{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,3]],"date-time":"2026-10-03T17:11:48Z","timestamp":1791047508302,"version":"4.1.0"},"reference-count":12,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"7","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2015]]},"DOI":"10.1587\/transinf.2015edl8002","type":"journal-article","created":{"date-parts":[[2015,6,30]],"date-time":"2015-06-30T22:12:15Z","timestamp":1435702335000},"page":"1430-1433","source":"Crossref","is-referenced-by-count":5,"title":["Visual Speech Recognition Using Weighted Dynamic Time Warping"],"prefix":"10.1587","volume":"E98.D","author":[{"given":"Kyungsun","family":"LEE","sequence":"first","affiliation":[{"name":"School of Electrical Engineering, Korea University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minseok","family":"KEUM","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Korea University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David K.","family":"HAN","sequence":"additional","affiliation":[{"name":"Office of Naval Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanseok","family":"KO","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Korea University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"[1] I. Matthews, T.F. Cootes, J.A. Bangham, S. Cox, and R. Harvey, \u201cExtraction of visual features for lipreading,\u201d IEEE Trans. Pattern Anal. Mach. Intell., vol.24, no.2, pp.198-213, 2002.","DOI":"10.1109\/34.982900"},{"key":"2","doi-asserted-by":"crossref","unstructured":"[2] G. Zhao, M. Barnard, and M. Pietikainen, \u201cLipreading with local spatiotemporal descriptors,\u201d IEEE Trans. Multimedia, vol.11, no.7, pp.1254-1265, 2009.","DOI":"10.1109\/TMM.2009.2030637"},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] E.-J. Ong and R. Bowden, \u201cLearning temporal signatures for lip reading,\u201d IEEE Conference on Computer Vision Workshops, Univ. of Surrey, pp.958-965, Guildford, UK, 2011.","DOI":"10.1109\/ICCVW.2011.6130355"},{"key":"4","unstructured":"[4] J.L. Newman, B.J. Theobald, and S.J. Cox, \u201cLimitations of visual speech recognition,\u201d Int. Conf. on Audio-Visual Speech Process, pp.1-4, 2010."},{"key":"5","doi-asserted-by":"crossref","unstructured":"[5] P. Viola and M.J. Jones, \u201cRobust real-time face detection,\u201d Int. J. Comput. Vision, vol.57, no.2, pp.137-154, 2004.","DOI":"10.1023\/B:VISI.0000013087.49260.fb"},{"key":"6","unstructured":"[6] Z. Niu, S. Shan, S. Yan, X. Chen, and W. Gao, \u201c2d cascaded adaboost for eye localization,\u201d International Conference on Pattern Recognition, pp.1216-1219, 2006."},{"key":"7","doi-asserted-by":"crossref","unstructured":"[7] N. Dalal and B. Triggs, \u201cHistogram of oriented gradients for human detection,\u201d IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.886-893, 2005.","DOI":"10.1109\/CVPR.2005.177"},{"key":"8","doi-asserted-by":"crossref","unstructured":"[8] T. Ojala, M. Pietikainen, and T. Maenpaa, \u201cMultiresolution gray-scale and rotation invariant texture classification with local binary patterns,\u201d IEEE Trans. Pattern Anal. Mach. Intell., vol.24, no.7, pp.971-987, 2002.","DOI":"10.1109\/TPAMI.2002.1017623"},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] Q. Li, J. Zheng, A. Tsai, and Z. Zhou, \u201cRobust endpoint detection and energy normalization for real-time speech and apeaker recognition,\u201d IEEE Trans. Speech and Audio Process., vol.10, no.3, pp.146-157, 2002.","DOI":"10.1109\/TSA.2002.1001979"},{"key":"10","doi-asserted-by":"crossref","unstructured":"[10] L. Rabiner, \u201cA tutorial on Hidden Markov Models and selected applications in speech recognition,\u201d Proc. IEEE, vol.77, no.2, pp.257-286, 1989.","DOI":"10.1109\/5.18626"},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] H. Sakoe and S. Chiba, \u201cDynamic programming algorithm optimization for spoken word recognition,\u201d IEEE Trans. Acoust. Speech Signal Process., vol.26, no.1, pp.43-49, 1978.","DOI":"10.1109\/TASSP.1978.1163055"},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] Y.-S. Jeong, M.K. Jeong, and O.A. Omitaomu, \u201cWeighted dynamic time warping for time series classification,\u201d Pattern Recognition, vol.44, no.9, pp.2231-2240, 2011.","DOI":"10.1016\/j.patcog.2010.09.022"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E98.D\/7\/E98.D_2015EDL8002\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T23:17:51Z","timestamp":1748474271000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E98.D\/7\/E98.D_2015EDL8002\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"references-count":12,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2015]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2015edl8002","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015]]}}}