{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:48:44Z","timestamp":1740098924307,"version":"3.37.3"},"publisher-location":"Cham","reference-count":15,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319664286"},{"type":"electronic","value":"9783319664293"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-66429-3_77","type":"book-chapter","created":{"date-parts":[[2017,8,12]],"date-time":"2017-08-12T02:02:55Z","timestamp":1502503375000},"page":"767-776","source":"Crossref","is-referenced-by-count":2,"title":["Utilizing Lipreading in Large Vocabulary Continuous Speech Recognition"],"prefix":"10.1007","author":[{"given":"Karel","family":"Pale\u010dek","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,8,13]]},"reference":[{"unstructured":"Assael, Y.M., Shillingford, B., Whiteson, S., de Freitas, N.: Lipnet: Sentence-level lipreading. CoRR abs\/1611.01599 (2016)","key":"77_CR1"},{"unstructured":"Cao, X., Wei, Y., Wen, F., Sun, J.: Face alignment by explicit shape regression. In: CVPR (2012)","key":"77_CR2"},{"doi-asserted-by":"crossref","unstructured":"Chung, J.S., Senior, A.W., Vinyals, O., Zisserman, A.: Lip reading sentences in the wild. CoRR abs\/1611.05358 (2016)","key":"77_CR3","DOI":"10.1109\/CVPR.2017.367"},{"unstructured":"C\u00edsa\u0159, P.: Application of lipreading methods for speech recognition. Ph.D. thesis (2006)","key":"77_CR4"},{"issue":"5","key":"77_CR5","doi-asserted-by":"crossref","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."},{"doi-asserted-by":"crossref","unstructured":"Glotin, H., Vergyr, D., Neti, C., Potamianos, G., Luettin, J.: Weighting schemes for audio-visual fusion in speech recognition. In: Proceedings of the 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2001), vol. 1, pp. 173\u2013176 (2001)","key":"77_CR6","DOI":"10.1109\/ICASSP.2001.940795"},{"unstructured":"Lan, Y., Theobald, B., Harvey, R., Bowden, R.: Improving visual features for lipreading, pp. 142\u2013147 (2010)","key":"77_CR7"},{"doi-asserted-by":"crossref","unstructured":"Lee, B., Hasegawa-Johnson, M., Goudeseune, C., Kamdar, S., Borys, S., Liu, M., Huang, T.S.: AVICAR: audio-visual speech corpus in a car environment. In: 8th International Conference on Spoken Language Processing, INTERSPEECH 2004 - ICSLP, Jeju Island, Korea, 4\u20138 October 2004","key":"77_CR8","DOI":"10.21437\/Interspeech.2004-424"},{"unstructured":"Nouza, J., Psutka, J., Uhl\u00ed\u0159, J.: Phonetic alphabet for speech recognition of czech (1997)","key":"77_CR9"},{"doi-asserted-by":"crossref","unstructured":"Palecek, K.: Lipreading using spatiotemporal histogram of oriented gradients. In: EUSIPCO 2016, Budapest, Hungary, pp. 1882\u20131885 (2016)","key":"77_CR10","DOI":"10.1109\/EUSIPCO.2016.7760575"},{"doi-asserted-by":"crossref","unstructured":"Potamianos, G., Neti, C., Gravier, G., Garg, A., Senior, A.W.: Recent advances in the automatic recognition of audio-visual speech. In: Proceedings of the IEEE, pp. 1306\u20131326 (2003)","key":"77_CR11","DOI":"10.1109\/JPROC.2003.817150"},{"unstructured":"Ramage, M.D.: Disproving Visemes as the Basic Visual Unit of Speech. Ph.D. thesis (2013)","key":"77_CR12"},{"doi-asserted-by":"crossref","unstructured":"Stolcke, A.: SRILM - an extensible language modeling toolkit. In: Proceedings of ICSLP, Denver, USA, vol. 2, pp. 901\u2013904 (2002)","key":"77_CR13","DOI":"10.21437\/ICSLP.2002-303"},{"issue":"7","key":"77_CR14","doi-asserted-by":"crossref","first-page":"1254","DOI":"10.1109\/TMM.2009.2030637","volume":"11","author":"G Zhao","year":"2009","unstructured":"Zhao, G., Barnard, M., Pietik\u00e4inen, M.: Lipreading with local spatiotemporal descriptors. IEEE Trans. Multimedia 11(7), 1254\u20131265 (2009)","journal-title":"IEEE Trans. Multimedia"},{"issue":"9","key":"77_CR15","doi-asserted-by":"crossref","first-page":"590","DOI":"10.1016\/j.imavis.2014.06.004","volume":"32","author":"Z Zhou","year":"2014","unstructured":"Zhou, Z., Zhao, G., Hong, X., Pietikinen, M.: A review of recent advances in visual speech decoding. Image Vis. Comput. 32(9), 590\u2013605 (2014)","journal-title":"Image Vis. Comput."}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-66429-3_77","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,25]],"date-time":"2023-08-25T00:52:27Z","timestamp":1692924747000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-66429-3_77"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319664286","9783319664293"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-66429-3_77","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2017]]}}}