{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T15:46:41Z","timestamp":1781279201526,"version":"3.54.1"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"JST, Moonshot R&D","award":["JPMJMS2011 (methodology conceptualization)"],"award-info":[{"award-number":["JPMJMS2011 (methodology conceptualization)"]}]},{"name":"Scientific Research on Innovative Areas","award":["JP22H04875 (evaluation experiments)"],"award-info":[{"award-number":["JP22H04875 (evaluation experiments)"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Human-Mach. Syst."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/thms.2024.3456085","type":"journal-article","created":{"date-parts":[[2024,10,9]],"date-time":"2024-10-09T17:52:10Z","timestamp":1728496330000},"page":"733-742","source":"Crossref","is-referenced-by-count":2,"title":["Speech-Driven Gesture Generation Using Transformer-Based Denoising Diffusion Probabilistic Models"],"prefix":"10.1109","volume":"54","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8518-2939","authenticated-orcid":false,"given":"Bowen","family":"Wu","sequence":"first","affiliation":[{"name":"Graduate School of Engineering Science, Osaka University, Osaka, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3789-2981","authenticated-orcid":false,"given":"Chaoran","family":"Liu","sequence":"additional","affiliation":[{"name":"Guardian Robot Project, 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":"Guardian Robot Project, RIKEN, Kyoto, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hiroshi","family":"Ishiguro","sequence":"additional","affiliation":[{"name":"Hiroshi Ishiguro Laboratories, 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":"10.1037\/a0022128"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_2"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-58750-9_28"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3267851.3267898"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13946"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417838"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10030228"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3461615.3485407"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981535"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_36"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793720"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14776"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-05710-7_56"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2974061"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01049"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00201"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3267851.3267878"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3308532.3329472"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1080\/10447318.2021.1883883"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3382507.3418815"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13946"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3592097"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3610661.3616551"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3577190.3614135"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/650"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01016"},{"key":"ref30","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein","year":"2015"},{"key":"ref31","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref32","article-title":"Denoising diffusion implicit models","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Song","year":"2021"},{"key":"ref33","first-page":"16784","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn","volume":"162","author":"Nichol","year":"2022"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref35","article-title":"WaveGrad: Estimating gradients for waveform generation","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Chen","year":"2021"},{"key":"ref36","first-page":"8857","article-title":"Autoregressive denoising diffusion models for multivariate probabilistic time series forecasting","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rasul","year":"2021"},{"key":"ref37","article-title":"Diffusion-based voice conversion with fast maximum likelihood sampling scheme","volume-title":"Proc. 10th Int. Conf. Learn. Representation","author":"Popov","year":"2022"},{"key":"ref38","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Vaswani","year":"2017"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref40","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref41","article-title":"Galactica: A large language model for science","author":"Taylor","year":"2022"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01080"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/VR50410.2021.00037"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3355414"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00361"},{"key":"ref46","first-page":"6010","article-title":"Searching for efficient transformers for language modeling","volume":"34","author":"So","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3275156"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2022.3149173"},{"key":"ref49","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Dhariwal","year":"2021"},{"key":"ref50","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Representation","author":"Kingma","year":"2015"},{"key":"ref51","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol","year":"2021"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2019.00084"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.497"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3472306.3478333"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref56","article-title":"Classifier-free diffusion guidance","volume-title":"Proc. NeurIPS Workshop Deep Generative Models Downstream Appl.","author":"Ho","year":"2021"}],"container-title":["IEEE Transactions on Human-Machine Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221037\/10766051\/10712170.pdf?arnumber=10712170","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:49:01Z","timestamp":1732668541000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10712170\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":56,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/thms.2024.3456085","relation":{},"ISSN":["2168-2291","2168-2305"],"issn-type":[{"value":"2168-2291","type":"print"},{"value":"2168-2305","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}