{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:21:16Z","timestamp":1750306876892,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":9,"publisher":"ACM","license":[{"start":{"date-parts":[[2012,6,6]],"date-time":"2012-06-06T00:00:00Z","timestamp":1338940800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100004963","name":"Seventh Framework Programme","doi-asserted-by":"publisher","award":["FP7-PEOPLE-2009-RG-247948 grant AVISPIRE"],"award-info":[{"award-number":["FP7-PEOPLE-2009-RG-247948 grant AVISPIRE"]}],"id":[{"id":"10.13039\/501100004963","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000144","name":"Division of Computer and Network Systems","doi-asserted-by":"publisher","award":["NSF-CNS 1035913NSF-CNS 0923494"],"award-info":[{"award-number":["NSF-CNS 1035913NSF-CNS 0923494"]}],"id":[{"id":"10.13039\/100000144","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2012,6,6]]},"DOI":"10.1145\/2413097.2413100","type":"proceedings-article","created":{"date-parts":[[2012,12,17]],"date-time":"2012-12-17T15:12:21Z","timestamp":1355757141000},"page":"1-4","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":18,"title":["Audio-visual speech recognition using depth information from the Kinect in noisy video conditions"],"prefix":"10.1145","author":[{"given":"Georgios","family":"Galatas","sequence":"first","affiliation":[{"name":"University of Texas at Arlington, Arlington, Texas and Inst. of Informatics & Telecom, Athens, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gerasimos","family":"Potamianos","sequence":"additional","affiliation":[{"name":"University of Thessaly, Volos, Greece and Inst. of Informatics & Telecom, Athens, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fillia","family":"Makedon","sequence":"additional","affiliation":[{"name":"University of Texas at Arlington, Arlington, Texas"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2012,6,6]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"187","volume-title":"Proc. of HSC","author":"Iwano K.","year":"2001","unstructured":"K. Iwano , S. Tamura , and S. Furui , \" Bimodal speech recognition using lip movement measured by optical-flow analysis \", in Proc. of HSC , 2001 , pp. 187 -- 190 . K. Iwano, S. Tamura, and S. Furui, \"Bimodal speech recognition using lip movement measured by optical-flow analysis\", in Proc. of HSC, 2001, pp. 187--190."},{"key":"e_1_3_2_1_2_1","first-page":"20","volume-title":"Proc. of ICSLP","author":"Nakamura H. I.","year":"2000","unstructured":"H. I. Nakamura and K. Shikano , \" Stream weight optimization of speech and lip image sequence for audio-visual speech recognition \", in Proc. of ICSLP , 2000 , vol. III , pp. 20 -- 24 . H. I. Nakamura and K. Shikano, \"Stream weight optimization of speech and lip image sequence for audio-visual speech recognition\", in Proc. of ICSLP, 2000, vol. III, pp. 20--24."},{"key":"e_1_3_2_1_3_1","first-page":"103","volume-title":"Proc. of AVSP","author":"Galatas G.","year":"2011","unstructured":"G. Galatas , G. Potamianos , D. Kosmopoulos , C. McMurrough , and F. Makedon , \" Bilingual corpus for AVASR using multiple sensors and depth information \", in Proc. of AVSP , 2011 , pp. 103 -- 106 . G. Galatas, G. Potamianos, D. Kosmopoulos, C. McMurrough, and F. Makedon, \"Bilingual corpus for AVASR using multiple sensors and depth information\", in Proc. of AVSP, 2011, pp. 103--106."},{"key":"e_1_3_2_1_4_1","volume-title":"Audio-visual speech recognition incorporating facial depth information captured by the Kinect\", submitted to EUSIPCO","author":"Galatas G.","year":"2012","unstructured":"G. Galatas , G. Potamianos and F. Makedon , \" Audio-visual speech recognition incorporating facial depth information captured by the Kinect\", submitted to EUSIPCO , 2012 . G. Galatas, G. Potamianos and F. Makedon, \"Audio-visual speech recognition incorporating facial depth information captured by the Kinect\", submitted to EUSIPCO, 2012."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_5_1","DOI":"10.1145\/2141622.2141646"},{"unstructured":"\"The Primesensor reference design\" {online} available at: http:\/\/www.primesensor.com\/?p=514.  \"The Primesensor reference design\" {online} available at: http:\/\/www.primesensor.com\/?p=514.","key":"e_1_3_2_1_6_1"},{"key":"e_1_3_2_1_7_1","volume-title":"Learning OpenCV: Computer Vision with the OpenCV Library","author":"Bradski G.","year":"2008","unstructured":"G. Bradski and A. Kaehler , Learning OpenCV: Computer Vision with the OpenCV Library , O'Reilly Media , 2008 . G. Bradski and A. Kaehler, Learning OpenCV: Computer Vision with the OpenCV Library, O'Reilly Media, 2008."},{"key":"e_1_3_2_1_8_1","volume-title":"The HTK Book Version 3.4","author":"Young S. J.","year":"2006","unstructured":"S. J. Young , D. Kershaw , J. Odell , D. Ollason , V. Valtchev , and P. Woodland , The HTK Book Version 3.4 , Cambridge University Press , 2006 . S. J. Young, D. Kershaw, J. Odell, D. Ollason, V. Valtchev, and P. Woodland, The HTK Book Version 3.4, Cambridge University Press, 2006."},{"unstructured":"\"The HMM-based speech synthesis system (HTS)\" {online} available at: http:\/\/hts.sp.nitech.ac.jp\/.  \"The HMM-based speech synthesis system (HTS)\" {online} available at: http:\/\/hts.sp.nitech.ac.jp\/.","key":"e_1_3_2_1_9_1"}],"event":{"sponsor":["U of Tex at Arlington U of Tex at Arlington"],"acronym":"PETRA2012","name":"PETRA2012: The 5th International Conference on PErvasive Technologies Related to Assistive Environments","location":"Heraklion Crete Greece"},"container-title":["Proceedings of the 5th International Conference on PErvasive Technologies Related to Assistive Environments"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2413097.2413100","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2413097.2413100","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T08:18:26Z","timestamp":1750234706000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2413097.2413100"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,6,6]]},"references-count":9,"alternative-id":["10.1145\/2413097.2413100","10.1145\/2413097"],"URL":"https:\/\/doi.org\/10.1145\/2413097.2413100","relation":{},"subject":[],"published":{"date-parts":[[2012,6,6]]},"assertion":[{"value":"2012-06-06","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}