{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,7]],"date-time":"2025-05-07T13:33:57Z","timestamp":1746624837745},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319439570"},{"type":"electronic","value":"9783319439587"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"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":[[2016]]},"DOI":"10.1007\/978-3-319-43958-7_40","type":"book-chapter","created":{"date-parts":[[2016,8,12]],"date-time":"2016-08-12T02:11:41Z","timestamp":1470967901000},"page":"338-345","source":"Crossref","is-referenced-by-count":24,"title":["HAVRUS Corpus: High-Speed Recordings of Audio-Visual Russian Speech"],"prefix":"10.1007","author":[{"given":"Vasilisa","family":"Verkhodanova","sequence":"first","affiliation":[]},{"given":"Alexander","family":"Ronzhin","sequence":"additional","affiliation":[]},{"given":"Irina","family":"Kipyatkova","sequence":"additional","affiliation":[]},{"given":"Denis","family":"Ivanko","sequence":"additional","affiliation":[]},{"given":"Alexey","family":"Karpov","sequence":"additional","affiliation":[]},{"given":"Milo\u0161","family":"\u017delezn\u00fd","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,8,13]]},"reference":[{"key":"40_CR1","unstructured":"Biwi 3D Audiovisual Corpus of Affective Communication. http:\/\/www.vision.ee.ethz.ch\/datasets\/b3dac2.en.html"},{"key":"40_CR2","unstructured":"CHIL - Computers in the Human Interaction Loop. https:\/\/imatge.upc.edu\/web\/projects\/chil-computers-human-interaction-loop"},{"key":"40_CR3","unstructured":"Czech Audio-Visual Speech Corpus for Recognition with Impaired Conditions. http:\/\/catalog.elra.info\/product_info.php?cPath=25&products_id=1082"},{"key":"40_CR4","unstructured":"C\u00edsa\u0159, P., \u017delezn\u1ef3, M., Kr\u0148oul, Z., Kanis, J., Zelinka, J., M\u00fcller, L.: Design and recording of czech speech corpus for audio-visual continuous speech recognition. In: Proceedings of International Conference on the Auditory-Visual Speech Processing, pp. 1\u20134 (2005)"},{"key":"40_CR5","unstructured":"C\u00edsa\u0159, P., Zelinka, J., \u017delezn\u1ef3, M., Karpov, A., Ronzhin, A.: Audio-visual speech recognition for slavonic languages (Czech and Russian). In: Proceedings of 11th International Conference SPECOM 2006, St. Petersburg, Russia, pp. 493\u2013498 (2006)"},{"key":"40_CR6","unstructured":"Estival, D., Cassidy, S., Cox, F., Burnham, D., et al.: Austalk: an audio-visual corpus of australian english. In: Proceedings of 9th Language Resources and Evaluation Conference LREC 2014, pp. 3105\u20133109 (2014)"},{"key":"40_CR7","unstructured":"Giraudel, A., Carr\u00e9, M., Mapelli, V., Kahn, J., Galibert, O., Quintard, L.: The REPERE corpus: a multimodal corpus for person recognition. In: Proceedings of 8th Language Resources and Evaluation Conference (LREC 2012), pp. 1102\u20131107 (2012)"},{"key":"40_CR8","unstructured":"Grishina, E.: Multimodal russian corpus (MURCO): first steps. In: Proceedings of 7th Language Resources and Evaluation Conference (LREC 2010), pp. 2953\u20132960 (2010)"},{"key":"40_CR9","doi-asserted-by":"crossref","unstructured":"Karpov, A., Ronzhin, A., Kipyatkova, I.: Designing a multimodal corpus of audio-visual speech using a high-speed camera. In: Proceedings of 11th International Conference on Signal Processing (ICSP 2012), vol. 1, pp. 519\u2013522. IEEE (2012)","DOI":"10.1109\/ICoSP.2012.6491539"},{"key":"40_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1007\/978-3-319-11581-8_6","volume-title":"Speech and Computer","author":"A Karpov","year":"2014","unstructured":"Karpov, A., Kipyatkova, I., \u017delezn\u00fd, M.: A framework for recording audio-visual speech corpora with a microphone and a high-speed camera. In: Ronzhin, A., Potapova, R., Delic, V. (eds.) SPECOM 2014. LNCS, vol. 8773, pp. 50\u201357. Springer, Heidelberg (2014)"},{"key":"40_CR11","unstructured":"Karpov, A., Ronzhin, A., Kipyatkova, I., \u017delezn\u1ef3, M.: Influene of phone-viseme temporal correlations on audiovisual STT and TTS performance. In: Proceedings of 17th International Congress of Phonetic Sciences, pp. 1030\u20131033 (2011)"},{"key":"40_CR12","doi-asserted-by":"crossref","unstructured":"Karpov, A., Ronzhin, A., Markov, K., Zelezn\u1ef3, M.: Viseme-dependent weight optimization for CHMM-based audio-visual speech recognition. In: Proceedings of INTERSPEECH 2010, Makuhari, Japan, pp. 2678\u20132681 (2010)","DOI":"10.21437\/Interspeech.2010-710"},{"issue":"3","key":"40_CR13","doi-asserted-by":"crossref","first-page":"546","DOI":"10.1134\/S1054661809030225","volume":"19","author":"AA Karpov","year":"2009","unstructured":"Karpov, A.A., Ronzhin, A.L.: Information enquiry kiosk with multimodal user interface. Pattern Recogn. Image Analy. 19(3), 546\u2013558 (2009)","journal-title":"Pattern Recogn. Image Analy."},{"key":"40_CR14","doi-asserted-by":"crossref","unstructured":"Lee, B., Hasegawa-Johnson, M., Goudeseune, C., Kamdar, S., Borys, S., Liu, M., Huang, T.S.: AVICAR: audio-visual sspeech corpus in a car eenvironment. In: Proceedings of INTERSPEECH 2004, Jeju Island, Korea, pp. 2489\u20132492 (2004)","DOI":"10.21437\/Interspeech.2004-424"},{"issue":"3\u20134","key":"40_CR15","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1007\/s10579-007-9054-4","volume":"41","author":"D Mostefa","year":"2007","unstructured":"Mostefa, D., Moreau, N., Choukri, K., Potamianos, G., Chu, S.M., Tyagi, A., Casas, J.R., Turmo, J., Cristoforetti, L., Tobia, F., et al.: The CHIL audiovisual corpus for lecture and meeting analysis inside smart rooms. Lang. Resour. Evalu. 41(3\u20134), 389\u2013407 (2007)","journal-title":"Lang. Resour. Evalu."},{"key":"40_CR16","unstructured":"Nikan, S.: Human face recognition under degraded conditions. University of Windsor (2014)"},{"key":"40_CR17","doi-asserted-by":"crossref","unstructured":"Patterson, E.K., Gurbuz, S., Tufekci, Z., Gowdy, J.N.: CUAVE: a new audio-visual database for multimodal human-computer interface research. In: Proceedings of International Conference on Acoustics, Speech, and Signal Processing (ICASSP), vol. 2, pp. 2017\u20132020. IEEE (2002)","DOI":"10.1109\/ICASSP.2002.5745028"},{"issue":"11","key":"40_CR18","doi-asserted-by":"crossref","first-page":"2011","DOI":"10.1134\/S0005117915110107","volume":"76","author":"AL Ronzhin","year":"2015","unstructured":"Ronzhin, A.L., Vatamanyuk, I., Ronzhin, A.L., \u017delezn\u1ef3, M.: Mathematical methods to estimate image blur and recognize faces in the system of automatic conference participant registration. Autom. Remote Control 76(11), 2011\u20132020 (2015)","journal-title":"Autom. Remote Control"},{"key":"40_CR19","unstructured":"Togneri, R., B.M., Sui, C.: Multimodal speech recognition with the AusTalk 3D audio-visual corpus. In: Tutorial at ITERSPEECH 2014 (2014)"},{"key":"40_CR20","doi-asserted-by":"crossref","first-page":"1071","DOI":"10.1007\/978-0-387-93808-0_40","volume-title":"Handbook of Ambient Intelligence and Smart Environments","author":"A Waibel","year":"2010","unstructured":"Waibel, A., Stiefelhagen, R., Carlson, R., Casas, J., Kleindienst, J., Lamel, L., Lanz, O., Mostefa, D., Omologo, M., Pianesi, F., et al.: Computers in the human interaction loop. In: Nakashima, H., Aghajan, H., Augusto, J.C. (eds.) Handbook of Ambient Intelligence and Smart Environments, pp. 1071\u20131116. Springer, Heidelberg (2010)"},{"key":"40_CR21","doi-asserted-by":"crossref","first-page":"250","DOI":"10.1016\/j.sigpro.2013.11.038","volume":"103","author":"X Xie","year":"2014","unstructured":"Xie, X.: Illumination preprocessing for face images based on empirical mode decomposition. Signal Process. 103, 250\u2013257 (2014)","journal-title":"Signal Process."},{"key":"40_CR22","unstructured":"\u017delezn\u1ef3, M., C\u00edsa\u0159, P., Kr\u0148oul, Z., Ronzhin, A., Li, I., Karpov, A.: Design of russian audio-visual speech corpus for bimodal speech recognition. In: Proceedings of SPECOM, pp. 397\u2013400 (2005)"},{"key":"40_CR23","unstructured":"Zelezn\u1ef3, M., C\u00edsar, P.: Czech audio-visual speech corpus of a car driver for in-vehicle audio-visual speech recognition. In: Proceedings of International Conference on Audio-Visual Speech Processing (AVSP 2003), pp. 169\u2013173 (2003)"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-43958-7_40","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,5]],"date-time":"2022-07-05T21:09:01Z","timestamp":1657055341000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-43958-7_40"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319439570","9783319439587"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-43958-7_40","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]}}}