{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T10:37:16Z","timestamp":1781606236105,"version":"3.54.5"},"reference-count":19,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,3]]},"DOI":"10.1109\/icassp.2017.7953172","type":"proceedings-article","created":{"date-parts":[[2017,6,20]],"date-time":"2017-06-20T21:35:36Z","timestamp":1497994536000},"page":"5320-5324","source":"Crossref","is-referenced-by-count":25,"title":["Improving audio-visual speech recognition using deep neural networks with dynamic stream reliability estimates"],"prefix":"10.1109","author":[{"given":"Hendrik","family":"Meutzner","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ning","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert","family":"Nickel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christopher","family":"Schymura","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dorothea","family":"Kolossa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","first-page":"109","article-title":"Improved Feature Processing for Deep Neural Networks","author":"rath","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6637622"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref13","first-page":"2345","article-title":"Sequence-discriminative Training of Deep Neural Networks","author":"vesel\u00fd","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1994.1016"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960661"},{"key":"ref16","first-page":"3726","article-title":"Twin-HMM-based Audio-visual Speech Enhancement","author":"hussen","year":"2013","journal-title":"Proc IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2003.811544"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2005.08.005"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"722","DOI":"10.1007\/s10489-014-0629-7","article-title":"Audio-visual Speech Recognition Using Deep Learning","volume":"42","author":"kuniaki","year":"2015","journal-title":"Applied Intelligence"},{"key":"ref3","article-title":"Improving Lip-reading Performance for Robust Audiovisual Speech Recognition using DNNs","author":"thangthai","year":"2015","journal-title":"Proc Joint Conference on Facial Analysis Animation and Audio-Visual Speech Processing"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639140"},{"key":"ref5","article-title":"Integration of Deep Bottleneck Features for Audio-visual Speech Recognition","author":"ninomiya","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref8","article-title":"The Kaldi Speech Recognition Toolkit","author":"povey","year":"2011","journal-title":"Proc IEEE Workshop on Automatic Speech Recognition and Understanding"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1155\/S1110865702206150"},{"key":"ref2","first-page":"863","article-title":"Learning Dynamic Stream Weights for Coupled-HMM-based Audio-Visual Speech Recognition","volume":"23","author":"hussen","year":"2015","journal-title":"IEEE\/ACM Transactions on Audio Speech and Language Processing"},{"key":"ref1","first-page":"1144","article-title":"Dy-namic Stream Weight Estimation in Coupled-HMM-based Audio-visual Speech Recognition using Multilayer Perceptrons","author":"hussen abdelaziz","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref9","article-title":"Feature and Model Space Speaker Adaptation with Full Covariance Gaussians","author":"povey","year":"2006","journal-title":"Proc INTERSPEECH"}],"event":{"name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"New Orleans, LA","start":{"date-parts":[[2017,3,5]]},"end":{"date-parts":[[2017,3,9]]}},"container-title":["2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7943262\/7951776\/07953172.pdf?arnumber=7953172","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,26]],"date-time":"2019-09-26T11:23:03Z","timestamp":1569496983000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7953172\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,3]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icassp.2017.7953172","relation":{},"subject":[],"published":{"date-parts":[[2017,3]]}}}