{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T23:36:44Z","timestamp":1729640204215,"version":"3.28.0"},"reference-count":26,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,4]]},"DOI":"10.1109\/icassp.2015.7178224","type":"proceedings-article","created":{"date-parts":[[2015,8,12]],"date-time":"2015-08-12T18:45:43Z","timestamp":1439405143000},"page":"1518-1522","source":"Crossref","is-referenced-by-count":8,"title":["Extracting deep bottleneck features for visual speech recognition"],"prefix":"10.1109","author":[{"given":"Chao","family":"Sui","sequence":"first","affiliation":[]},{"given":"Roberto","family":"Togneri","sequence":"additional","affiliation":[]},{"given":"Mohammed","family":"Bennamoun","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"237","article-title":"Improved bottleneck features using pretrained deep neural networks","author":"dong","year":"2011","journal-title":"InterSpeech"},{"key":"ref11","first-page":"4153","article-title":"Auto-encoder bottleneck features using deep belief networks","author":"tara","year":"2012","journal-title":"Acoustics Speech and Signal Processing (ICASSP) 2012 IEEE International Conference on"},{"key":"ref12","first-page":"3377","article-title":"Extracting deep bottleneck features using stacked auto-encoders","author":"jonas","year":"2013","journal-title":"Acoustics Speech and Signal Processing (ICASSP) 2013 IEEE International Conference on"},{"key":"ref13","article-title":"Deep bottleneck features for spoken language identification","volume":"9","author":"bing","year":"2014","journal-title":"PLoS ONE"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"4765","DOI":"10.1109\/TSP.2009.2026513","article-title":"Information theoretic feature extraction for audio-visual speech recognition","volume":"57","author":"mihai","year":"2009","journal-title":"IEEE Transactions on Signal Processing"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2009.2030637"},{"key":"ref16","first-page":"3371","article-title":"Stacked denoising autoen-coders: Learning useful representations in a deep network with a local denoising criterion","volume":"11","author":"pascal","year":"2010","journal-title":"The Journal of Machine Learning Research"},{"key":"ref17","first-page":"96","article-title":"A blueprint for a comprehensive Australian English auditory-visual speech corpus","author":"denis","year":"2009","journal-title":"Selected Proceedings of the 2008 HCSNet Workshop on Designing the Australian National Corpus"},{"key":"ref18","first-page":"166","article-title":"The big Australian speech corpus (the big ASC)","author":"michael","year":"2010","journal-title":"Proceedings of 13th Australasian International Conference on Speech Science and Technology"},{"key":"ref19","article-title":"Building an audiovisual corpus of Australian English: Large corpus collection with an economical portable and replicable black box","author":"denis","year":"2011","journal-title":"Twelfth Annual Conference of the International Speech Communication Association"},{"journal-title":"Foundations and Trends in Signal Pro-cessing DEEP LEARNING - Methods and Applications","year":"2014","author":"li","key":"ref4"},{"key":"ref3","article-title":"A review of recent advances in visual speech decoding","author":"ziheng","year":"0","journal-title":"Image and Vision Computing 2014"},{"key":"ref6","first-page":"153","article-title":"Greedy layer-wise training of deep networks","volume":"19","author":"yoshua","year":"2007","journal-title":"Advances in neural information processing systems"},{"key":"ref5","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":"geoffrey","year":"2006","journal-title":"Science"},{"key":"ref8","first-page":"689","article-title":"Multimodal deep learning","author":"jiquan","year":"2011","journal-title":"Proceedings of the 28th International Conference on Machine Learning (ICML-11)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383157"},{"key":"ref2","first-page":"23","article-title":"Audio-visual automatic speech recognition: An overview","volume":"22","author":"gerasimos","year":"2004","journal-title":"Issues in visual and audio-visual speech pro-cessing"},{"key":"ref9","first-page":"7596","article-title":"Audio-visual deep learning for noise robust speech recognition","author":"jing","year":"2013","journal-title":"Acoustics Speech and Signal Processing (ICASSP) 2013 IEEE International Conference on"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"1306","DOI":"10.1109\/JPROC.2003.817150","article-title":"Recent advances in the automatic recognition of audiovisual speech","volume":"91","author":"gerasimos","year":"2003","journal-title":"Proceedings of the IEEE"},{"key":"ref20","article-title":"A 3D audio-visual corpus for speech recognition","author":"chao","year":"0","journal-title":"Proceedings of Australasian International Conference on Speech Science and Technology 2012"},{"article-title":"The HTK book version 3.4","year":"2006","author":"steve","key":"ref22"},{"key":"ref21","article-title":"Theano: a cpu and gpu math expression compiler","author":"james","year":"2010","journal-title":"Proceedings of the Python for Scientific Computing Conference (SciPy)"},{"key":"ref24","first-page":"129","article-title":"Unsupervised random forest manifold alignment for lipreading","author":"yuru","year":"2013","journal-title":"Computer Vision (ICCV) 2013 IEEE International Conference on"},{"key":"ref23","first-page":"684","article-title":"Mkpls: Manifold kernel partial least squares for lipreading and speaker identification","author":"amr","year":"2013","journal-title":"Computer Vision and Pattern Recognition (CVPR) 2013 IEEE Conference on"},{"key":"ref26","article-title":"Rate-invariant analysis of trajectories on rie-mannian manifolds with application in visual speech recognition","author":"jingyong","year":"2014","journal-title":"Computer Vision and Pattern Recognition (CVPR) 2014 IEEE Conference on"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.173"}],"event":{"name":"ICASSP 2015 - 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2015,4,19]]},"location":"South Brisbane, Queensland, Australia","end":{"date-parts":[[2015,4,24]]}},"container-title":["2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7158221\/7177909\/07178224.pdf?arnumber=7178224","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,23]],"date-time":"2017-06-23T13:32:13Z","timestamp":1498224733000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7178224\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,4]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp.2015.7178224","relation":{},"subject":[],"published":{"date-parts":[[2015,4]]}}}