{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T02:35:54Z","timestamp":1784428554124,"version":"3.55.0"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1741472"],"award-info":[{"award-number":["1741472"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100008091","name":"University of Rochester","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100008091","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/taslp.2019.2947741","type":"journal-article","created":{"date-parts":[[2019,10,16]],"date-time":"2019-10-16T20:53:43Z","timestamp":1571259223000},"page":"27-38","source":"Crossref","is-referenced-by-count":25,"title":["Noise-Resilient Training Method for Face Landmark Generation From Speech"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6259-5925","authenticated-orcid":false,"given":"Sefik Emre","family":"Eskimez","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ross K.","family":"Maddox","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2183-822X","authenticated-orcid":false,"given":"Chenliang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8334-9974","authenticated-orcid":false,"given":"Zhiyao","family":"Duan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/BF02291478"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.116"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/34.927467"},{"key":"ref32","first-page":"2743","article-title":"A new language independent, photo-realistic talking head driven by voice only","author":"zhang","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88190-2_9"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2006.12.001"},{"key":"ref37","first-page":"1755","article-title":"Dlib-ml: A machine learning toolkit","volume":"10","author":"king","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2009.08.002"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073658"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.287"},{"key":"ref10","first-page":"112-1","article-title":"Looking to listen at the cocktail party: A speaker-independent audio-visual model for speech separation","volume":"37","author":"ephrat","year":"2008","journal-title":"ACM Trans Graph"},{"key":"ref40","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1006\/cviu.1995.1004","article-title":"Active shape models-Their training and application","volume":"61","author":"cootes","year":"1995","journal-title":"Comput Vision Image Understanding"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178347"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952625"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11036-016-0685-9"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2405481"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2359987"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3295748"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2015.7177428"},{"key":"ref19","first-page":"3307","article-title":"Text driven 3D photo-realistic talking head","author":"wang","year":"0","journal-title":"Proc 12th Annu Conf Int Speech Commun Assoc"},{"key":"ref28","first-page":"20","article-title":"Video realistic talking heads using hierarchical non-linear speech-appearance models","volume":"147","author":"cosker","year":"2003","journal-title":"Proc Mirage"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.04995"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1023\/A:1011171430700"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1121\/1.3110132"},{"key":"ref6","article-title":"You said that?","author":"chung","year":"0"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2004.1334024"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1145\/3072959.3073640","article-title":"Synthesizing Obama: Learning lip sync from audio","volume":"36","author":"suwajanakorn","year":"2017","journal-title":"ACM Trans Graph"},{"key":"ref8","first-page":"372","article-title":"Generating talking face landmarks from speech","author":"eskimez","year":"0","journal-title":"Proc Int Conf Latent Variable Anal Signal Separat"},{"key":"ref7","first-page":"361","article-title":"End-to-end learning for 3D facial animation from raw waveforms of speech","author":"pham","year":"0","journal-title":"Proc 20th ACM Int Conf Multimodal Interact"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1121\/1.1836832"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"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":"ref20","first-page":"2667","article-title":"Photo-realistic expressive text to talking head synthesis","author":"wan","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref45","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"CoRR"},{"key":"ref22","first-page":"1205","article-title":"Real-time conversion from a single 2D face image to a 3D text-driven emotive audio-visual avatar","author":"tang","year":"0","journal-title":"Proc IEEE Int Conf Multimedia Expo"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2015.08.011"},{"key":"ref42","year":"2018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178899"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029666.37597.d3"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-013-1633-3"},{"key":"ref44","article-title":"Automatic differentiation in pytorch","author":"paszke","year":"0","journal-title":"Proc Neural Inf Process Syst Workshop"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/311535.311537"},{"key":"ref43","year":"2018"},{"key":"ref25","article-title":"Lip movements generation at a glance","author":"chen","year":"0","journal-title":"Proc Eur Conf Comput Vision"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6570655\/8938144\/8871109-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8938144\/08871109.pdf?arnumber=8871109","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:31:21Z","timestamp":1651080681000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8871109\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/taslp.2019.2947741","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}