{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:02:47Z","timestamp":1776884567576,"version":"3.51.2"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"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":[[2021,10,17]]},"DOI":"10.1109\/waspaa52581.2021.9632773","type":"proceedings-article","created":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T21:12:28Z","timestamp":1639429948000},"page":"211-215","source":"Crossref","is-referenced-by-count":17,"title":["Differentiable Tracking-Based Training of Deep Learning Sound Source Localizers"],"prefix":"10.1109","author":[{"given":"Sharath","family":"Adavanne","sequence":"first","affiliation":[]},{"given":"Archontis","family":"Politis","sequence":"additional","affiliation":[]},{"given":"Tuomas","family":"Virtanen","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2901664"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3019646"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3040031"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1121\/1.5147419"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.23919\/Eusipco47968.2020.9287344"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3049337"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937277"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178484"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2016.7738817"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.33682\/xb0q-a335"},{"key":"ref28","article-title":"The USTC-IFLYTEK system for sound event localization and detection of dcase2020 challenge","author":"wang","year":"2020","journal-title":"DCASE2020 Challenge Tech Rep"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-04619-7_8"},{"key":"ref27","article-title":"A dataset of reverberant spatial sound scenes with moving sources for sound event localization and detection","author":"politis","year":"2020","journal-title":"Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2007.4425280"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2876169"},{"key":"ref5","author":"pulkki","year":"2018","journal-title":"Parametric time-frequency-domain spatial audio"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2018.2885636"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553182"},{"key":"ref2","article-title":"Overview and evaluation of sound event localization and detection in DCASE 2019","author":"politis","year":"2020","journal-title":"IEEE\/ACM Transactions on Audio Speech and Language Processing"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2900164"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-04619-7"},{"key":"ref20","author":"adavanne","year":"2020","journal-title":"Sound Event Localization Detection and Tracking by Deep Neural Networks"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref21","article-title":"Event-independent network for polyphonic sound event localization and detection","author":"cao","year":"2020","journal-title":"Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1155\/2008\/246309"},{"key":"ref23","first-page":"1","article-title":"On performance evaluation of multi-object filters","author":"schuhmacher","year":"2008","journal-title":"2008 11th International Conference on Information Fusion FUSION"},{"key":"ref26","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"NIPS"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00682"}],"event":{"name":"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","location":"New Paltz, NY, USA","start":{"date-parts":[[2021,10,17]]},"end":{"date-parts":[[2021,10,20]]}},"container-title":["2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9632687\/9632666\/09632773.pdf?arnumber=9632773","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:54:24Z","timestamp":1652201664000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9632773\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/waspaa52581.2021.9632773","relation":{},"subject":[],"published":{"date-parts":[[2021,10,17]]}}}