{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:13:54Z","timestamp":1776885234488,"version":"3.51.2"},"reference-count":34,"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"}],"funder":[{"DOI":"10.13039\/501100002551","name":"Seoul National University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002551","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890579","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":["Speaking Without Sound: Multi-speaker Silent Speech Voicing with Facial Inputs Only"],"prefix":"10.1109","author":[{"given":"Jaejun","family":"Lee","sequence":"first","affiliation":[{"name":"Seoul National University,Music and Audio Research Group (MARG),Department of Intelligence and Information"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoori","family":"Oh","sequence":"additional","affiliation":[{"name":"Seoul National University,Music and Audio Research Group (MARG),Department of Intelligence and Information"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kyogu","family":"Lee","sequence":"additional","affiliation":[{"name":"Seoul National University,Music and Audio Research Group (MARG),Department of Intelligence and Information"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1044\/1092-4388(2008\/069)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.08.002"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3026579"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.445"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097120"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613825"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-232"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2006-212"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746484"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20873-8_18"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2007.10.001"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1037\/a0030945"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2136"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475198"},{"key":"ref15","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"International Conference on Machine Learning","author":"Kim"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref17","first-page":"1558","article-title":"Autoencoding beyond pixels using a learned similarity metric","volume-title":"International conference on machine learning","author":"Larsen"},{"issue":"9\/10","key":"ref18","first-page":"341","article-title":"Speak and unspeak with praat","volume":"5","author":"Boersma","year":"2001","journal-title":"Glot International"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1006\/jsvi.1998.2072"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(90)90021-Z"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"ref22","article-title":"Density estimation using real nvp","author":"Dinh","year":"2016"},{"key":"ref23","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref24","first-page":"18 003","article-title":"Contentvec: An improved self-supervised speech representation by disentangling speakers","volume-title":"International Conference on Machine Learning","author":"Qian"},{"key":"ref25","first-page":"17 022","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":"10.1109\/ICASSP.2019.8682298"},{"key":"ref27","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.wocn.2018.07.001"},{"key":"ref29","article-title":"Lrs3-ted: a large-scale dataset for visual speech recognition","author":"Afouras","year":"2018"},{"key":"ref30","first-page":"28 492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref31","article-title":"Bigvgan: A universal neural vocoder with large-scale training","author":"Lee","year":"2022"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21350"},{"key":"ref33","first-page":"16 251","article-title":"Neural analysis and synthesis: Reconstructing speech from self-supervised representations","volume":"34","author":"Choi","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref34","article-title":"Nansy++: Unified voice synthesis with neural analysis and synthesis","volume-title":"The Eleventh International Conference on Learning Representations","author":"Choi"}],"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\/10890579.pdf?arnumber=10890579","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:48Z","timestamp":1774416168000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890579\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890579","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}