{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T20:53:10Z","timestamp":1777495990850,"version":"3.51.4"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","award":["637422 EVERYSOUND"],"award-info":[{"award-number":["637422 EVERYSOUND"]}],"id":[{"id":"10.13039\/501100000781","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":[[2021]]},"DOI":"10.1109\/taslp.2020.3047233","type":"journal-article","created":{"date-parts":[[2020,12,24]],"date-time":"2020-12-24T22:26:26Z","timestamp":1608848786000},"page":"684-698","source":"Crossref","is-referenced-by-count":108,"title":["Overview and Evaluation of Sound Event Localization and Detection in DCASE 2019"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0595-2356","authenticated-orcid":false,"given":"Archontis","family":"Politis","sequence":"first","affiliation":[{"name":"Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, Finland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6640-9752","authenticated-orcid":false,"given":"Annamaria","family":"Mesaros","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, Finland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5001-6911","authenticated-orcid":false,"given":"Sharath","family":"Adavanne","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, Finland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8855-0415","authenticated-orcid":false,"given":"Toni","family":"Heittola","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, Finland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4604-9729","authenticated-orcid":false,"given":"Tuomas","family":"Virtanen","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, Finland"}]}],"member":"263","reference":[{"key":"ref39","article-title":"A report on sound event localization and detection","author":"lin","year":"2019"},{"key":"ref38","article-title":"Cross-task learning for audio tagging, sound event detection and spatial localization: DCASE 2019 baseline systems","author":"kong","year":"2019"},{"key":"ref33","first-page":"55","article-title":"GCC-PHAT cross-correlation audio features for simultaneous sound event localization and detection (SELD) on multiple rooms","author":"cordourier-maruri","year":"0","journal-title":"Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE)"},{"key":"ref32","article-title":"Sound event detection and localization using ResNet RNN and time-delay DOA","author":"tan","year":"2019"},{"key":"ref31","article-title":"Polyphonic sound event detection and localization using a two-stage strategy","author":"lihong","year":"2019"},{"key":"ref30","article-title":"Sound event detection and localization based on CNN and LSTM","author":"lu","year":"2019"},{"key":"ref37","article-title":"Group delay features for sound event detection and localization (Task 3) of the DCASE 2019 challenge","author":"nustede","year":"2019"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.33682\/c6q0-wv87"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.33682\/v1za-0k45"},{"key":"ref34","article-title":"Arborescent neural network architectures for sound event detection and localization","author":"krause","year":"2019"},{"key":"ref28","article-title":"Spectrum combination and convolutional recurrent neural networks for joint localization and detection of sound events","author":"leung","year":"2019"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.33682\/nzsm-jr50"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.33682\/4v2a-7q02"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2326181"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2907016"},{"key":"ref20","article-title":"Multi-beam and multi-task learning for joint sound event detection and localization","author":"xue","year":"2019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.33682\/gbfk-re38"},{"key":"ref21","article-title":"Data augmentation and prior knowledge-based regularization for sound event localization and detection","author":"zhang","year":"2019"},{"key":"ref24","article-title":"Sound event localization and detection using FOA domain spatial augmentation","author":"mazzon","year":"2019"},{"key":"ref23","article-title":"DCASE 2019 Task 3: A two-step system for sound event localization and detection","author":"nguyen","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.33682\/93dp-f064"},{"key":"ref25","article-title":"Three-stage approach for sound event localization and detection","author":"noh","year":"2019"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.33682\/xb0q-a335"},{"key":"ref55","article-title":"A dataset of reverberant spatial sound scenes with moving sources for sound event localization and detection","author":"politis","year":"2020"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.2307\/1412159"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.33682\/3qgs-e216"},{"key":"ref52","article-title":"Mixup: Beyond empirical risk minimization","author":"zhang","year":"0","journal-title":"Proc Intl Conf on Learning Representations"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IECON.2017.8217063"},{"key":"ref11","article-title":"Classification of spatial audio location and content using convolutional neural networks","author":"hirvonen","year":"0","journal-title":"Proc Audio Eng Soc Conv"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2958408"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2018.2885636"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2778423"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553182"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2900164"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2901664"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.33682\/1xwd-5v76"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.33682\/9f2t-ab23"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.33682\/4jhy-bj81"},{"key":"ref4","first-page":"4930","article-title":"Signal-aware broadband DOA estimation using attention mechanisms","author":"mack","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2828321"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2193391"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2007.4425280"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853670"},{"key":"ref7","first-page":"1317","article-title":"Two-source acoustic event detection and localization: Online implementation in a smart-room","author":"butko","year":"0","journal-title":"Proc 19th Eur Signal Process Conf"},{"key":"ref49","first-page":"655","article-title":"Jackknife","volume":"1","author":"abdi","year":"0","journal-title":"Encyclopedia Res Des"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-015-3105-4"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3390\/app6060162"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1155\/2008\/246309"},{"key":"ref47","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":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/IoTaIS47347.2019.8980421"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3404716.3404726"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937220"},{"key":"ref43","first-page":"71","article-title":"A sequence matching network for polyphonic sound event localization and detection","author":"nguyen","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09306885.pdf?arnumber=9306885","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T08:27:09Z","timestamp":1643185629000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9306885\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/taslp.2020.3047233","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}