{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T18:40:46Z","timestamp":1785955246927,"version":"3.56.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,5]]},"DOI":"10.1109\/smc58881.2025.11343015","type":"proceedings-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T20:54:44Z","timestamp":1769633684000},"page":"5827-5832","source":"Crossref","is-referenced-by-count":1,"title":["Visual-based spatial audio generation system for multi-speaker environments\n                    <sup>*<\/sup>"],"prefix":"10.1109","author":[{"given":"Xiaojing","family":"Liu","sequence":"first","affiliation":[{"name":"Queen Mary University of London,School of Electronic Engineering and Computer Science, Center for Digital Music (C4DM),United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ogulcan","family":"Gurelli","sequence":"additional","affiliation":[{"name":"Queen Mary University of London,School of Electronic Engineering and Computer Science, Center for Digital Music (C4DM),United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Wang","sequence":"additional","affiliation":[{"name":"Xidian University,Department of Electrical Engineering,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joshua","family":"Reiss","sequence":"additional","affiliation":[{"name":"Queen Mary University of London,School of Electronic Engineering and Computer Science, Center for Digital Music (C4DM),United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"A survey on multimodal wearable sensor-based human action recognition","author":"Ni","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2018.8486455"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/VR.2019.8798247"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201391"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2008.4607471"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2011.6012065"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/iros40897.2019.8968183"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00041"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16302"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-7962-2_39"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01523"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.596"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref16","article-title":"Demucs: Deep extractor for music sources with extra unlabeled data remixed","author":"D\u00e9fossez","year":"2019"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3390\/app8112029"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref19","article-title":"Self-supervised generation of spatial audio for 360 video","volume":"31","author":"Morgado","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"1\/2","key":"ref20","first-page":"3","article-title":"Peaq-the itu standard for objective measurement of perceived audio quality","volume":"48","author":"Thiede","year":"2000","journal-title":"J. Audio Eng. Soc."},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2585878"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2003"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.878256"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3384034"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-166"}],"event":{"name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","location":"Vienna, Austria","start":{"date-parts":[[2025,10,5]]},"end":{"date-parts":[[2025,10,8]]}},"container-title":["2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11342430\/11342431\/11343015.pdf?arnumber=11343015","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T20:50:38Z","timestamp":1770843038000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11343015\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,5]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/smc58881.2025.11343015","relation":{},"subject":[],"published":{"date-parts":[[2025,10,5]]}}}