{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T21:33:39Z","timestamp":1769549619325,"version":"3.49.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9054103","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"1948-1952","source":"Crossref","is-referenced-by-count":19,"title":["End-To-End Generation of Talking Faces from Noisy Speech"],"prefix":"10.1109","author":[{"given":"Sefik Emre","family":"Eskimez","sequence":"first","affiliation":[]},{"given":"Ross K.","family":"Maddox","sequence":"additional","affiliation":[]},{"given":"Chenliang","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Zhiyao","family":"Duan","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"End-to-end speech-driven facial animation with temporal gans","author":"vougioukas","year":"2018","journal-title":"BMVC"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01251-8"},{"key":"ref12","first-page":"1","article-title":"Noise-resilient training method for face landmark generation from speech","volume":"pp","author":"eskimez","year":"2019","journal-title":"IEEE\/ACM Transactions on Audio Speech and Language Processing"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019299"},{"key":"ref14","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref15","first-page":"234","article-title":"U-net: Convo-lutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref17","first-page":"1755","article-title":"Dlib-ml: A machine learning toolkit","volume":"10","author":"king","year":"2009","journal-title":"Journal of Machine Learning Research"},{"key":"ref18","first-page":"87","article-title":"Lip reading in the wild","author":"chung","year":"2016","journal-title":"Asian Conference on Computer Vision"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.04995"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1121\/1.3110132"},{"key":"ref6","article-title":"You said thatƒ","author":"chung","year":"2017","journal-title":"British Machine Vision Conference"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1145\/3072959.3073640","article-title":"Synthesizing obama: learning lip sync from audio","volume":"36","author":"suwajanakorn","year":"2017","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00802"},{"key":"ref7","first-page":"520","article-title":"Lip movements generation at a glance","author":"chen","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1121\/1.1836832"},{"key":"ref1","first-page":"43","article-title":"Bi-sensory articulation functions for normal hearing and sensorineural hearing loss patients","volume":"6","author":"binnie","year":"1973","journal-title":"J Acad Rehabilitative Audiology"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/129"},{"key":"ref20","year":"2019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/BF02291478"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Barcelona, Spain","start":{"date-parts":[[2020,5,4]]},"end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09054103.pdf?arnumber=9054103","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:18:28Z","timestamp":1656375508000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9054103\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9054103","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}