{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T05:10:09Z","timestamp":1756789809127,"version":"3.44.0"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100009619","name":"Japan Science and Technology Agency (JST) Moonshot Research and Development","doi-asserted-by":"publisher","award":["JPMJMS2011"],"award-info":[{"award-number":["JPMJMS2011"]}],"id":[{"id":"10.13039\/100009619","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3602885","type":"journal-article","created":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T19:22:56Z","timestamp":1756236176000},"page":"150365-150378","source":"Crossref","is-referenced-by-count":0,"title":["A Feasibility Study With In-the-Wild Data in Human Interaction Settings: Acoustic-Visual Fusion for Predictive Sound Source Positioning"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1362-7940","authenticated-orcid":false,"given":"Zhichao","family":"Chen","sequence":"first","affiliation":[{"name":"Graduate School of Engineering Science, Osaka University, Osaka, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9778-7853","authenticated-orcid":false,"given":"Chenfei","family":"Xu","sequence":"additional","affiliation":[{"name":"Graduate School of Engineering Science, Osaka University, Osaka, Japan"}]},{"given":"Huthaifa","family":"Ahmad","sequence":"additional","affiliation":[{"name":"RIKEN Information Research and Development and Strategy Headquarters, RIKEN, Kyoto, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2961-8417","authenticated-orcid":false,"given":"Yuya","family":"Okadome","sequence":"additional","affiliation":[{"name":"Department of Information and Computer Technology, Tokyo University of Science, Tokyo, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0805-7648","authenticated-orcid":false,"given":"Hiroshi","family":"Ishiguro","sequence":"additional","affiliation":[{"name":"Graduate School of Engineering Science, Osaka University, Osaka, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6307-5104","authenticated-orcid":false,"given":"Yutaka","family":"Nakamura","sequence":"additional","affiliation":[{"name":"RIKEN Information Research and Development and Strategy Headquarters, RIKEN, Kyoto, Japan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2023.1125308"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3404752"},{"key":"ref3","first-page":"371","article-title":"Understanding large-language model (LLM)-powered human\u2013robot interaction","volume-title":"Proc. ACM\/IEEE Int. Conf. Hum.-Robot Interact.","author":"Kim"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3267385"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2016.09.015"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3442629"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.281849"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2013.7029977"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/S0921-8890(02)00325-1"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2828321"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2701973.2702019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-023-11183-7"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC58517.2023.10317433"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1609.03499"},{"article-title":"DiffWave: A versatile diffusion model for audio synthesis","volume-title":"Proc. 9th Int. Conf. Learn. Represent.","author":"Kong","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10955"},{"key":"ref18","first-page":"11873","article-title":"Multilingual turn-taking prediction using voice activity projection","volume-title":"Proc. Joint Int. Conf. Comput. Linguistics","author":"Inoue"},{"key":"ref19","article-title":"Voice activity projection model with multimodal encoders","author":"Saga","year":"2025","journal-title":"arXiv:2506.03980"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3165153"},{"key":"ref21","first-page":"26565","article-title":"Elucidating the design space of diffusion-based generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Karras"},{"key":"ref22","first-page":"69819","article-title":"OpenSTL: A comprehensive benchmark of spatio-temporal predictive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tan"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3010650"},{"volume-title":"Discrete-time Signal Processing","year":"1999","author":"Oppenheim","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1980.4308379"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1978.10837"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1121\/1.4820885"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.153"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/53.665"},{"key":"ref31","first-page":"19","article-title":"Functional beamforming","volume-title":"Proc. 5th Berlin beamforming Conf.","author":"Dougherty"},{"article-title":"Identification of noise source mechanisms using orthogonal beamforming","volume-title":"Proc. Int. Congr. Noise Vib. Emerg. Methods (NOVEM)","author":"Sarradj","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1969.7278"},{"volume-title":"Fundamentals of Speech Recognition","year":"1993","author":"Rabiner","key":"ref34"},{"article-title":"Taskprompter: Spatial-channel multi-task prompting for dense scene understanding","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Ye","key":"ref35"},{"key":"ref36","article-title":"Real-time flying object detection with YOLOv8","author":"Reis","year":"2023","journal-title":"arXiv:2305.09972"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3378180"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00280-0"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01485"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref41","first-page":"1144","article-title":"Video-to-video synthesis","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","volume":"31","author":"Wang"},{"volume-title":"Fundamentals of Acoustics","year":"2000","author":"Kinsler","key":"ref42"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11142245.pdf?arnumber=11142245","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T04:43:49Z","timestamp":1756788229000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11142245\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3602885","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}