"given":"Md Rashad","family":"Tanjim","sequence":"additional","affiliation":[{"name":"North South University, Bangladesh"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8511-8678","authenticated-orcid":false,"given":"Saraf Sumaita","family":"Hasan","sequence":"additional","affiliation":[{"name":"North South University, Bangladesh"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6976-9123","authenticated-orcid":false,"given":"Sayeed Md.","family":"Shaiban","sequence":"additional","affiliation":[{"name":"North South University, Bangladesh"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6547-9580","authenticated-orcid":false,"given":"Mohammad Ashrafuzzaman","family":"Khan","sequence":"additional","affiliation":[{"name":"Electrical & Computer Engineering, North South University, Bangladesh"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,3,14]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1611.05358"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1611.01599"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","unstructured":"Chung J.S. and Zisserman A.P. 2017. Lip reading in profile. DOI:10.5244\/C.31.155","DOI":"10.5244\/C.31.155"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054384"},{"issue":"4","key":"e_1_3_2_1_6_1","first-page":"7","article-title":"Viseme Recognition using lip curvature and Neural Networks to detect Bangla Vowels","volume":"9","author":"Akhter N.","year":"2017","unstructured":"Akhter, N. and Chakrabarty, A., 2017. Viseme Recognition using lip curvature and Neural Networks to detect Bangla Vowels. Journal of Telecommunication, Electronic and Computer Engineering (JTEC), 9(4), pp.7-11. http:\/\/hdl.handle.net\/10361\/8366","journal-title":"Journal of Telecommunication, Electronic and Computer Engineering (JTEC)"},{"key":"e_1_3_2_1_7_1","volume-title":"Last accessed","year":"2022","unstructured":"https:\/\/www.statista.com\/statistics\/266808\/the-most-spoken-languages-worldwide\/. Last accessed September 26, 2022."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019211"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3328833.3328845"},{"issue":"3","key":"e_1_3_2_1_10_1","first-page":"116","article-title":". Visual Speech Recognition of Lips Images Using Convolutional Neural Network in VGG-M Model","volume":"11","author":"Chan Z.M.","year":"2020","unstructured":"Chan, Z.M., Lau, C.Y. and Thang, K.F., 2020. Visual Speech Recognition of Lips Images Using Convolutional Neural Network in VGG-M Model. J. Inf. Hiding Multim. Signal Process., 11(3), pp.116-125.","journal-title":"J. Inf. Hiding Multim. Signal Process."},{"key":"e_1_3_2_1_11_1","unstructured":"Hilder S. Harvey R.W. and Theobald B.J. 2009 September. Comparison of human and machine-based lip-reading. In AVSP (pp. 86-89). https:\/\/ueaeprints.uea.ac.uk\/id\/eprint\/21664."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","unstructured":"Afouras T. Chung J.S. Senior A. Vinyals O. and Zisserman A. 2018. Deep audio-visual speech recognition. IEEE transactions on pattern analysis and machine intelligence. DOI: 10.1109\/TPAMI.2018.2889052","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","unstructured":"Vaswani A. Shazeer N. Parmar N. Uszkoreit J. Jones L. Gomez A.N. Kaiser \u0141. and Polosukhin I. 2017. Attention is all you need. Advances in neural information processing systems 30. https:\/\/doi.org\/10.48550\/arXiv.1706.03762.","DOI":"10.48550\/arXiv.1706.03762"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1601.08188"},{"key":"e_1_3_2_1_15_1","volume-title":"Last accessed","year":"2022","unstructured":"https:\/\/spandh.dcs.shef.ac.uk\/gridcorpus\/. Last accessed September 26, 2022."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","unstructured":"Stafylakis T. and Tzimiropoulos G. 2017. Combining residual networks with LSTMs for lipreading. arXiv preprint arXiv:1703.04105. https:\/\/doi.org\/10.48550\/arXiv.1703.04105.","DOI":"10.48550\/arXiv.1703.04105"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1512.03385"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","unstructured":"Ephrat A. Mosseri I. Lang O. Dekel T. Wilson K. Hassidim A. Freeman W.T. and Rubinstein M. 2018. Looking to listen at the cocktail party: A speaker-independent audio-visual model for speech separation. arXiv preprint arXiv:1804.03619. https:\/\/doi.org\/10.48550\/arXiv.1804.03619.","DOI":"10.48550\/arXiv.1804.03619"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","unstructured":"Afouras T. Chung J.S. and Zisserman A. 2018. The conversation: Deep audio-visual speech enhancement. arXiv preprint arXiv:1804.04121. https:\/\/doi.org\/10.48550\/arXiv.1804.04121","DOI":"10.48550\/arXiv.1804.04121"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","unstructured":"Afouras T. Chung J.S. and Zisserman A. 2018. Deep lip reading: a comparison of models and an online application. arXiv preprint arXiv:1806.06053. https:\/\/doi.org\/10.48550\/arXiv.1806.06053.","DOI":"10.48550\/arXiv.1806.06053"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","unstructured":"Shillingford B. Assael Y. Hoffman M.W. Paine T. Hughes C. Prabhu U. Liao H. Sak H. Rao K. Bennett L. and Mulville M. 2018. Large-scale visual speech recognition. arXiv preprint arXiv:1807.05162. https:\/\/doi.org\/10.48550\/arXiv.1807.05162.","DOI":"10.48550\/arXiv.1807.05162"},{"key":"e_1_3_2_1_22_1","unstructured":"Garg A. Noyola J. and Bagadia S. 2016. Lip reading using CNN and LSTM. Technical report Stanford University CS231 n project report."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","unstructured":"Hochreiter S. and Schmidhuber J. 1997. Long short-term memory. Neural computation 9(8) pp.1735-1780. https:\/\/doi.org\/10.1162\/neco.1997.9.8.1735.","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","unstructured":"Simonyan K. and Zisserman A. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556. https:\/\/doi.org\/10.48550\/arXiv.1409.1556","DOI":"10.48550\/arXiv.1409.1556"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"}],"event":{"name":"ACAI 2022: 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence","location":"Sanya China","acronym":"ACAI 2022"},"container-title":["Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3579654.3579677","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3579654.3579677","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T07:00:31Z","timestamp":1755846031000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3579654.3579677"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,23]]},"references-count":28,"alternative-id":["10.1145\/3579654.3579677","10.1145\/3579654"],"URL":"https:\/\/doi.org\/10.1145\/3579654.3579677","relation":{},"subject":[],"published":{"date-parts":[[2022,12,23]]},"assertion":[{"value":"2023-03-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}