{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T21:40:31Z","timestamp":1776116431826,"version":"3.50.1"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"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":["IEEE Trans. Visual. Comput. Graphics"],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/tvcg.2025.3549898","type":"journal-article","created":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T02:33:19Z","timestamp":1743042799000},"page":"3397-3407","source":"Crossref","is-referenced-by-count":3,"title":["Multimodal Neural Acoustic Fields for Immersive Mixed Reality"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5370-6192","authenticated-orcid":false,"given":"Guaneen","family":"Tong","sequence":"first","affiliation":[{"name":"Department of Computer Science, The University of North Carolina at Chapel Hill, Chapel Hill, NC, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1877-430X","authenticated-orcid":false,"given":"Johnathan Chi-Ho","family":"Leung","sequence":"additional","affiliation":[{"name":"Department of Computer Science, The University of North Carolina at Chapel Hill, Chapel Hill, NC, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5759-7917","authenticated-orcid":false,"given":"Xi","family":"Peng","sequence":"additional","affiliation":[{"name":"Department of Computer Science, The University of North Carolina at Chapel Hill, Chapel Hill, NC, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4199-0330","authenticated-orcid":false,"given":"Haosheng","family":"Shi","sequence":"additional","affiliation":[{"name":"Department of Computer Science, The University of North Carolina at Chapel Hill, Chapel Hill, NC, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liujie","family":"Zheng","sequence":"additional","affiliation":[{"name":"Department of Computer Science, The University of North Carolina at Chapel Hill, Chapel Hill, NC, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0660-5014","authenticated-orcid":false,"given":"Shengze","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, The University of North Carolina at Chapel Hill, Chapel Hill, NC, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arryn Carlos","family":"O'Brien","sequence":"additional","affiliation":[{"name":"Department of Computer Science, The University of North Carolina at Chapel Hill, Chapel Hill, NC, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ashley Paula-Ann","family":"Neall","sequence":"additional","affiliation":[{"name":"Department of Computer Science, The University of North Carolina at Chapel Hill, Chapel Hill, NC, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Grace","family":"Fei","sequence":"additional","affiliation":[{"name":"Department of Computer Science, The University of North Carolina at Chapel Hill, Chapel Hill, NC, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martim","family":"Gaspar","sequence":"additional","affiliation":[{"name":"Department of Computer Science, The University of North Carolina at Chapel Hill, Chapel Hill, NC, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3092-7435","authenticated-orcid":false,"given":"Praneeth","family":"Chakravarthula","sequence":"additional","affiliation":[{"name":"Department of Computer Science, The University of North Carolina at Chapel Hill, Chapel Hill, NC, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","journal-title":"Listen with personalized spatial audio for airpods and beats"},{"key":"ref2","article-title":"On seeing stuff: the perception of materials by humans and machines","author":"Adelson","year":"2001","journal-title":"IS&T\/SPIE Electronic Imaging"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2011.04.004"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01829"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00620"},{"key":"ref7","first-page":"231","article-title":"Introduction to head-related transfer functions (hrtfs): Representations of hrtfs in time, frequency, and space","volume":"49","author":"Cheng","journal-title":"AES: Journal of the Audio Engineering Society"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2022.3203102"},{"key":"ref9","volume-title":"Adversarial audio synthesis","author":"Donahue","year":"2019"},{"key":"ref10","volume-title":"Gansynth: Adversarial neural audio synthesis","author":"Engel","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.141505198"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00041"},{"key":"ref14","author":"Gardner","year":"1994","journal-title":"Hrtf measurements of a kemar dummy-head micro-phone"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1121\/1.1981556"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref17","author":"He","year":"2015","journal-title":"Deep residual learning for image recognition"},{"key":"ref18","volume-title":"Putting nerf on a diet: Seman-tically consistent few-shot view synthesis","author":"Jain","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606782"},{"key":"ref20","author":"Jiang","year":"2023","journal-title":"Gaussianshader: 3d gaussian splatting with shading functions for reflective surfaces"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657448"},{"key":"ref22","author":"Kerbl","year":"2023","journal-title":"3d gaus-sian splatting for real-time radiance field rendering"},{"key":"ref23","author":"Khalfaoui- Hassani","year":"2023","journal-title":"Dilated convolution with learnable spacings"},{"key":"ref24","volume-title":"Diffwave: A versatile diffusion model for audio synthesis","author":"Kong","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/0022-460X(68)90198-3"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_12"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1201\/9781315372150"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.96"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00643"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02518"},{"key":"ref31","volume-title":"Av-nerf: Learning neural fields for real-world audio-visual scene synthesis","author":"Liang","year":"2023"},{"key":"ref32","volume-title":"Neural actor: Neural free-view synthesis of hu-man actors with pose control","author":"Liu","year":"2022"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/VR46266.2020.00111"},{"key":"ref34","volume-title":"Architectural acoustics","author":"Long","year":"2014"},{"key":"ref35","first-page":"3165","article-title":"Learning neural acoustic fields","volume":"35","author":"Luo","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref36","author":"Mehri","year":"2017","journal-title":"Samplernn: An unconditional end-to-end neural audio generation model"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/131"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1250\/ast.1.167"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1038\/nature05724"},{"key":"ref41","volume-title":"Regnerf: Regularizing neural radiance fields for view synthesis from sparse inputs","author":"Niemeyer","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00581"},{"key":"ref44","volume-title":"Full-band general audio synthesis with score-based diffusion","author":"Pascual","year":"2022"},{"key":"ref45","author":"Pumarola","year":"2020","journal-title":"D-nerf: Neural radiance fields for dynamic scenes"},{"key":"ref46","author":"Qin","year":"2023","journal-title":"Langsplat: 3d language gaussian splatting"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01072"},{"key":"ref48","article-title":"Deep impulse re-sponses: Estimating and parameterizing filters with deep net-works","author":"Richard","year":"2022","journal-title":"arXiv preprint"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/2947508"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/VR.2017.7892239"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1080\/09298210600696857"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01860"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1364\/JOSAA.25.000846"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1121\/1.2766781"},{"key":"ref55","article-title":"Scene repre-sentation networks: Continuous 3d-structure-aware neural scene representations","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Sitzmann","year":"2019"},{"key":"ref56","author":"Sridhar","year":"2017","journal-title":"A method for efficiently calculating head-related transfer functions directly from head scan point clouds"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414364"},{"key":"ref58","article-title":"The Replica dataset: A digital replica of indoor spaces","author":"Straub","year":"2019","journal-title":"arXiv preprint"},{"key":"ref59","first-page":"8144","article-title":"Inras: Implicit neural repre-sentation for audio scenes","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Su","year":"2022"},{"key":"ref60","author":"Su","year":"2021","journal-title":"A-nerf: Articulated neural radiance fields for learning human shape, appearance, and pose"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/VR50410.2021.00111"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1121\/1.2164987"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01272"},{"key":"ref64","author":"van den Oord","year":"2016","journal-title":"Wavenet: A generative model for raw audio"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1121\/1.398336"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1250\/ast.35.159"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1121\/1.407089"},{"key":"ref68","volume-title":"Extrapolation, Interpolation, and Smoothing of Stationary Time Series","author":"Wiener","year":"1964"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00455"},{"issue":"16","key":"ref71","doi-asserted-by":"crossref","DOI":"10.3390\/app12168155","article-title":"Magnitude modeling of person-alized hrtf based on ear images and anthropometric measurements","volume":"12","author":"Zhao","year":"2022","journal-title":"Applied Sciences"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1121"},{"key":"ref73","volume-title":"Edmsound: Spectrogram based diffusion models for efficient and high-quality audio synthesis","author":"Zhu","year":"2023"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2003.1285855"}],"container-title":["IEEE Transactions on Visualization and Computer Graphics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/2945\/10977053\/10938352.pdf?arnumber=10938352","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,26]],"date-time":"2025-04-26T05:10:09Z","timestamp":1745644209000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10938352\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":74,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tvcg.2025.3549898","relation":{},"ISSN":["1077-2626","1941-0506","2160-9306"],"issn-type":[{"value":"1077-2626","type":"print"},{"value":"1941-0506","type":"electronic"},{"value":"2160-9306","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}