{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:50:22Z","timestamp":1742914222707,"version":"3.40.3"},"publisher-location":"Cham","reference-count":14,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319642055"},{"type":"electronic","value":"9783319642062"}],"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":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-64206-2_49","type":"book-chapter","created":{"date-parts":[[2017,7,28]],"date-time":"2017-07-28T14:21:48Z","timestamp":1501251708000},"page":"438-446","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Spatiotemporal Convolutional Features for Lipreading"],"prefix":"10.1007","author":[{"given":"Karel","family":"Pale\u010dek","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,7,29]]},"reference":[{"key":"49_CR1","unstructured":"Assael, Y.M., Shillingford, B., Whiteson, S., de Freitas, N.: LipNet: sentence-level lipreading. CoRR abs\/1611.01599 (2016). http:\/\/arxiv.org\/abs\/1611.01599"},{"key":"49_CR2","unstructured":"Chung, J.S., Senior, A.W., Vinyals, O., Zisserman, A.: Lip reading sentences in the wild. CoRR abs\/1611.05358 (2016). http:\/\/arxiv.org\/abs\/1611.05358"},{"key":"49_CR3","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014, pp. 1725\u20131732. IEEE Computer Society, Washington, DC (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"49_CR4","doi-asserted-by":"crossref","unstructured":"Kazemi, V., Sullivan, J.: One millisecond face alignment with an ensemble of regression trees. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014, Columbus, OH, USA, 23\u201328 June 2014, pp. 1867\u20131874 (2014)","DOI":"10.1109\/CVPR.2014.241"},{"key":"49_CR5","first-page":"1755","volume":"10","author":"DE King","year":"2009","unstructured":"King, D.E.: Dlib-ml: a machine learning toolkit. J. Mach. Learn. Res. 10, 1755\u20131758 (2009)","journal-title":"J. Mach. Learn. Res."},{"key":"49_CR6","unstructured":"Ngiam, J., Khosla, A., Kim, M., Nam, J., Lee, H., Ng, A.Y.: Multimodal deep learning. In: Proceedings of the 28th International Conference on Machine Learning, ICML 2011, Bellevue, Washington, USA, 28 June\u20132 July 2011, pp. 689\u2013696 (2011)"},{"key":"49_CR7","doi-asserted-by":"crossref","unstructured":"Noda, K., Yamaguchi, Y., Nakadai, K., Okuno, H., Ogata, T.: Lipreading using convolutional neural network. In: International Speech and Communication Association, pp. 1149\u20131153 (2014)","DOI":"10.21437\/Interspeech.2014-293"},{"key":"49_CR8","unstructured":"Nouza, J., Psutka, J., Uhl\u00ed\u0159, J.: Phonetic alphabet for speech recognition of Czech (1997)"},{"key":"49_CR9","doi-asserted-by":"crossref","unstructured":"Palecek, K.: Lipreading using spatiotemporal histogram of oriented gradients. In: EUSIPCO 2016, Budapest, Hungary, pp. 1882\u20131885 (2016)","DOI":"10.1109\/EUSIPCO.2016.7760575"},{"key":"49_CR10","doi-asserted-by":"crossref","unstructured":"Pei, Y., Kim, T., Zha, H.: Unsupervised random forest manifold alignment for lipreading. In: IEEE International Conference on Computer Vision, Sydney, Australia, pp. 129\u2013136 (2013)","DOI":"10.1109\/ICCV.2013.23"},{"key":"49_CR11","unstructured":"Ramage, M.D.: Disproving visemes as the basic visual unit of speech (2013). http:\/\/www.mramage.id.au\/phd"},{"key":"49_CR12","doi-asserted-by":"crossref","unstructured":"Wand, M., Koutn\u00edk, J., Schmidhuber, J.: Lipreading with long short-term memory. CoRR abs\/1601.08188 (2016). http:\/\/arxiv.org\/abs\/1601.08188","DOI":"10.1109\/ICASSP.2016.7472852"},{"issue":"7","key":"49_CR13","doi-asserted-by":"publisher","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":"49_CR14","doi-asserted-by":"publisher","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 Vision Comput. 32(9), 590\u2013605 (2014)","journal-title":"Image Vision Comput."}],"container-title":["Lecture Notes in Computer Science","Text, Speech, and Dialogue"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-64206-2_49","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T12:43:07Z","timestamp":1710333787000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-64206-2_49"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319642055","9783319642062"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-64206-2_49","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2017]]},"assertion":[{"value":"29 July 2017","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"TSD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Text, Speech, and Dialogue","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Prague","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czech Republic","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2017","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 August 2017","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 August 2017","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"tsd2017","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.tsdconference.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}