{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:19:28Z","timestamp":1742912368710,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":12,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642393297"},{"type":"electronic","value":"9783642393303"}],"license":[{"start":{"date-parts":[[2013,1,1]],"date-time":"2013-01-01T00:00:00Z","timestamp":1356998400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-39330-3_5","type":"book-chapter","created":{"date-parts":[[2013,7,1]],"date-time":"2013-07-01T13:50:32Z","timestamp":1372686632000},"page":"43-48","source":"Crossref","is-referenced-by-count":0,"title":["Robust Multi-Modal Speech Recognition in Two Languages Utilizing Video and Distance Information from the Kinect"],"prefix":"10.1007","author":[{"given":"Georgios","family":"Galatas","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gerasimos","family":"Potamianos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fillia","family":"Makedon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"5_CR1","unstructured":"Iwano, K., Tamura, S., Furui, S.: Bimodal speech recognition using lip movement measured by optical-flow analysis. In: Proc. HSC, pp. 187\u2013190 (2001)"},{"key":"5_CR2","doi-asserted-by":"crossref","unstructured":"Nakamura, S., Ito, H., Shikano, K.: Stream weight optimization of speech and lip image sequence for audio-visual speech recognition. In: Proc. ICSLP, vol.\u00a03, pp. 20\u201324 (2000)","DOI":"10.21437\/ICSLP.2000-468"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Goecke, R., Millar, B.: The audio-video Australian English speech data corpus AVOZES. In: Proc. ICSLP, vol.\u00a03, pp. 2525\u20132528 (2004)","DOI":"10.21437\/Interspeech.2004-433"},{"key":"5_CR4","unstructured":"Vorwerk, A., Wang, X., Kolossa, D., Zeiler, S., Orglmeister, R.: WAPUSK20 \u2013 a database for robust audiovisual speech recognition. In: Proc. LREC (2010)"},{"key":"5_CR5","unstructured":"Ortega, A., Sukno, F., Lleida, E., Frangi, A., Miguel, A., Buera, L., Zacur, E.: AV@CAR: A Spanish multichannel multimodal corpus for in-vehicle automatic audio-visual speech recognition. In: Proc. LREC., vol.\u00a03, pp. 763\u2013767 (2004)"},{"key":"5_CR6","unstructured":"The Primesensor Reference Design, http:\/\/www.primesensor.com"},{"key":"5_CR7","doi-asserted-by":"crossref","unstructured":"Galatas, G., Potamianos, G., Makedon, F.: Audio-visual speech recognition incorporating facial depth information captured by the Kinect. In: Proc. EUSIPCO, pp. 2714\u20132717 (2012)","DOI":"10.1145\/2413097.2413100"},{"key":"5_CR8","unstructured":"Bishop, C.M.: Pattern Recognition and Machine Learning. Springer (2006)"},{"key":"5_CR9","unstructured":"Young, S.J., Kershaw, D., Odell, J., Ollason, D., Valtchev, V., Woodland, P.: The HTK Book version 3.4. Cambridge University Press (2006)"},{"key":"5_CR10","unstructured":"The HMM-based speech synthesis system (HTS), http:\/\/hts.sp.nitech.ac.jp"},{"key":"5_CR11","unstructured":"Galatas, G., Potamianos, G., Kosmopoulos, D., Mcmurrough, C., Makedon, F.: Bilingual corpus for AVASR using multiple sensors and depth information. In: Proc. AVSP, pp. 103\u2013106 (2011)"},{"issue":"3","key":"5_CR12","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1016\/0167-6393(93)90095-3","volume":"12","author":"A. Varga","year":"1993","unstructured":"Varga, A., Steeneken, H.: Assessment for automatic speech recognition: Noisex-92. A database and an experiment to study the effect of additive noise on speech recognition systems. Speech Communication\u00a012(3), 247\u2013251 (1993)","journal-title":"Speech Communication"}],"container-title":["Lecture Notes in Computer Science","Human-Computer Interaction. Interaction Modalities and Techniques"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-39330-3_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,2]],"date-time":"2023-07-02T20:11:07Z","timestamp":1688328667000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-39330-3_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642393297","9783642393303"],"references-count":12,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-39330-3_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2013]]}}}