{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T23:45:32Z","timestamp":1777938332764,"version":"3.51.4"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2019,3,1]],"date-time":"2019-03-01T00:00:00Z","timestamp":1551398400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,3,1]],"date-time":"2019-03-01T00:00:00Z","timestamp":1551398400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,3,1]],"date-time":"2019-03-01T00:00:00Z","timestamp":1551398400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100010663","name":"H2020 European Research Council","doi-asserted-by":"publisher","award":["637422"],"award-info":[{"award-number":["637422"]}],"id":[{"id":"10.13039\/100010663","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2019,3]]},"DOI":"10.1109\/jstsp.2018.2885636","type":"journal-article","created":{"date-parts":[[2018,12,7]],"date-time":"2018-12-07T20:41:13Z","timestamp":1544215273000},"page":"34-48","source":"Crossref","is-referenced-by-count":419,"title":["Sound Event Localization and Detection of Overlapping Sources Using Convolutional Recurrent Neural Networks"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5001-6911","authenticated-orcid":false,"given":"Sharath","family":"Adavanne","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0595-2356","authenticated-orcid":false,"given":"Archontis","family":"Politis","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6092-9346","authenticated-orcid":false,"given":"Joonas","family":"Nikunen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4604-9729","authenticated-orcid":false,"given":"Tuomas","family":"Virtanen","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952260"},{"key":"ref38","article-title":"A report on sound event detection with different binaural features","author":"adavanne","year":"0","journal-title":"Proc Workshop Detection Classif Acoust Scenes Events"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178031"},{"key":"ref32","first-page":"493","article-title":"Virtual adversarial training and data augmentation for acoustic event detection with gated recurrent neural networks","author":"z\u00f6hrer","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2740002"},{"key":"ref30","article-title":"Sound event detection in multichannel audio using spatial and harmonic features","author":"adavanne","year":"0","journal-title":"Proc Workshop Detection Classif Acoust Scenes Events"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2690575"},{"key":"ref36","article-title":"Rare sound event detection using 1D convolutional recurrent neural networks","author":"lim","year":"0","journal-title":"Proc Workshop Detection Classif Acoust Scenes Events"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2018.8489542"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-123"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2009.5346532"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404837"},{"key":"ref63","article-title":"Microphone array processing for parametric spatial audio techniques","author":"politis","year":"2016"},{"key":"ref28","first-page":"1","article-title":"Polyphonic sound event detection using multi-label deep neural networks","author":"\u00e7ak?r","year":"0","journal-title":"Proc IEEE Int Joint Conf Neural Netw"},{"key":"ref64","article-title":"DCASE 2017 challenge setup: tasks, datasets and baseline system","author":"mesaros","year":"0","journal-title":"Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE)"},{"key":"ref27","first-page":"1267","article-title":"Acoustic event detection in real-life recordings","author":"mesaros","year":"0","journal-title":"Proc of European Signal Process Conf"},{"key":"ref65","author":"ottersten","year":"1993","journal-title":"Radar Array Processing (Springer Series in Information Sciences)"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1121\/1.4726012"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472917"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.3390\/app6060162"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-63450-0_6"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846325"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471706"},{"key":"ref20","article-title":"Classification of spatial audio location and content using convolutional neural networks","author":"hirvonen","year":"0","journal-title":"Proc Audio Eng Soc Conv 138"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462024"},{"key":"ref21","first-page":"12384","article-title":"Distance estimation and localization of sound sources in reverberant conditions using deep neural networks","volume":"12","author":"yiwere","year":"2017","journal-title":"Int J Appl Eng Res"},{"key":"ref24","first-page":"6403","article-title":"Indoor sound source localization with probabilisitic neural network","volume":"29","author":"sun","year":"2017","journal-title":"IEEE Trans Ind Electron"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2016.7738817"},{"key":"ref26","article-title":"On sound source localization of speech signals using deep neural networks","author":"roden","year":"0","journal-title":"Proc Deutsche Jahrestagung für Akustik"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553182"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2006.08.004"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2014.6958891"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1121\/1.382599"},{"key":"ref58","article-title":"Sound event detection in synthetic audio","author":"benetos","year":"2016"},{"key":"ref57","article-title":"TensorFlow: Large-scale machine learning on heterogeneous systems","author":"abadi","year":"2015"},{"key":"ref56","article-title":"Keras v2.0.8","author":"chollet","year":"2015"},{"key":"ref55","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref54","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-015-3105-4"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853670"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1997.599595"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1002\/9780470714089"},{"key":"ref40","article-title":"Audio event detection using multiple-input convolutional neural network","author":"jeong","year":"0","journal-title":"Proc Workshop Detection Classif Acoust Scenes Events"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2014.2325781"},{"key":"ref13","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 Euro Signal Process Conf"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2017438"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1111\/brv.12001"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1002\/jwmg.821"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170010"},{"key":"ref18","article-title":"Multi-speaker localization using convolutional neural network trained with noise","author":"chakrabarty","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178484"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461267"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.20965\/jrm.2017.p0037"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IECON.2017.8217063"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2871183"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2015.2470216"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1121\/1.4988711"},{"key":"ref49","volume":"348","author":"teutsch","year":"2007","journal-title":"Modal Array Signal Processing Principles and Applications of Acoustic Wavefield Decomposition"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1415605"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TAP.1986.1143830"},{"key":"ref45","first-page":"80","article-title":"A high-accuracy, low-latency technique for talker localization in reverberant environments using microphone arrays","author":"brandstein","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref48","author":"dibiase","year":"2001","journal-title":"Microphone Arrays"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/29.32276"},{"key":"ref42","article-title":"Bidirectional GRU for sound event detection","author":"lu","year":"0","journal-title":"Proc Workshop Detection Classif Acoust Scenes Events"},{"key":"ref41","article-title":"Sound event detection in multichannel audio LSTM network","author":"zhou","year":"0","journal-title":"Proc Workshop Detection Classif Acoust Scenes Events"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/89.966097"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-68585-2_34"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4200690\/8688688\/08567942.pdf?arnumber=8567942","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T20:46:53Z","timestamp":1657745213000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8567942\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,3]]},"references-count":68,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2018.2885636","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,3]]}}}