{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:36:05Z","timestamp":1776886565237,"version":"3.51.2"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development","award":["2022YFB2602000"],"award-info":[{"award-number":["2022YFB2602000"]}]},{"name":"National Key Research and Development","award":["XJTLU RDF-22-01-084"],"award-info":[{"award-number":["XJTLU RDF-22-01-084"]}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/T019751\/1"],"award-info":[{"award-number":["EP\/T019751\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3451974","type":"journal-article","created":{"date-parts":[[2024,8,29]],"date-time":"2024-08-29T18:02:48Z","timestamp":1724954568000},"page":"4313-4327","source":"Crossref","is-referenced-by-count":7,"title":["Selective-Memory Meta-Learning With Environment Representations for Sound Event Localization and Detection"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-5082-3835","authenticated-orcid":false,"given":"Jinbo","family":"Hu","sequence":"first","affiliation":[{"name":"Key Laboratory of Noise and Vibration Research, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9086-7027","authenticated-orcid":false,"given":"Yin","family":"Cao","sequence":"additional","affiliation":[{"name":"Department of Intelligent Science, Xi'an Jiaotong Liverpool University, Suzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Wu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Noise and Vibration Research, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiuqiang","family":"Kong","sequence":"additional","affiliation":[{"name":"Chinese University of Hong Kong, Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1734-3785","authenticated-orcid":false,"given":"Feiran","family":"Yang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Acoustics, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9708-1075","authenticated-orcid":false,"given":"Mark D.","family":"Plumbley","sequence":"additional","affiliation":[{"name":"Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2807-6130","authenticated-orcid":false,"given":"Jun","family":"Yang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Noise and Vibration Research, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.33682\/1xwd-5v76"},{"key":"ref2","first-page":"165","article-title":"A dataset of reverberant spatial sound scenes with moving sources for sound event localization and detection","volume-title":"Proc. Detection Classification Acoustic Scenes Events Workshop","author":"Politis","year":"2020"},{"key":"ref3","first-page":"125","article-title":"A dataset of dynamic reverberant sound scenes with directional interferers for sound event localization and detection","volume-title":"Proc. Detection Classification Acoustic Scenes Events Workshop","author":"Politis","year":"2021"},{"key":"ref4","first-page":"161","article-title":"STARSS22: A dataset of spatial recordings of real scenes with spatiotemporal annotations of sound events","volume-title":"Proc. Detection Classification Acoustic Scenes Events Workshop","author":"Politis","year":"2022"},{"key":"ref5","first-page":"72931","article-title":"STARSS23: An audio-visual dataset of spatial recordings of real scenes with spatiotemporal annotations of sound events","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Shimada","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2018.2885636"},{"key":"ref7","first-page":"11","article-title":"Event-independent network for polyphonic sound event localization and detection","volume-title":"Proc. Detection Classification Acoustic Scenes Events Workshop","author":"Cao","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413473"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747283"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413609"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746384"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.05.083"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2945942"},{"key":"ref14","first-page":"46","article-title":"Sound event localization and detection for real spatial sound scenes: Event-independent network and data augmentation chains","volume-title":"Proc. Detection Classification Acoustic Scenes Events Workshop","author":"Hu"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1121\/10.0011809"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3256088"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746754"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref20","article-title":"TAU spatial room impulse response database (TAU-SRIR DB)","author":"Politis","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1121\/1.382599"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052932"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461310"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09905-3"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1121\/1.4740497"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3004555"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3386252"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3079209"},{"key":"ref29","first-page":"1620","article-title":"A closer look at few-shot classification","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01436"},{"key":"ref31","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn","year":"2017"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3167258"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3231700"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3275029"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00245"},{"key":"ref36","first-page":"1","article-title":"Multimodal model-agnostic meta-learning via task-aware modulation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vuorio","year":"2019"},{"key":"ref37","first-page":"51","article-title":"Meta-SELD: Meta-learning for fast adaptation to the new environment in sound event localization and detection","volume-title":"Proc. Detection Classification Acoust. Scenes Events Workshop","author":"Hu"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448497"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-45664-4"},{"key":"ref41","article-title":"Microphone array processing for parametric spatial audio techniques","author":"Politis","year":"2016"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170028"},{"issue":"86","key":"ref43","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref44","article-title":"[DCASE2022 Task 3] Synthetic SELD mixtures for baseline training","author":"Politis","year":"2022"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937220"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3047233"},{"key":"ref47","first-page":"4061","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90095-3"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01075"},{"key":"ref51","first-page":"1","article-title":"GWA: A large geometric-wave acoustic dataset for audio processing","volume-title":"Proc. Special Int. Group Comput. Graph. Interactive Techn. Conf.","author":"Tang","year":"2022"},{"key":"ref52","first-page":"3770","article-title":"Two sides of meta-learning evaluation: In vs. out of distribution","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Setlur","year":"2021"},{"key":"ref53","first-page":"67007","article-title":"Secure out-of-distribution task generalization with energy-based models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen","year":"2023"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570655\/10304349\/10659228.pdf?arnumber=10659228","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,3]],"date-time":"2024-10-03T17:24:46Z","timestamp":1727976286000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10659228\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3451974","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}