{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:43:56Z","timestamp":1772909036544,"version":"3.50.1"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icasspw59220.2023.10193719","type":"proceedings-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T17:30:54Z","timestamp":1690997454000},"page":"1-5","source":"Crossref","is-referenced-by-count":14,"title":["Face-Dubbing++: LIP-Synchronous, Voice Preserving Translation Of Videos"],"prefix":"10.1109","author":[{"given":"Alexander","family":"Waibel","sequence":"first","affiliation":[{"name":"Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology"}]},{"given":"Moritz","family":"Behr","sequence":"additional","affiliation":[{"name":"Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology"}]},{"given":"Dogucan","family":"Yaman","sequence":"additional","affiliation":[{"name":"Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology"}]},{"given":"Fevziye Irem","family":"Eyiokur","sequence":"additional","affiliation":[{"name":"Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology"}]},{"given":"Tuan-Nam","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology"}]},{"given":"Carlos","family":"Mullov","sequence":"additional","affiliation":[{"name":"Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology"}]},{"given":"Mehmet Arif","family":"Demirtas","sequence":"additional","affiliation":[{"name":"Istanbul Technical University,Department of Computer Engineering"}]},{"given":"Alperen","family":"Kantarci","sequence":"additional","affiliation":[{"name":"Istanbul Technical University,Department of Computer Engineering"}]},{"given":"Stefan","family":"Constantin","sequence":"additional","affiliation":[{"name":"Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology"}]},{"given":"Hazim Kemal","family":"Ekenel","sequence":"additional","affiliation":[{"name":"Istanbul Technical University,Department of Computer Engineering"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Face translation: A multimodal translation agent","author":"ritter","year":"1999","journal-title":"AVSPN"},{"key":"ref12","article-title":"Isometricmt: Neural machine translation for automatic dubbing","author":"lakew","year":"2021","journal-title":"arXiv preprint arXiv 2112 06814"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2702"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054130"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1500"},{"key":"ref30","first-page":"261","article-title":"Wit3: Web inventory of transcribed and translated talks","author":"cettolo","year":"2012","journal-title":"EAMT"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.iwslt-1.10"},{"key":"ref33","article-title":"Gans trained by a two timescale update rule converge to a local nash equilibrium","volume":"30","author":"heusel","year":"2017","journal-title":"NeurIPS"},{"key":"ref10","first-page":"125","article-title":"Kit’s iwslt 2021 offline speech translation system","author":"nguyen","year":"2021","journal-title":"IWSLT"},{"key":"ref32","article-title":"Deep audio-visual speech recognition","author":"afouras","year":"2018","journal-title":"arXiv 1809 02108"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1997.599557"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1991.150456"},{"key":"ref17","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref19","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"2020","journal-title":"ICLRE"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2526"},{"key":"ref24","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"kong","year":"2020","journal-title":"NeurIPS"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1016\/S0167-6393(96)00068-4","article-title":"Ssml: A speech synthesis markup language","volume":"21","author":"taylor","year":"1997","journal-title":"Speech Communication"},{"key":"ref26","article-title":"Generative adversarial nets","volume":"27","author":"goodfellow","year":"2014","journal-title":"NeurIPS"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-283"},{"key":"ref20","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume":"32","author":"ren","year":"2019","journal-title":"NeurIPS"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/29.21701"},{"key":"ref28","first-page":"251","article-title":"Out of time: automated lip sync in the wild","author":"chung","year":"2016","journal-title":"ACCV"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref29","first-page":"79","article-title":"Europarl: A parallel corpus for statistical machine translation","author":"koehn","year":"2005","journal-title":"Proceedings of Machine Translation Summit X Papers"},{"key":"ref8","article-title":"Super-human performance in online low-latency recognition of conversational speech","author":"nguyen","year":"2020","journal-title":"arXiv preprint arXiv 2010 00170"},{"key":"ref7","article-title":"ow-latency neural speech translation","author":"niehues","year":"2018","journal-title":"arXiv preprint arXiv 1808 00508"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.iwslt-1.18"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2010.5700843"},{"key":"ref3","article-title":"Simultaneous german-english lecture translation","author":"kolss","year":"2008","journal-title":"IWSLT"},{"key":"ref6","author":"waibel","year":"2016","journal-title":"Hybrid offline\/online speech translation system"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-3017"}],"event":{"name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10192576\/10192577\/10193719.pdf?arnumber=10193719","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T17:42:35Z","timestamp":1692639755000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10193719\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icasspw59220.2023.10193719","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}