{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:11:21Z","timestamp":1774419081445,"version":"3.50.1"},"reference-count":47,"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\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","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\/icassp49660.2025.10889780","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["V2SFlow: Video-to-Speech Generation with Speech Decomposition and Rectified Flow"],"prefix":"10.1109","author":[{"given":"Jeongsoo","family":"Choi","sequence":"first","affiliation":[{"name":"Korea Advanced Institute of Science and Technology"}]},{"given":"Ji-Hoon","family":"Kim","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology"}]},{"given":"Jinyu","family":"Li","sequence":"additional","affiliation":[{"name":"Mircrosoft"}]},{"given":"Joon Son","family":"Chung","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology"}]},{"given":"Shujie","family":"Liu","sequence":"additional","affiliation":[{"name":"Mircrosoft"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2716178"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953127"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33012588"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095582"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01802"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-194"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28055"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.543"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611787"},{"key":"ref10","article-title":"Lipvoicer: Generating speech from silent videos guided by lip reading","volume-title":"Proc. ICLR","author":"Yemini"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10770"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00718"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19966"},{"key":"ref14","article-title":"Lip to speech synthesis with visual context attentional GAN","author":"Kim","year":"2021","journal-title":"NeurIPS"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3162495"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548081"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-475"},{"key":"ref18","article-title":"Neural analysis and synthesis: Reconstructing speech from self-supervised representations","author":"Choi","year":"2021","journal-title":"NeurIPS"},{"key":"ref19","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","volume-title":"Proc. ICLR","author":"Liu"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.20003"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref23","first-page":"1336","article-title":"On generative spoken language modeling from raw audio","volume":"9","author":"Lakhotia","year":"2021","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.769"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3444470"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414853"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29740"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.1005751"},{"key":"ref29","article-title":"Neural discrete representation learning","author":"Van Den Oord","year":"2017","journal-title":"NeurIPS"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01033"},{"key":"ref32","article-title":"Learning audiovisual speech representation by masked multimodal cluster prediction","volume-title":"Proc. ICLR","author":"Shi"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-232"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref35","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref36","article-title":"Classifier-free diffusion guidance","volume-title":"NeurIPS 2021 Workshop","author":"Ho"},{"key":"ref37","article-title":"Lrs3-ted: a large-scale dataset for visual speech recognition","author":"Afouras","year":"2018"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00525"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.116"},{"key":"ref45","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Proc. ICML","author":"Esser"},{"key":"ref46","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"Kong","year":"2020","journal-title":"NeurIPS"},{"key":"ref47","article-title":"Denoising diffusion implicit models","volume-title":"Proc. ICLR","author":"Song"}],"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\/10889780.pdf?arnumber=10889780","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:20:15Z","timestamp":1774416015000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889780\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889780","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}