{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T17:40:32Z","timestamp":1762623632470},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2015]]},"DOI":"10.1109\/taslp.2015.2409785","type":"journal-article","created":{"date-parts":[[2015,3,9]],"date-time":"2015-03-09T18:53:54Z","timestamp":1425927234000},"page":"1-1","source":"Crossref","is-referenced-by-count":35,"title":["Learning Dynamic Stream Weights For Coupled-HMM-based Audio-visual Speech Recognition"],"prefix":"10.1109","author":[{"given":"Ahmed","family":"Hussen Abdelaziz","sequence":"first","affiliation":[]},{"given":"Steffen","family":"Zeiler","sequence":"additional","affiliation":[]},{"given":"Dorothea","family":"Kolossa","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90095-3"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref33","article-title":"Using entropy as a stream reliability estimate for audio-visual speech recognition","author":"gurban","year":"2008","journal-title":"Proc Eur Signal Process Conf"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2003.811544"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/97.988717"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/89.928915"},{"key":"ref37","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2010-715","article-title":"Efficient many core CHMM speech recognition for audiovisual and multistream data","author":"kolossa","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref36","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2009-371","article-title":"Accounting for the uncertainty of speech estimates in the complex domain for minimum mean square error speech enhancement","author":"astudillo","year":"2009","journal-title":"Proc INTERSPEECH"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1202473"},{"key":"ref34","article-title":"Stream confidence estimation for audio-visual speech recognition","author":"potamianos","year":"2000","journal-title":"Proc ICSLP"},{"key":"ref28","author":"boyd","year":"2009","journal-title":"Convex optimization"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.679695"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163394"},{"key":"ref2","year":"2011","journal-title":"Robust Speech Recognition of Uncertain or Missing Data"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6637622"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1198707"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367227"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2001.1034671"},{"key":"ref24","article-title":"Dynamic stream weight estimation in coupled-HMM-based audio-visual speech recognition using multilayer perceptrons","author":"abdelaziz","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref23","first-page":"1527","article-title":"A new EM estimation of dynamic stream weights for coupled-HMM-based audio-visual ASR","author":"abdelaziz","year":"2014","journal-title":"Proc ICASSP"},{"key":"ref26","article-title":"Word-dependent acoustic-labial weights in HMM-based speech recognition","author":"jourlin","year":"1997","journal-title":"European Tutorial Workshop on Audio-visual Speech Recognition"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/5.18626"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref51","first-page":"1","article-title":"Exploring strategies for training deep neural networks","volume":"1","author":"larochelle","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref53","author":"hagan","year":"1996","journal-title":"Neural Network Design"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/72.329697"},{"key":"ref10","first-page":"169","article-title":"Asynchronous stream modeling for large vocabulary audio-visual speech recognition","author":"luettin","year":"2001","journal-title":"Proc ICASSP"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"1274","DOI":"10.1155\/S1110865702206083","article-title":"Dynamic Bayesian networks for audio-visual speech recognition","volume":"2002","author":"nefian","year":"2002","journal-title":"EURASIP J Adv Signal Process"},{"key":"ref12","article-title":"A new ASR approach based on independent processing and recombination of partial frequency bands","author":"bourlard","year":"1996","journal-title":"Proc ICSLP"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.543247"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/6046.865479"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518662"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1997.596176"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.1005874"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/S1007-0214(05)70045-6"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2172427"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-13015-5_35"},{"key":"ref3","year":"2012","journal-title":"Techniques for Noise Robustness in Automatic Speech Recognition"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/89.799688"},{"key":"ref5","article-title":"Lip-reading of Japanese vowels using neural networks","author":"watanabe","year":"1990","journal-title":"Proc ICSLP"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.2001.962801"},{"key":"ref49","first-page":"35","article-title":"Note on the convergence of methods of conjugate directions","volume":"3","author":"polak","year":"1969","journal-title":"Rev Francaise Recherche Operationnelle"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"1260","DOI":"10.1155\/S1110865702206150","article-title":"Noise adaptive stream weighting in audio-visual speech recognition","volume":"2002","author":"heckmann","year":"2002","journal-title":"EURASIP J Adv Signal Process"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2003.817150"},{"key":"ref46","article-title":"Binaural signal processing for enhanced speech recognition robustness in complex listening environments","author":"meutzner","year":"2013","journal-title":"Proc CHiME Workshop on Mach Listen Multisource Environ"},{"key":"ref45","article-title":"CHiME challenge: Approaches to robustness using beamforming and uncertainty-of-observation techniques","author":"kolossa","year":"2011","journal-title":"Proc CHiME Workshop on Mach Listen Multisource Environ"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1214\/ss\/1177011454"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-21317-5_13"},{"key":"ref42","author":"bradski","year":"2008","journal-title":"Computer Vision with the OpenCV Library"},{"key":"ref41","year":"2003","journal-title":"Speech processing transmission and quality aspects (STQ) Distributed speech recognition Advanced front-end feature extraction algorithm Compression algorithms"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2013.2278556"},{"key":"ref43","author":"johnson","year":"2007","journal-title":"Applied multivariate statistical analysis"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/7070847\/07056468.pdf?arnumber=7056468","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,1]],"date-time":"2022-05-01T19:10:22Z","timestamp":1651432222000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7056468\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/taslp.2015.2409785","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015]]}}}