{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:02:30Z","timestamp":1777888950192,"version":"3.51.4"},"reference-count":69,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01222","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"13151-13161","source":"Crossref","is-referenced-by-count":0,"title":["MAVFlow: Preserving Paralinguistic Elements with Conditional Flow Matching for Zero-Shot AV2AV Multilingual Translation"],"prefix":"10.1109","author":[{"given":"Sungwoo","family":"Cho","sequence":"first","affiliation":[{"name":"KAIST AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeongsoo","family":"Choi","sequence":"additional","affiliation":[{"name":"KAIST EE"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sungnyun","family":"Kim","sequence":"additional","affiliation":[{"name":"KAIST AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Se-Young","family":"Yun","sequence":"additional","affiliation":[{"name":"KAIST AI"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.ijcnlp-demo.1"},{"key":"ref2","article-title":"Lrs3-ted: a large-scale dataset for visual speech recognition","author":"Afouras","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2279"},{"key":"ref4","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00551"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref7","first-page":"2709","article-title":"Yourtts: Towards zero-shot multi-speaker tts and zero-shot voice conversion for everyone","volume-title":"International conference on machine learning","author":"Casanova","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2016"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02056"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1897"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1294"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.593"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02580"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref15","article-title":"No language left behind: Scaling human-centered machine translation","author":"Costa-Juss\u00e0","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref16","first-page":"87808794","article-title":"Diffusion models beat GANs on image synthesis","author":"Dhariwal","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref17","article-title":"Cosyvoice: A scalable multilingual zero-shot text-to-speech synthesizer based on supervised semantic tokens","author":"Du","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref18","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first international conference on machine learning","author":"Esser","year":"2024"},{"issue":"107","key":"ref19","first-page":"1","article-title":"Beyond english-centric multilingual machine translation","volume":"22","author":"Fan","year":"2021","journal-title":"Journal of Machine Learning Research"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.iwslt-1.31"},{"key":"ref21","article-title":"Lumina-t2x: Transforming text into any modality, resolution, and duration via flow-based large diffusion transformers","author":"Gao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref22","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems, 30"},{"key":"ref23","first-page":"6840","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0628"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.479"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-469"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1951"},{"key":"ref28","first-page":"1012010134","article-title":"Translatotron 2: High-quality direct speech-to-speech translation with voice preservation","volume-title":"International Conference on Machine Learning","author":"Jia","year":"2022"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3444470"},{"key":"ref30","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":"ref31","article-title":"DiffWave: A versatile diffusion model for audio synthesis","volume-title":"International Conference on Learning Representations (ICLR)","author":"Kong","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1177\/0267323102017003694"},{"key":"ref33","first-page":"14281436","article-title":"Towards automatic face-to-face translation","volume-title":"Proceedings of the 27th ACM international conference on multimedia","author":"Prajwal","year":"2019"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3362\/0262-8104.2002.009"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.63"},{"key":"ref36","article-title":"Flow matching for generative modeling","author":"Lipman","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref37","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","author":"Liu","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref38","article-title":"Instaflow: One step is enough for high-quality diffusionbased text-to-image generation","volume-title":"The Twelfth International Conference on Learning Representations","author":"Liu","year":"2023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_2"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.931"},{"key":"ref41","first-page":"641","article-title":"Integration of speech recognition and machine translation in computer-assisted translation","volume-title":"Proceedings of the 9th International Conference on Spoken Language Processing (Interspeech\/ICSLP)","author":"Matusov","year":"2006"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-5209"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1038\/264746a0"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448291"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448426"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1999.758176"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20102"},{"key":"ref50","first-page":"8599","article-title":"Grad-TTS: A diffusion probabilistic model for text-to-speech","volume-title":"International Conference on Machine Learning (ICML)","author":"Popov","year":"2021"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref52","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2023"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-11"},{"key":"ref55","article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","volume-title":"International Conference on Learning Representations","author":"Shi","year":"2022"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref58","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612365"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00280-0"},{"key":"ref61","article-title":"Improving and generalizing flow-based generative models with minibatch optimal transport","author":"Tong","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"ref63","article-title":"Audiobox: Unified audio generation with natural language prompts","author":"Vyas","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW59220.2023.10193719"},{"key":"ref65","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-503"},{"key":"ref67","article-title":"Large-scale multilingual audio visual dubbing","author":"Yang","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019299"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445907.pdf?arnumber=11445907","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:03:26Z","timestamp":1777611806000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445907\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01222","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}