{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T01:49:43Z","timestamp":1767836983600,"version":"3.49.0"},"reference-count":35,"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":"International Postgraduate Research Scholarship"},{"DOI":"10.13039\/501100001801","name":"University of Western Australia","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001801","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.2020.2998298","type":"journal-article","created":{"date-parts":[[2020,5,28]],"date-time":"2020-05-28T20:45:32Z","timestamp":1590698732000},"page":"1745-1754","source":"Crossref","is-referenced-by-count":8,"title":["Sound Event Detection Using Multiple Optimized Kernels"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5277-6634","authenticated-orcid":false,"given":"Xianjun","family":"Xia","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3778-4633","authenticated-orcid":false,"given":"Roberto","family":"Togneri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1557-4907","authenticated-orcid":false,"given":"Ferdous","family":"Sohel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6153-3543","authenticated-orcid":false,"given":"Yuanjun","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1431-8859","authenticated-orcid":false,"given":"Defeng","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref32","article-title":"Sound event detection using weakly labeled dataset with stacked convolutional and recurrent neural network","author":"adavanne","year":"0"},{"key":"ref31","first-page":"2067","article-title":"Gated feedback recurrent neural networks","author":"chung","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref30","first-page":"4278","article-title":"Inception-v4, inception-resnet and the impact of residual connections on learning","author":"szegedy","year":"0","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref35","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3390\/app6060162"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2013.6701862"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472917"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2013.02.015"},{"key":"ref13","article-title":"Sound event detection in multichannel audio using spatial and harmonic features","author":"adavanne","year":"0"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4959522"},{"key":"ref15","first-page":"1","article-title":"Automatic event classification using front end single channel noise reduction, MFCC features and a support vector machine classifier","author":"nogueira","year":"0","journal-title":"IEEE AASP Challenge Detection and Classification of Acoustic Scenes and Events"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019452"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019418"},{"key":"ref18","first-page":"55","article-title":"FrameCNN: A weakly-supervised learning framework for frame-wise acoustic event detection and classification","volume":"14","author":"chou","year":"2017","journal-title":"ReCALL"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461975"},{"key":"ref28","first-page":"58","article-title":"Manual on setting up, using, and understanding random forests v3. 1","volume":"1","author":"breiman","year":"2002"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"1291","DOI":"10.1109\/TASLP.2017.2690575","article-title":"Convolutional recurrent neural networks for polyphonic sound event detection","volume":"25","author":"parascandolo","year":"2017","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3390\/rs10030415"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2879750"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2428998"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2013.6654829"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2933330"},{"key":"ref8","article-title":"A report on sound event detection with different binaural features","author":"adavanne","year":"2017"},{"key":"ref7","first-page":"6","article-title":"Proceedings of the detection and classification of acoustic scenes and events 2016 workshop","volume":"6","author":"virtanen","year":"0","journal-title":"Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.03.025"},{"key":"ref9","article-title":"Large-scale weakly labeled semi-supervised sound event detection in domestic environments","author":"serizel","year":"2018"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2018.2885636"},{"key":"ref20","article-title":"Mean teacher convolution system for dcase 2018 task 4","author":"jiakai","year":"2018"},{"key":"ref22","article-title":"Multi-scale convolutional recurrent neural network with ensemble method for weakly labeled sound event detection","author":"guo","year":"2018"},{"key":"ref21","article-title":"Audio event detection using multiple-input convolutional neural network","author":"jeong","year":"2017"},{"key":"ref24","article-title":"Multi-scale embedded cnn for music tagging (MSE-CNN)","author":"hamidi","year":"2019"},{"key":"ref23","article-title":"Ensemble of convolutional neural networks for weakly-supervised sound event detection using multiple scale input","author":"lee","year":"2017"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1121\/1.5118245"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8938144\/09103031.pdf?arnumber=9103031","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:31:22Z","timestamp":1651080682000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9103031\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/taslp.2020.2998298","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}