{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:27:44Z","timestamp":1776889664961,"version":"3.51.2"},"reference-count":30,"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\/icassp49660.2025.10890859","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":["Speech2rtMRI: Speech-Guided Diffusion Model for Real-time MRI Video of the Vocal Tract during Speech"],"prefix":"10.1109","author":[{"given":"Hong","family":"Nguyen","sequence":"first","affiliation":[{"name":"University of Southern California,Signal Analysis and Interpretation Lab,Los Angeles,CA,90089"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sean","family":"Foley","sequence":"additional","affiliation":[{"name":"University of Southern California,Signal Analysis and Interpretation Lab,Los Angeles,CA,90089"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kevin","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Southern California,Signal Analysis and Interpretation Lab,Los Angeles,CA,90089"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuan","family":"Shi","sequence":"additional","affiliation":[{"name":"University of Southern California,Signal Analysis and Interpretation Lab,Los Angeles,CA,90089"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tiantian","family":"Feng","sequence":"additional","affiliation":[{"name":"University of Southern California,Signal Analysis and Interpretation Lab,Los Angeles,CA,90089"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shrikanth","family":"Narayanan","sequence":"additional","affiliation":[{"name":"University of Southern California,Signal Analysis and Interpretation Lab,Los Angeles,CA,90089"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2006.05.010"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/10471.001.0001"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1121\/1.5092807"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1216262.1216270"},{"key":"ref5","article-title":"Towards streaming speech-to-avatar synthesis","volume":"abs\/2310.16287","author":"Prabhune","year":"2023","journal-title":"ArXiv"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1121\/1.4931827"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-538"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1075\/sibil.36.15gic"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1044\/2018_PERS-SIG19-2018-0003"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1121\/10.0004789"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1121\/1.4813590"},{"key":"ref12","article-title":"Speaker dependent acoustic-to-articulatory inversion using real-time mri of the vocal tract","volume":"abs\/2008.02098","author":"G\u2019abor Csap\u2019o","year":"2020","journal-title":"ArXiv"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682506"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-16"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2664"},{"key":"ref16","article-title":"Ciwagan: Articulatory information exchange","author":"Begus","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06443-4"},{"key":"ref18","article-title":"Speech driven video editing via an audio-conditioned diffusion model","volume":"abs\/2301.04474","author":"Bigioi","year":"2023","journal-title":"ArXiv"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1121\/1.1652588"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094797"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-021-00976-x"},{"key":"ref22","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref25","article-title":"Fvd: A new metric for video generation","author":"Unterthiner","year":"2019","journal-title":"DGS@ICLR"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref27","article-title":"Fr\u00e9chet video motion distance: A metric for evaluating motion consistency in videos","volume-title":"First Workshop on Controllable Video Generation@ ICML24","author":"Liu"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/S0095-4470(19)31446-9"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1111\/j.1096-3642.1985.tb01178.x"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2019.02998"}],"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\/10890859.pdf?arnumber=10890859","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:42Z","timestamp":1774416282000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890859\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890859","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}