{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T05:59:24Z","timestamp":1781243964269,"version":"3.54.1"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"RIKEN Special Postdoctoral Program"},{"name":"JST Moonshot R&D","award":["JPMJMS2011"],"award-info":[{"award-number":["JPMJMS2011"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/lra.2026.3700424","type":"journal-article","created":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T19:57:26Z","timestamp":1780603046000},"page":"8720-8727","source":"Crossref","is-referenced-by-count":0,"title":["Speech-Driven Gesture Generation via Conditional Flow Matching With Masked Training and Clamped Sampling"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8518-2939","authenticated-orcid":false,"given":"Bowen","family":"Wu","sequence":"first","affiliation":[{"name":"RIKEN, Kyoto, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8130-1048","authenticated-orcid":false,"given":"Carlos Toshinori","family":"Ishi","sequence":"additional","affiliation":[{"name":"RIKEN, Kyoto, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4071-1352","authenticated-orcid":false,"given":"Takashi","family":"Minato","sequence":"additional","affiliation":[{"name":"RIKEN, Kyoto, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0805-7648","authenticated-orcid":false,"given":"Hiroshi","family":"Ishiguro","sequence":"additional","affiliation":[{"name":"ATR, Kyoto, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511807572"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.7208\/chicago\/9780226514642.001.0001"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1037\/a0022128"},{"key":"ref4","article-title":"Towards a GENEA leaderboardAn extended, living benchmark for evaluating and advancing conversational motion synthesis","author":"Nagy","year":"2024"},{"key":"ref5","first-page":"3015","article-title":"HARMON: Whole-body motion generation of humanoid robots from language descriptions","volume-title":"Proc. Conf. Robot Learn.","author":"Jiang","year":"2025"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3592458"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2024.3456085"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00115"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3658134"},{"key":"ref10","article-title":"Flow matching for generative modeling","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lipman","year":"2023"},{"key":"ref11","first-page":"1","article-title":"Improving and generalizing flow-based generative models with minibatch optimal transport","author":"Tong","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref12","first-page":"12606","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Esser","year":"2024"},{"key":"ref13","article-title":"Fast flow-based visuomotor policies via conditional optimal transport couplings","volume-title":"Proc. Conf. Robot Learn.","author":"Sochopoulos","year":"2025"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4405"},{"key":"ref15","article-title":"On the guidance of flow matching","author":"Feng","year":"2025"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01473"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3267851.3267878"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3308532.3329472"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793720"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417838"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3382507.3418815"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10030228"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3461615.3485407"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13946"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01110"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0633"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00581"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01016"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3592097"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445998"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01017"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981535"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-023-01051-8"},{"key":"ref34","article-title":"VDT: General-purpose video diffusion transformers via mask modeling","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lu","year":"2024"},{"key":"ref35","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00795"},{"key":"ref38","article-title":"On the variance of the adaptive learning rate and beyond","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu","year":"2020"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_36"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3389\/fneur.2018.00615"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11520964\/11551310.pdf?arnumber=11551310","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T05:39:53Z","timestamp":1781242793000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11551310\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":40,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/lra.2026.3700424","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}