{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T08:51:03Z","timestamp":1744188663800,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,9]]},"DOI":"10.1109\/btas.2015.7358754","type":"proceedings-article","created":{"date-parts":[[2015,12,17]],"date-time":"2015-12-17T17:00:53Z","timestamp":1450371653000},"page":"1-6","source":"Crossref","is-referenced-by-count":5,"title":["A deep neural network for audio-visual person recognition"],"prefix":"10.1109","author":[{"given":"Mohammad Rafiqul","family":"Alam","sequence":"first","affiliation":[]},{"given":"Mohammed","family":"Bennamoun","sequence":"additional","affiliation":[]},{"given":"Roberto","family":"Togneri","sequence":"additional","affiliation":[]},{"given":"Ferdous","family":"Sohel","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2013.10.001"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW.2012.116"},{"key":"ref12","first-page":"689","article-title":"Multimodal deep learning","author":"ngiam","year":"2011","journal-title":"Proceedings of the 28th International Conference on Machine Learning (ICML-11)"},{"key":"ref13","article-title":"Msr identity toolbox v 1.0: A matlab toolbox for speaker recognition research","author":"sadjadi","year":"2013","journal-title":"Speech and Language Processing Technical Committee Newsletter"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00311"},{"key":"ref15","first-page":"448","article-title":"Deep boltzmann machines","author":"salakhutdinov","year":"2009","journal-title":"International Conference on Artificial Intelligence and Statistics"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-01793-3_21"},{"key":"ref17","article-title":"First attempt of boltzmann machines for speaker verification","author":"senoussaoui","year":"2012","journal-title":"Odyssey 2012-The Speaker and Language Recognition Workshop"},{"key":"ref18","first-page":"2222","article-title":"Multimodal learning with deep boltzmann machines","author":"srivastava","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref19","article-title":"Preliminary investigation of boltzmann machine classifiers for speaker recognition","author":"stafylakis","year":"2012","journal-title":"IEEE Odyssey Speaker and Language Recognition Workshop"},{"year":"2013","author":"cho","key":"ref4"},{"article-title":"Svm and kernel methods matlab toolbox. Perception Syst?mes et Information, INSA de Rouen, Rouen","year":"2005","author":"canu","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40728-4_14"},{"key":"ref5","first-page":"105","article-title":"Enhanced gradient and adaptive learning rate for training restricted boltzmann machines","author":"cho","year":"2011","journal-title":"Proceedings of the 28th International Conference on Machine Learning (ICML-11)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853888"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCSPA.2013.6487281"},{"key":"ref1","article-title":"A confidence-based late fusion framework for audio-visual biometric identification","author":"alam","year":"2014","journal-title":"Pattern Recognition Letters"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1126\/science.1127647","article-title":"Reducing the dimensionality of data with neural networks","volume":"313","author":"hinton","year":"2006","journal-title":"Science"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"1635","DOI":"10.1109\/TIP.2010.2042645","article-title":"Enhanced local texture feature sets for face recognition under difficult lighting conditions","volume":"19","author":"tan","year":"2010","journal-title":"Image Processing IEEE Transactions on"},{"key":"ref22","first-page":"31","article-title":"Multi-view semi-supervised discriminant analysis: A new approach to audio-visual person recognition","author":"zhao","year":"2012","journal-title":"Signal Processing Conference (EUSIPCO) 2012 Proceedings of the 20th European"},{"key":"ref21","article-title":"Speaker recognition by means of deep belief networks","author":"vasilakakis","year":"2013","journal-title":"Proc Biometric Technologies in Forensic Science"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS.2013.6707786"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2012.14"}],"event":{"name":"2015 IEEE 7th International Conference on Biometrics Theory, Applications and Systems (BTAS)","start":{"date-parts":[[2015,9,8]]},"location":"Arlington, VA, USA","end":{"date-parts":[[2015,9,11]]}},"container-title":["2015 IEEE 7th International Conference on Biometrics Theory, Applications and Systems (BTAS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7348870\/7358743\/07358754.pdf?arnumber=7358754","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,23]],"date-time":"2017-06-23T21:57:02Z","timestamp":1498255022000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7358754\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,9]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/btas.2015.7358754","relation":{},"subject":[],"published":{"date-parts":[[2015,9]]}}}