{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T02:17:18Z","timestamp":1730254638581,"version":"3.28.0"},"reference-count":23,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,8]]},"DOI":"10.1109\/icpr.2018.8545744","type":"proceedings-article","created":{"date-parts":[[2018,11,30]],"date-time":"2018-11-30T00:17:38Z","timestamp":1543537058000},"page":"633-638","source":"Crossref","is-referenced-by-count":3,"title":["Dense Convolutional Recurrent Neural Network for Generalized Speech Animation"],"prefix":"10.1109","author":[{"given":"Lei","family":"Xiao","sequence":"first","affiliation":[]},{"given":"Zengfu","family":"Wang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"Audio-to-visual speech conversion using deep neural networks","author":"taylor","year":"2016","journal-title":"InterSpeech"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SII.2015.7404961"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1145\/3072959.3073640","article-title":"Syn-thesizing obama: learning lip sync from audio","volume":"36","author":"suwajanakorn","year":"2017","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"journal-title":"ESpeak Text to Speech","year":"2012","author":"duddington","key":"ref14"},{"key":"ref15","first-page":"4790","article-title":"Conditional image generation with pixelcnn decoders","author":"van den oord","year":"2016","journal-title":"NIPS"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1145\/3072959.3073658","article-title":"Audio-driven facial animation by joint end-to-end learning of pose and emotion","volume":"36","author":"karras","year":"2017","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.465"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"1505","DOI":"10.21437\/Interspeech.2011-316","article-title":"Announcing the electromagnetic articulography (day 1) subset of the mngu0 articulatory corpus.","author":"richmond","year":"2011","journal-title":"InterSpeech"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1145\/2461912.2462012","article-title":"3d shape regression for realtime facial animation","volume":"32","author":"cao","year":"2013","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2019406.2019435"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854467"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288921"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2008-591","article-title":"Speech-driven lip motion generation with a trajectory hmm","author":"hofer","year":"2008","journal-title":"InterSpeech"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/311535.311537"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"746","DOI":"10.1038\/264746a0","article-title":"Hearing lips and seeing voices","volume":"264","author":"mcgurk","year":"1976","journal-title":"Nature"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1145\/3072959.3073699","article-title":"A deep learning approach for generalized speech animation","volume":"36","author":"taylor","year":"2017","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288925"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"2835","DOI":"10.21437\/Interspeech.2009-724","article-title":"Preliminary inversion mapping results with a new ema corpus","author":"richmond","year":"2009","journal-title":"InterSpeech"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-263","article-title":"Deep architectures for articulatory inversion","author":"uria","year":"2012","journal-title":"InterSpeech"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2010.5684840"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178812"}],"event":{"name":"2018 24th International Conference on Pattern Recognition (ICPR)","start":{"date-parts":[[2018,8,20]]},"location":"Beijing","end":{"date-parts":[[2018,8,24]]}},"container-title":["2018 24th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8527858\/8545020\/08545744.pdf?arnumber=8545744","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T03:22:44Z","timestamp":1643253764000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8545744\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,8]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icpr.2018.8545744","relation":{},"subject":[],"published":{"date-parts":[[2018,8]]}}}