{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T00:43:58Z","timestamp":1774399438943,"version":"3.50.1"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/OAPA.html"}],"funder":[{"name":"Center for Identification Technology Research"},{"DOI":"10.13039\/100000151","name":"NSF Industry\/University Cooperative Research Center","doi-asserted-by":"publisher","award":["CNS-1650474"],"award-info":[{"award-number":["CNS-1650474"]}],"id":[{"id":"10.13039\/100000151","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2017]]},"DOI":"10.1109\/access.2017.2761539","type":"journal-article","created":{"date-parts":[[2017,10,9]],"date-time":"2017-10-09T18:10:18Z","timestamp":1507572618000},"page":"22081-22091","source":"Crossref","is-referenced-by-count":90,"title":["3D Convolutional Neural Networks for Cross Audio-Visual Matching Recognition"],"prefix":"10.1109","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2282-4361","authenticated-orcid":false,"given":"Amirsina","family":"Torfi","sequence":"first","affiliation":[{"name":"Lane Department of Computer Science and Electrical Engineering, West Virginia University College of Engineering and Mineral Resources, Morgantown, WV, USA"}]},{"given":"Seyed Mehdi","family":"Iranmanesh","sequence":"additional","affiliation":[{"name":"Lane Department of Computer Science and Electrical Engineering, West Virginia University College of Engineering and Mineral Resources, Morgantown, WV, USA"}]},{"given":"Nasser","family":"Nasrabadi","sequence":"additional","affiliation":[{"name":"Lane Department of Computer Science and Electrical Engineering, West Virginia University College of Engineering and Mineral Resources, Morgantown, WV, USA"}]},{"given":"Jeremy","family":"Dawson","sequence":"additional","affiliation":[{"name":"Lane Department of Computer Science and Electrical Engineering, West Virginia University College of Engineering and Mineral Resources, Morgantown, WV, USA"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref38","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc ICML"},{"key":"ref33","author":"torfi","year":"2017","journal-title":"Feature Extraction for Speech Recognition"},{"key":"ref32","year":"2016","journal-title":"FFmpeg Tool (Version be1d324) [Software]"},{"key":"ref31","first-page":"1755","article-title":"Dlib-ml: A machine learning toolkit","volume":"10","author":"king","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref30","year":"2017","journal-title":"Audio-Visual Dataset"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143874"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.202"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2339736"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-015-0499-9"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s10044-008-0121-2"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472172"},{"key":"ref12","author":"werda","year":"2013","journal-title":"Lip Localization and Viseme Classification for Visual Speech Recognition"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1155\/2007\/70186"},{"key":"ref14","first-page":"814","article-title":"FaceSync: A linear operator for measuring synchronization of video facial images and audio tracks","author":"slaney","year":"2001","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref15","first-page":"358","article-title":"‘Liveness’ verification in audio-video authentication","author":"chetty","year":"2004","journal-title":"Proc 10th Austral Int Conf Speech Sci Technol (SST)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref18","author":"torfi","year":"2017","journal-title":"Text-independent speaker verification using 3D convolutional neural networks"},{"key":"ref19","author":"torfi","year":"2017","journal-title":"astorfi\/lip-reading-deeplearning 3D Convolutional Neural Networks for Cross Audio-Visual Matching Recognition"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2007.906583"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2520091"},{"key":"ref27","first-page":"548","article-title":"Detecting audio-visual synchrony using deep neural networks","author":"marcheret","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref3","first-page":"1","article-title":"Multimodal deep learning","author":"ngiam","year":"2011","journal-title":"Proc ICML"},{"key":"ref6","first-page":"689","article-title":"Multimodal deep learning","author":"ngiam","year":"2011","journal-title":"Proc 28th Int Conf Mach Learn (ICML)"},{"key":"ref29","first-page":"87","article-title":"Lip reading in the wild","author":"chung","year":"2016","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639140"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2005.854464"},{"key":"ref7","article-title":"Audio visual speech recognition","author":"neti","year":"2000"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639343"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472187"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178347"},{"key":"ref22","first-page":"1149","article-title":"Lipreading using convolutional neural network","author":"noda","year":"2014","journal-title":"Proc Annu Conf Int Speech Commun Assoc (Interspeech)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-014-0629-7"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472088"},{"key":"ref41","article-title":"Labeled faces in the wild: Updates and new reporting procedures","author":"huang","year":"2014"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2015.69"},{"key":"ref26","first-page":"251","article-title":"Out of time: Automated lip sync in the wild","author":"chung","year":"2016","journal-title":"Proc ACCV"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472852"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/7859429\/08063416.pdf?arnumber=8063416","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,15]],"date-time":"2024-01-15T21:22:01Z","timestamp":1705353721000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8063416\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/access.2017.2761539","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017]]}}}