{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,12]],"date-time":"2025-07-12T22:49:56Z","timestamp":1752360596894,"version":"3.37.3"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Two!Ears"},{"DOI":"10.13039\/100011102","name":"Seventh Framework Programme","doi-asserted-by":"publisher","award":["618075"],"award-info":[{"award-number":["618075"]}],"id":[{"id":"10.13039\/100011102","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":[[2020]]},"DOI":"10.1109\/taslp.2019.2958408","type":"journal-article","created":{"date-parts":[[2019,12,31]],"date-time":"2019-12-31T21:14:06Z","timestamp":1577826846000},"page":"487-502","source":"Crossref","is-referenced-by-count":17,"title":["Joining Sound Event Detection and Localization Through Spatial Segregation"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7596-6377","authenticated-orcid":false,"given":"Ivo","family":"Trowitzsch","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6128-3556","authenticated-orcid":false,"given":"Christopher","family":"Schymura","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0678-3053","authenticated-orcid":false,"given":"Dorothea","family":"Kolossa","sequence":"additional","affiliation":[]},{"given":"Klaus","family":"Obermayer","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1121\/1.3642604"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(00)00034-0"},{"article-title":"Auditory machine learning training and testing pipeline: AMLTTP v3.0","year":"2019","author":"trowitzsch","key":"ref33"},{"key":"ref32","article-title":"A free database of head related impulse response measurements in the horizontal plane with multiple distances","author":"wierstorf","year":"0","journal-title":"Proc Audio Eng Soc Conv"},{"article-title":"Two!ears auditory model 1.5","year":"2018","author":"team","key":"ref31"},{"article-title":"The NIGENS general sound events database","year":"2019","author":"trowitzsch","key":"ref30"},{"key":"ref37","first-page":"547","article-title":"A functional model of neural activity patterns and auditory images","volume":"3","author":"patterson","year":"1996","journal-title":"Adv Speech Hearing Language Process"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/0378-5955(90)90170-T"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638890"},{"journal-title":"An Introduction to Generalized Linear Models","year":"2002","author":"dobson","key":"ref34"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2337846"},{"key":"ref27","article-title":"Two!ears&#x2014;integral interactive model of auditory perception and experience","author":"raake","year":"0","journal-title":"Proc DAGA"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2647702"},{"key":"ref2","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 IEEE 19th Eur Signal Process Conf"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-015-3105-4"},{"key":"ref20","first-page":"1","article-title":"Convolutional recurrent neural networks for rare sound event detection","author":"cakir","year":"0","journal-title":"Workshop on Detection and Classification of Acoustic Scenes and Events"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2740002"},{"key":"ref21","first-page":"51","article-title":"Audio event detection using multiple-input convolutional neural network","author":"jeong","year":"0","journal-title":"Workshop on Detection and Classification of Acoustic Scenes and Events"},{"journal-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events 2016 Workshop","year":"2016","author":"virtanen","key":"ref24"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-234"},{"journal-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events 2018 Workshop","year":"2018","author":"plumbley","key":"ref26"},{"journal-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events 2017 Workshop","year":"2017","author":"virtanen","key":"ref25"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1996.tb02080.x"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v033.i01"},{"article-title":"Supplementary materials to TASLP: SELD through spatial segregation","year":"2019","author":"trowitzsch","key":"ref59"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780198522577.003.0002"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1038\/nrn3565"},{"article-title":"Binaural room impulse responses recorded with KEMAR in a mid-size lecture hall","year":"2016","author":"wierstorf","key":"ref56"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2750760"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1002\/1097-0142(1950)3:1<32::AID-CNCR2820030106>3.0.CO;2-3"},{"key":"ref53","first-page":"37","article-title":"Evaluation: From precision, recall and F-measure to ROC, informedness, markedness & correlation","volume":"2","author":"powers","year":"2011","journal-title":"J Mach Learn Technol"},{"article-title":"Glmnet for matlab","year":"2013","author":"qian","key":"ref52"},{"key":"ref10","first-page":"5874","article-title":"Filterbank-based blind signal separation with estimated sound direction","volume":"6","author":"park","year":"0","journal-title":"Proc IEEE Int Symp Circuits Syst"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2011.6082274"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.800560"},{"key":"ref12","first-page":"480","article-title":"From binaural to multimicrophone blind source separation using fixed beamforming with hrtfs","author":"maazaoui","year":"0","journal-title":"Proc 19th Int Conf Syst Signals Image Process"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ISPACS.2015.7432750"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2017.8335176"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30110-3_105"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCIC.2014.7238420"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2690573"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2016.7727635"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-123"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853670"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2855960"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2193391"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IECON.2017.8217063"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1269"},{"key":"ref7","first-page":"138","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":"ref49","doi-asserted-by":"publisher","DOI":"10.1002\/0471722162"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2018.2885636"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947602"},{"key":"ref45","first-page":"65","article-title":"Pairwise decomposition with deep neural networks and multiscale kernel subspace learning for acoustic scene classification","author":"marchi","year":"0","journal-title":"Workshop on Detection and Classification of Acoustic Scenes and Events"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1990.tb01775.x"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1121\/1.4901711"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1325955"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-39900-1_2"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2013.6701857"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1002\/9781118393550"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8938144\/08928942.pdf?arnumber=8928942","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:31:20Z","timestamp":1651080680000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8928942\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/taslp.2019.2958408","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2020]]}}}