{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T03:16:31Z","timestamp":1774926991702,"version":"3.50.1"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890684","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Improving Lip-synchrony in Direct Audio-Visual Speech-to-Speech Translation"],"prefix":"10.1109","author":[{"given":"Lucas","family":"Goncalves","sequence":"first","affiliation":[{"name":"Amazon"}]},{"given":"Prashant","family":"Mathur","sequence":"additional","affiliation":[{"name":"Amazon"}]},{"given":"Xing","family":"Niu","sequence":"additional","affiliation":[{"name":"Amazon"}]},{"given":"Chandrashekhar","family":"Lavania","sequence":"additional","affiliation":[{"name":"Amazon"}]},{"given":"Brady","family":"Houston","sequence":"additional","affiliation":[{"name":"Amazon"}]},{"given":"Srikanth","family":"Vishnubhotla","sequence":"additional","affiliation":[{"name":"Amazon"}]},{"given":"Lijia","family":"Sun","sequence":"additional","affiliation":[{"name":"Amazon"}]},{"given":"Anthony","family":"Ferritto","sequence":"additional","affiliation":[{"name":"Amazon"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.4324\/9781003161660"},{"key":"ref2","first-page":"16582","article-title":"Neural dubber: Dubbing for videos according to scripts","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Hu","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356500"},{"key":"ref4","first-page":"255","article-title":"An empirical take on the dubbing vs. subtitling debate: An eye movement study","volume":"19","author":"Perego","year":"2016","journal-title":"Lingue e Linguaggi"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00551"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02580"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.1109\/ICME57554.2024.10687902","article-title":"Exposing lip-syncing deepfakes from mouth inconsistencies","author":"Datta","year":"2024"},{"key":"ref9","article-title":"The deepfake detection challenge dataset","volume-title":"CoRR","author":"Dolhansky","year":"2020"},{"key":"ref10","article-title":"Faces of the future: How generative ai is redefining likeness and identity in the age of artificial intelligence","author":"Bariach","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0287503"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1093\/jiplp\/jpz167"},{"key":"ref13","article-title":"Vasa-1: Lifelike audio-driven talking faces generated in real time","author":"Xu","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.479"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01442"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9747023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747158"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2022-11089","article-title":"Prosodic alignment for off-screen automatic dubbing","author":"Virkar","year":"2022"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2023-1063","article-title":"Improving isochronous machine translation with target factors and auxiliary counters","author":"Pal","year":"2023"},{"key":"ref20","article-title":"Jointly optimizing translations and speech timing to improve isochrony in automatic dubbing","author":"Chronopoulou","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475318"},{"key":"ref23","first-page":"2","article-title":"Learning audiovisual speech representation by masked multimodal cluster prediction","volume-title":"International Conference on Learning Representations","author":"Shi"},{"key":"ref24","first-page":"1","article-title":"Many-to-many spoken language translation via unified speech and text representation learning with unit-to-unit translation","author":"Kim","year":"2023"},{"key":"ref25","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Kong","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.235"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref29","article-title":"Seamlessm4t: Massively multilingual and multimodal machine translation","author":"Barrault","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref31","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890684.pdf?arnumber=10890684","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:20:35Z","timestamp":1774416035000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890684\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890684","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}