{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T14:42:21Z","timestamp":1783608141484,"version":"3.55.0"},"reference-count":20,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2024,12,20]],"date-time":"2024-12-20T00:00:00Z","timestamp":1734652800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Data in Brief"],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1016\/j.dib.2024.111254","type":"journal-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T03:24:29Z","timestamp":1735097069000},"page":"111254","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":5,"special_numbering":"C","title":["LipBengal: Pioneering Bengali lip-reading dataset for pronunciation mapping through lip gestures"],"prefix":"10.1016","volume":"58","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-3108-7655","authenticated-orcid":false,"given":"Md. Tanvir Rahman","family":"Sahed","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Md. Tanjil Islam","family":"Aronno","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4839-5059","authenticated-orcid":false,"given":"Hussain","family":"Nyeem","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4703-0373","authenticated-orcid":false,"given":"Md. Abdul","family":"Wahed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tashrif","family":"Ahsan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"R Rafiul","family":"Islam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6961-8894","authenticated-orcid":false,"given":"Tareque Bashar","family":"Ovi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manab Kumar","family":"Kundu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jane Alam","family":"Sadeef","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.dib.2024.111254_bib0001","doi-asserted-by":"crossref","first-page":"121184","DOI":"10.1109\/ACCESS.2021.3107946","article-title":"Deep learning-based automated lip-reading: a survey","volume":"9","author":"Fenghour","year":"2021","journal-title":"IEEE Access"},{"issue":"5","key":"10.1016\/j.dib.2024.111254_bib0002","doi-asserted-by":"crossref","first-page":"2421","DOI":"10.1121\/1.2229005","article-title":"An audio-visual corpus for speech perception and automatic speech recognition","volume":"120","author":"Cooke","year":"2006","journal-title":"J. Acoust. Soc. Am."},{"key":"10.1016\/j.dib.2024.111254_bib0003","series-title":"Eighth International Conference on Spoken Language Processing","article-title":"AVICAR: Audio-visual speech corpus in a car environment","author":"Lee","year":"2004"},{"key":"10.1016\/j.dib.2024.111254_bib0004","series-title":"2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)","first-page":"1","article-title":"OuluVS2: A multi-view audiovisual database for non-rigid mouth motion analysis","author":"Anina","year":"2015"},{"key":"10.1016\/j.dib.2024.111254_bib0005","series-title":"Proceedings of the 29th ACM International Conference on Multimedia, Virtual Event China","first-page":"1359","article-title":"SimulLR: Simultaneous lip reading transducer with attention-guided adaptive memory","author":"Lin","year":"2021"},{"issue":"4","key":"10.1016\/j.dib.2024.111254_bib0006","first-page":"1","article-title":"Read my lips: artificial intelligence word-level arabic lipreading system","volume":"23","author":"Dweik","year":"2022","journal-title":"Egypt. Inf. J."},{"key":"10.1016\/j.dib.2024.111254_bib0007","doi-asserted-by":"crossref","unstructured":"J. S. Chung and A. Zisserman, \u201cLip Reading in the Wild,\u201d in Computer Vision \u2013 ACCV 2016, vol. 10112, S.-H. Lai, V. Lepetit, K. Nishino, and Y. Sato, Eds., in Lecture Notes in Computer Science, vol. 10112., Cham: Springer International Publishing, 2017, pp. 87\u2013103. doi: 10.1007\/978-3-319-54184-6_6.","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"10.1016\/j.dib.2024.111254_bib0008","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"6447","article-title":"Lip reading sentences in the wild","author":"Chung","year":"2017"},{"key":"10.1016\/j.dib.2024.111254_bib0009","unstructured":"T. Afouras, J. S. Chung, and A. Zisserman, \u201cLRS3-TED: a large-scale dataset for visual speech recognition,\u201d 2018, arXiv: arXiv:1809.00496. Accessed: Jun. 26, 2024. [Online]. Available: http:\/\/arxiv.org\/abs\/1809.00496"},{"key":"10.1016\/j.dib.2024.111254_bib0010","series-title":"AVSP","first-page":"93","article-title":"Design and recording of Czech speech corpus for audio-visual continuous speech recognition","author":"C\u00edsar","year":"2005"},{"key":"10.1016\/j.dib.2024.111254_bib0011","doi-asserted-by":"crossref","unstructured":"A. G. Chitu, K. Driel, and L. J. M. Rothkrantz, \u201cAutomatic lip reading in the Dutch language using active appearance models on high speed recordings,\u201d in Text, Speech and Dialogue, vol. 6231, P. Sojka, A. Hor\u00e1k, I. Kope\u010dek, and K. Pala, Eds., in Lecture Notes in Computer Science, vol. 6231., Berlin, Heidelberg: Springer Berlin Heidelberg, 2010, pp. 259\u2013266. doi: 10.1007\/978-3-642-15760-8_33.","DOI":"10.1007\/978-3-642-15760-8_33"},{"key":"10.1016\/j.dib.2024.111254_bib0012","series-title":"2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017)","first-page":"208","article-title":"Towards estimating the upper bound of visual-speech recognition: the visual lip-reading feasibility database","author":"Fernandez-Lopez","year":"2017"},{"key":"10.1016\/j.dib.2024.111254_bib0013","unstructured":"Y. B.-G. B. Le and J.-N. S.-L. Bimbot, \u201cBL-database: a French audiovisual database for speech driven lip animation systems,\u201d 2011, Accessed: Oct. 02, 2024. [Online]. Available: https:\/\/core.ac.uk\/download\/pdf\/48231634.pdf"},{"issue":"2B","key":"10.1016\/j.dib.2024.111254_bib0014","first-page":"163","article-title":"Audiovisual database of Polish speech recordings","volume":"33","author":"Igras","year":"2012","journal-title":"Stud. Inf."},{"issue":"9","key":"10.1016\/j.dib.2024.111254_bib0015","article-title":"Audio visual Arabic speech (AVAS) database for human-computer interaction applications","volume":"3","author":"Antar","year":"2013","journal-title":"Int. J. Adv. Res. Comput. Sci. Softw. Eng."},{"key":"10.1016\/j.dib.2024.111254_bib0016","doi-asserted-by":"crossref","unstructured":"V. Verkhodanova, A. Ronzhin, I. Kipyatkova, D. Ivanko, A. Karpov, and M. \u017delezn\u00fd, \u201cHAVRUS corpus: high-speed recordings of audio-visual Russian speech,\u201d in Speech and Computer, vol. 9811, A. Ronzhin, R. Potapova, and G. N\u00e9meth, Eds., in Lecture Notes in Computer Science, vol. 9811., Cham: Springer International Publishing, 2016, pp. 338\u2013345. doi: 10.1007\/978-3-319-43958-7_40.","DOI":"10.1007\/978-3-319-43958-7_40"},{"key":"10.1016\/j.dib.2024.111254_bib0017","series-title":"Proceedings of the Thirteenth Language Resources and Evaluation Conference","first-page":"1555","article-title":"RUSAVIC corpus: Russian audio-visual speech in cars","author":"Ivanko","year":"2022"},{"key":"10.1016\/j.dib.2024.111254_bib0018","unstructured":"\u201cMuAViC:AMultilingualAudio-VisualCorpusforRobustSpeechRecognition andRobustSpeech-to-TextTranslation - SciSpace Literature Review.\u201d Accessed: Dec. 09, 2024. [Online]. Available: https:\/\/typeset.io\/search"},{"key":"10.1016\/j.dib.2024.111254_bib0019","unstructured":"\u201c[1611.01599] LipNet: End-to-End Sentence-level Lipreading.\u201d Accessed: Oct. 03, 2024. [Online]. Available: https:\/\/arxiv.org\/abs\/1611.01599"},{"key":"10.1016\/j.dib.2024.111254_bib0020","unstructured":"S. Tamura et al., \u201cCENSREC-1-AV: An audio-visual corpus for noisy bimodal speech recognition\u201d."}],"container-title":["Data in Brief"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2352340924012162?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2352340924012162?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,5,7]],"date-time":"2025-05-07T13:09:49Z","timestamp":1746623389000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2352340924012162"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":20,"alternative-id":["S2352340924012162"],"URL":"https:\/\/doi.org\/10.1016\/j.dib.2024.111254","relation":{"is-supplemented-by":[{"id-type":"uri","id":"https:\/\/huggingface.co\/datasets\/tanjilaronno2024\/LipBengal\/tree\/main","asserted-by":"subject"}]},"ISSN":["2352-3409"],"issn-type":[{"value":"2352-3409","type":"print"}],"subject":[],"published":{"date-parts":[[2025,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"LipBengal: Pioneering Bengali lip-reading dataset for pronunciation mapping through lip gestures","name":"articletitle","label":"Article Title"},{"value":"Data in Brief","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.dib.2024.111254","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2024 The Author(s). Published by Elsevier Inc.","name":"copyright","label":"Copyright"}],"article-number":"111254"}}