{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:13:26Z","timestamp":1776885206668,"version":"3.51.2"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"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\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2019,6]]},"DOI":"10.1109\/taslp.2019.2907016","type":"journal-article","created":{"date-parts":[[2019,3,25]],"date-time":"2019-03-25T22:44:31Z","timestamp":1553553871000},"page":"992-1006","source":"Crossref","is-referenced-by-count":96,"title":["Sound Event Detection in the DCASE 2017 Challenge"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6640-9752","authenticated-orcid":false,"given":"Annamaria","family":"Mesaros","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aleksandr","family":"Diment","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6461-5790","authenticated-orcid":false,"given":"Benjamin","family":"Elizalde","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8855-0415","authenticated-orcid":false,"given":"Toni","family":"Heittola","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0183-7289","authenticated-orcid":false,"given":"Emmanuel","family":"Vincent","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bhiksha","family":"Raj","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tuomas","family":"Virtanen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Ensemble of convolutional neural networks for weakly-supervised sound event detection using multiple scale input","author":"lee","year":"2017"},{"key":"ref38","article-title":"Sound event detection using weakly labeled dataset with stacked convolutional and recurrent neural network","author":"adavanne","year":"2017"},{"key":"ref33","article-title":"DCASE2017 sound event detection using convolutional neural network","author":"chen","year":"2017"},{"key":"ref32","article-title":"A report on sound event detection with different binaural features","author":"adavanne","year":"0"},{"key":"ref31","article-title":"Transfer learning based DNN-HMM hybrid system for rare sound event detection","author":"wang","year":"2017"},{"key":"ref30","article-title":"Multi-frame concatenation for detection of rare sound events based on deep neural network","author":"wang","year":"2017"},{"key":"ref37","first-page":"64","article-title":"Neuroevolution for sound event detection in real life audio: A pilot study","author":"kroos","year":"2017","journal-title":"Tech Rep DCASE2016 Challenge"},{"key":"ref36","article-title":"Bidirectional GRU for sound event detection","author":"lu","year":"0"},{"key":"ref35","first-page":"51","article-title":"Audio event detection using multiple-input convolutional neural network","author":"jeong","year":"2017","journal-title":"Proc Workshop Detection Classif Acoust Scenes Events"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952260"},{"key":"ref28","article-title":"A hierarchic multi-scaled approach for rare sound event detection","author":"vesperini","year":"2017"},{"key":"ref27","first-page":"27","article-title":"Convolutional recurrent neural networks for rare sound event detection","author":"cakir","year":"2017","journal-title":"Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE)"},{"key":"ref29","article-title":"DNN and CNN with weighted and multi-task loss functions for audio event detection","author":"phan","year":"2017"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471668"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2015.2470216"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2016.7760424"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1882471.1882479"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7287.001.0001"},{"key":"ref24","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref26","first-page":"80","article-title":"Rare sound event detection using 1D convolutional recurrent neural networks","author":"lim","year":"2017","journal-title":"Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE)"},{"key":"ref25","first-page":"1","article-title":"Jackknife","author":"abdi","year":"2010","journal-title":"Encyclopedia of Research Design"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2587218"},{"key":"ref51","first-page":"9","article-title":"A multi-device dataset for urban acoustic scene classification","author":"mesaros","year":"2018","journal-title":"Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE)"},{"key":"ref54","article-title":"DCASE 2018 Challenge - Task 5: Monitoring of domestic activities based on multi-channel acoustics","author":"dekkers","year":"2018","journal-title":"Tech Rep"},{"key":"ref53","article-title":"Automatic acoustic detection of birds through deep learning: The first bird audio detection challenge","author":"stowell","year":"2018","journal-title":"Method Ecol Evol"},{"key":"ref52","first-page":"69","article-title":"General-purpose tagging of freesound audio with audioset labels: Task description, dataset, and baseline","author":"fonseca","year":"2018","journal-title":"Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/1486.001.0001"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1207\/s15326969eco0504_2"},{"key":"ref40","article-title":"Surrey-CVSSP system for DCASE2017 challenge task4","author":"xu","year":"2017"},{"key":"ref12","first-page":"13","author":"heittola","year":"2018","journal-title":"The Machine Learning Approach for Analysis of Sound Scenes and Events"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2428998"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2778423"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-68585-2_1"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3390\/app6060162"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1186\/1687-4722-2013-1"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7177950"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2013.6701847"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3109\/17538157.2010.528655"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2015.7336885"},{"key":"ref6","first-page":"32","article-title":"The SINS database for detection of daily activities in a home environment using an acoustic sensor network","author":"dekkers","year":"2017","journal-title":"Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2016.04.007"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2751969"},{"key":"ref49","first-page":"123","article-title":"Data-efficient weakly supervised learning for low-resource audio event detection using deep learning","author":"morfi","year":"2018","journal-title":"Proc Workshop Detection Classif Acoust Scenes Events"},{"key":"ref9","first-page":"85","article-title":"DCASE2017 challenge setup: Tasks, datasets and baseline system","author":"mesaros","year":"2017","journal-title":"Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE)"},{"key":"ref46","first-page":"19","article-title":"Large-scale weakly labeled semi-supervised sound event detection in domestic environments","author":"serizel","year":"2018","journal-title":"Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE)"},{"key":"ref45","first-page":"188","article-title":"Multi-level attention model for weakly supervised audio classification","author":"yu","year":"0","journal-title":"Proc Detect Classif Acoust Sce Events 2018 Workshop"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2016.7552989"},{"key":"ref47","article-title":"The SEIE-SCUT systems for IEEE AASP challenge on DCASE 2017: Deep learning techniques for audio representation and classification","author":"li","year":"0","journal-title":"Proc Detect Classif Acoust Sce Events 2018 Workshop"},{"key":"ref42","article-title":"Combining multi-scale features using sample-level deep convolutional neural networks for weakly supervised sound event detection","author":"lee","year":"2017"},{"key":"ref41","article-title":"DCASE 2017 submission: Multiple instance learning for sound event detection","author":"salamon","year":"2017"},{"key":"ref44","first-page":"2518","article-title":"Weakly supervised representation learning for unsynchronized audio-visual events","author":"parekh","year":"2018","journal-title":"Proc IEEE Conf Comput Vision Pattern Recognit Workshops"},{"key":"ref43","article-title":"Deep learning for DCASE2017 challenge","author":"dang","year":"2017"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8685671\/08673582.pdf?arnumber=8673582","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T20:46:05Z","timestamp":1657745165000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8673582\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6]]},"references-count":54,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2019.2907016","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,6]]}}}