{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:17:40Z","timestamp":1776889060219,"version":"3.51.2"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10448497","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"636-640","source":"Crossref","is-referenced-by-count":11,"title":["Zero- and Few-Shot Sound Event Localization and Detection"],"prefix":"10.1109","author":[{"given":"Kazuki","family":"Shimada","sequence":"first","affiliation":[{"name":"Sony AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kengo","family":"Uchida","sequence":"additional","affiliation":[{"name":"Sony AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuichiro","family":"Koyama","sequence":"additional","affiliation":[{"name":"Sony Group Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takashi","family":"Shibuya","sequence":"additional","affiliation":[{"name":"Sony AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shusuke","family":"Takahashi","sequence":"additional","affiliation":[{"name":"Sony Group Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuki","family":"Mitsufuji","sequence":"additional","affiliation":[{"name":"Sony AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tatsuya","family":"Kawahara","sequence":"additional","affiliation":[{"name":"Kyoto University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2871183"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2017438"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.20965\/jrm.2017.p0037"},{"key":"ref4","article-title":"Emergency vehicles audio detection and localization in autonomous driving","author":"Sun","year":"2021","journal-title":"arXiv"},{"key":"ref5","article-title":"A dataset of dynamic reverberant sound scenes with directional interferers for sound event localization and detection","volume-title":"Proc. of DCASE Workshop","author":"Politis"},{"key":"ref6","article-title":"STARSS22: A dataset of spatial recordings of real scenes with spatiotemporal annotations of sound events","volume-title":"Proc. of DCASE Workshop","author":"Politis"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/jstsp.2018.2885636"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413609"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413473"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747604"},{"key":"ref11","article-title":"META-SELD: Meta-learning for fast adaptation to the new environment in sound event localization and detection","volume-title":"Proc. of DCASE Workshop","author":"Hu"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096460"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095144"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094681"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-982"},{"key":"ref18","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. of ICML","author":"Radford"},{"key":"ref19","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","volume-title":"Proc. of ICLR","author":"Gu"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682558"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054708"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054712"},{"key":"ref23","article-title":"STARSS23: An audio-visual dataset of spatial recordings of real scenes with spatiotemporal annotations of sound events","volume-title":"Proc. of NeurIPS","author":"Shimada"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295163"},{"key":"ref25","article-title":"Crossstitch networks for multi-task learning","volume-title":"Proc. of IEEE CVPR","author":"Misra"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937220"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746384"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2751969"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.33682\/3qgs-e216"},{"key":"ref31","article-title":"Accurate, large minibatch SGD: Training ImageNetin 1 hour","author":"Goyal","year":"2017","journal-title":"arXiv"},{"key":"ref32","article-title":"Averaging weights leads to wider optima and better generalization","volume-title":"Proc. of UAI","author":"Izmailov"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10448497.pdf?arnumber=10448497","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,3]],"date-time":"2024-08-03T04:54:48Z","timestamp":1722660888000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448497\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448497","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}