{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:16:54Z","timestamp":1753600614775,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,9]]},"DOI":"10.23919\/eusipco.2019.8902572","type":"proceedings-article","created":{"date-parts":[[2019,11,25]],"date-time":"2019-11-25T13:39:38Z","timestamp":1574689178000},"page":"1-5","source":"Crossref","is-referenced-by-count":8,"title":["Lip-Reading with Limited-Data Network"],"prefix":"10.23919","author":[{"given":"Adriana","family":"Fernandez-Lopez","sequence":"first","affiliation":[]},{"given":"Federico M.","family":"Sukno","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc"},{"key":"ref11","first-page":"87","article-title":"Lip reading in the wild","author":"chung","year":"2016","journal-title":"Proc"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462280"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952625"},{"key":"ref14","article-title":"End-to-end audiovisual fusion with LSTMs","author":"petridis","year":"2017","journal-title":"Proc"},{"key":"ref15","article-title":"End-to-end multi-view lipreading","author":"petridis","year":"0","journal-title":"Proc"},{"key":"ref16","article-title":"Return of the devil in the details: Delving deep into convolutional nets","author":"chatfield","year":"2014","journal-title":"Proc"},{"key":"ref17","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"ICLRE"},{"key":"ref18","first-page":"341","article-title":"Praat, a system for doing phonetics by computer","volume":"5","author":"boersma","year":"2002","journal-title":"Glot International"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"498","DOI":"10.21437\/Interspeech.2017-1386","article-title":"Montreal forced aligner: trainable text-speech alignment using kaldi","author":"mcauliffe","year":"2017","journal-title":"Proc of Interspeech"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288999"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461326"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2017.07.001"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"3652","DOI":"10.21437\/Interspeech.2017-85","article-title":"Combining residual networks with LSTMs for lipreading","author":"stafylakis","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2018.07.002"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2015.7163155"},{"key":"ref8","article-title":"Lipnet: Sentence-level lipreading","author":"assael","year":"2017","journal-title":"Proc"},{"key":"ref7","first-page":"290","article-title":"Multi-view automatic lip-reading using neural network","author":"lee","year":"2016","journal-title":"Proc"},{"key":"ref2","first-page":"251","article-title":"Out of time: automated lip sync in the wild","author":"chung","year":"2016","journal-title":"Proc"},{"key":"ref9","article-title":"Lip reading in profile","author":"chung","year":"2017","journal-title":"Proc"},{"key":"ref1","first-page":"277","article-title":"Concatenated frame image based CNN for visual speech recognition","author":"saitoh","year":"2016","journal-title":"Proc"},{"journal-title":"Speechreading (Lipreading)","year":"1971","author":"jeffers","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2407694"},{"key":"ref21","first-page":"2109","article-title":"Viseme definitions comparison for visualonly speech recognition","author":"cappelletta","year":"2011","journal-title":"Proc"},{"key":"ref24","first-page":"230","article-title":"Which phoneme-to-viseme maps best improve visualonly computer lip-reading?","author":"bear","year":"2014","journal-title":"Proc"},{"key":"ref23","first-page":"2009","article-title":"Decoding visemes: improving machine lipreading","author":"bear","year":"2016","journal-title":"Proc"},{"key":"ref26","article-title":"Comparing phonemes and visemes with DNNbased lipreading","author":"thangthai","year":"2017","journal-title":"Proc"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.5220\/0006102100520063"}],"event":{"name":"2019 27th European Signal Processing Conference (EUSIPCO)","start":{"date-parts":[[2019,9,2]]},"location":"A Coruna, Spain","end":{"date-parts":[[2019,9,6]]}},"container-title":["2019 27th European Signal Processing Conference (EUSIPCO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8893974\/8902336\/08902572.pdf?arnumber=8902572","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,10,30]],"date-time":"2020-10-30T16:57:12Z","timestamp":1604077032000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8902572\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9]]},"references-count":28,"URL":"https:\/\/doi.org\/10.23919\/eusipco.2019.8902572","relation":{},"subject":[],"published":{"date-parts":[[2019,9]]}}}