{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T23:29:41Z","timestamp":1771025381980,"version":"3.50.1"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030922696","type":"print"},{"value":"9783030922702","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-92270-2_45","type":"book-chapter","created":{"date-parts":[[2021,12,6]],"date-time":"2021-12-06T11:06:00Z","timestamp":1638788760000},"page":"526-535","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["BenAV: a\u00a0Bengali Audio-Visual Corpus for\u00a0Visual Speech Recognition"],"prefix":"10.1007","author":[{"given":"Ashish","family":"Pondit","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad Eshaque Ali","family":"Rukon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anik","family":"Das","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad Ashad","family":"Kabir","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,12,7]]},"reference":[{"key":"45_CR1","doi-asserted-by":"crossref","unstructured":"Anina, I., Zhou, Z., Zhao, G., Pietik\u00e4inen, M.: Ouluvs2: a multi-view audiovisual database for non-rigid mouth motion analysis. In: 11th International Conference and Workshops on Automatic Face and Gesture Recognition, vol. 1, pp. 1\u20135. IEEE (2015)","DOI":"10.1109\/FG.2015.7163155"},{"key":"45_CR2","unstructured":"Assael, Y.M., Shillingford, B., Whiteson, S., de Freitas, N.: Lipnet: End-to-end sentence-level lipreading. arXiv (2016)"},{"issue":"05","key":"45_CR3","doi-asserted-by":"publisher","first-page":"1266002","DOI":"10.1142\/S0218001412660024","volume":"26","author":"JR Barr","year":"2012","unstructured":"Barr, J.R., Bowyer, K.W., Flynn, P.J., Biswas, S.: Face recognition from video: a review. Int. J. Patt. Recogon. Artif. Intell. 26(05), 1266002 (2012)","journal-title":"Int. J. Patt. Recogon. Artif. Intell."},{"key":"45_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1007\/978-3-319-54184-6_6","volume-title":"Computer Vision \u2013 ACCV 2016","author":"JS Chung","year":"2017","unstructured":"Chung, J.S., Zisserman, A.: Lip reading in the wild. In: Lai, S.-H., Lepetit, V., Nishino, K., Sato, Y. (eds.) ACCV 2016. LNCS, vol. 10112, pp. 87\u2013103. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-54184-6_6"},{"issue":"5","key":"45_CR5","doi-asserted-by":"publisher","first-page":"2421","DOI":"10.1121\/1.2229005","volume":"120","author":"M Cooke","year":"2006","unstructured":"Cooke, M., Barker, J., Cunningham, S., Shao, X.: An audio-visual corpus for speech perception and automatic speech recognition. J. Acoust. Soc. Am. 120(5), 2421\u20132424 (2006)","journal-title":"J. Acoust. Soc. Am."},{"key":"45_CR6","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)","journal-title":"Image Vis. Comput."},{"key":"45_CR7","unstructured":"Hilder, S., Harvey, R.W., Theobald, B.J.: Comparison of human and machine-based lip-reading. In: International Conference on Auditory-Visual Speech Processing (AVSP), pp. 86\u201389. ISCA (2009)"},{"key":"45_CR8","doi-asserted-by":"crossref","unstructured":"Jitaru, A.C., Abdulamit, \u015e., Ionescu, B.: LRRO: a lip reading data set for the under-resourced Romanian language. In: Proceedings of the 11th ACM Multimedia Systems Conference, pp. 267\u2013272 (2020)","DOI":"10.1145\/3339825.3394932"},{"key":"45_CR9","doi-asserted-by":"crossref","unstructured":"Kazemi, V., Sullivan, J.: One millisecond face alignment with an ensemble of regression trees. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1867\u20131874. IEEE (2014)","DOI":"10.1109\/CVPR.2014.241"},{"issue":"2","key":"45_CR10","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1109\/34.982900","volume":"24","author":"I Matthews","year":"2002","unstructured":"Matthews, I., Cootes, T.F., Bangham, J.A., Cox, S., Harvey, R.: Extraction of visual features for lipreading. IEEE Trans. Patt. Anal. Mach. Intell. 24(2), 198\u2013213 (2002)","journal-title":"IEEE Trans. Patt. Anal. Mach. Intell."},{"key":"45_CR11","doi-asserted-by":"crossref","unstructured":"Noda, K., Yamaguchi, Y., Nakadai, K., Okuno, H.G., Ogata, T.: Lipreading using convolutional neural network. In: 15th Annual Conference of the International Speech Communication Association, pp. 1149\u20131153. ISCA (2014)","DOI":"10.21437\/Interspeech.2014-293"},{"key":"45_CR12","doi-asserted-by":"crossref","unstructured":"Patterson, E.K., Gurbuz, S., Tufekci, Z., Gowdy, J.N.: Cuave: A new audio-visual database for multimodal human-computer interface research. In: International Conference on Acoustics, Speech, and Signal Processing (ICASSP), vol. 2, pp. II-2017-II-2020. IEEE (2002)","DOI":"10.1109\/ICASSP.2002.1006168"},{"key":"45_CR13","doi-asserted-by":"crossref","unstructured":"Petridis, S., Stafylakis, T., Ma, P., Cai, F., Tzimiropoulos, G., Pantic, M.: End-to-end audiovisual speech recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6548\u20136552. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8461326"},{"key":"45_CR14","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1016\/j.patrec.2020.01.022","volume":"131","author":"S Petridis","year":"2020","unstructured":"Petridis, S., Wang, Y., Ma, P., Li, Z., Pantic, M.: End-to-end visual speech recognition for small-scale datasets. Patt. Recogn. Lett. 131, 421\u2013427 (2020)","journal-title":"Patt. Recogn. Lett."},{"issue":"4","key":"45_CR15","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. Exp. Syst. Appl. 38(4), 4477\u20134481 (2011)","journal-title":"Exp. Syst. Appl."},{"key":"45_CR16","doi-asserted-by":"crossref","unstructured":"Sak, H., Senior, A., Rao, K., Beaufays, F.: Fast and accurate recurrent neural network acoustic models for speech recognition. In: 16th Annual Conference of the International Speech Communication Association, pp. 1468\u20131472. ISCA (2015)","DOI":"10.21437\/Interspeech.2015-350"},{"key":"45_CR17","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1016\/j.cviu.2018.10.003","volume":"176","author":"T Stafylakis","year":"2018","unstructured":"Stafylakis, T., Khan, M.H., Tzimiropoulos, G.: Pushing the boundaries of audiovisual word recognition using residual networks and LSTMS. Comput. Vis. Image Underst. 176, 22\u201332 (2018)","journal-title":"Comput. Vis. Image Underst."},{"key":"45_CR18","doi-asserted-by":"crossref","unstructured":"Stafylakis, T., Tzimiropoulos, G.: Combining residual networks with LSTMs for lipreading. In: 18th Annual Conference of the International Speech Communication Association (INTERSPEECH), pp. 3652\u20133656. ISCA (2017)","DOI":"10.21437\/Interspeech.2017-85"},{"key":"45_CR19","doi-asserted-by":"crossref","unstructured":"Sun, K., Yu, C., Shi, W., Liu, L., Shi, Y.: Lip-interact: improving mobile device interaction with silent speech commands. In: Proceedings of the 31st Annual ACM Symposium on User Interface Software and Technology, pp. 581\u2013593. ACM (2018)","DOI":"10.1145\/3242587.3242599"},{"key":"45_CR20","doi-asserted-by":"crossref","unstructured":"Xu, B., Lu, C., Guo, Y., Wang, J.: Discriminative multi-modality speech recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14433\u201314442. IEEE (2020)","DOI":"10.1109\/CVPR42600.2020.01444"},{"key":"45_CR21","doi-asserted-by":"crossref","unstructured":"Yang, S., et al.: LRW-1000: a naturally-distributed large-scale benchmark for lip reading in the wild. In: 14th IEEE International Conference on Automatic Face and Gesture Recognition (FG), pp. 1\u20138. IEEE (2019)","DOI":"10.1109\/FG.2019.8756582"},{"key":"45_CR22","doi-asserted-by":"crossref","unstructured":"Zhao, X., Yang, S., Shan, S., Chen, X.: Mutual information maximization for effective lip reading. In: 15th International Conference on Automatic Face and Gesture Recognition (FG), pp. 420\u2013427. IEEE (2020)","DOI":"10.1109\/FG47880.2020.00133"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-92270-2_45","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T15:28:35Z","timestamp":1710257315000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-92270-2_45"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030922696","9783030922702"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-92270-2_45","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"7 December 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sanur, Bali","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Indonesia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2021.apnns.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1093","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"226","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"177","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"21% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.57","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"6","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Due to the COVID-19 pandemic the conference was held online.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}