{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T13:16:05Z","timestamp":1775913365987,"version":"3.50.1"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,7]]},"DOI":"10.1109\/ijcnn48605.2020.9207532","type":"proceedings-article","created":{"date-parts":[[2020,9,30]],"date-time":"2020-09-30T00:40:33Z","timestamp":1601426433000},"page":"1-7","source":"Crossref","is-referenced-by-count":29,"title":["Sound Event Detection with Depthwise Separable and Dilated Convolutions"],"prefix":"10.1109","author":[{"given":"Konstantinos","family":"Drossos","sequence":"first","affiliation":[{"name":"Tampere University,Audio Research Group,Tampere,Finland"}]},{"given":"Stylianos I.","family":"Mimilakis","sequence":"additional","affiliation":[{"name":"Fraunhofer-IDMT,Semantic Music Technologies Group,Germany"}]},{"given":"Shayan","family":"Gharib","sequence":"additional","affiliation":[{"name":"Tampere University,Audio Research Group,Tampere,Finland"}]},{"given":"Yanxiong","family":"Li","sequence":"additional","affiliation":[{"name":"South China University of Technology,School of Electronic & Information Engineering,Guangzhou,China"}]},{"given":"Tuomas","family":"Virtanen","sequence":"additional","affiliation":[{"name":"Tampere University,Audio Research Group,Tampere,Finland"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"3rd International Conference for Learning Representations"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2018.8521367"},{"key":"ref31","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume":"37","author":"ioffe","year":"2015","journal-title":"Proceedings of the 32Nd International Conference on International Conference on Machine Learning"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref10","article-title":"Ensemble of convolutional neural networks for weakly-supervised sound event detection using multiple scale input","author":"lee","year":"2017","journal-title":"Dcase2016 challenge"},{"key":"ref11","article-title":"Listening for sirens: Locating and classifying acoustic alarms in city scenes","author":"marchegiani","year":"2018","journal-title":"ArXiv"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/941"},{"key":"ref13","first-page":"208","article-title":"Stacked convolutional and recurrent neural networks for music emotion recognition","author":"malik","year":"2017","journal-title":"14th Sound & Music Computing Conference (SMC-17)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2018.2885636"},{"key":"ref15","article-title":"Rigid-motion scattering for image classification","author":"sifre","year":"2014","journal-title":"Ph D Dissertation"},{"key":"ref16","article-title":"Network decoupling: From regular to depthwise separable convolutions","author":"guo","year":"2018","journal-title":"British Machine Vision Conference (BMVC)"},{"key":"ref17","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"ArXiv"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-75988-8_28"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.33682\/4v2a-7q02"},{"key":"ref27","article-title":"TUT-SED Synthetic 2016","year":"0"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.33682\/9f2t-ab23"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2017.8081505"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref5","first-page":"1744","article-title":"Convolutional recurrent neural networks for bird audio detection","author":"\u00e7akir","year":"2017","journal-title":"2017 25th European Signal Processing Conference (EUSIPCO 2017)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3390\/s17040854"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.33682\/006b-jx26"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.33682\/1dze-8739"},{"key":"ref9","article-title":"Surrey-CVSSP system for DCASE2017 challenge task4","author":"xu","year":"2017","journal-title":"Dcase2016 challenge"},{"key":"ref1","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":"\u00e7akir","year":"2017","journal-title":"IEEE\/ACM Transactions on Audio Speech and Language Processing"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/78.157290"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49409-8_7"},{"key":"ref21","article-title":"Multi-scale context aggregation by dilated convolutions","author":"yu","year":"2016","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054433"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1213\/4\/042050"},{"key":"ref26","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"ArXiv"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.33682\/w13e-5v06"}],"event":{"name":"2020 International Joint Conference on Neural Networks (IJCNN)","location":"Glasgow, UK","start":{"date-parts":[[2020,7,19]]},"end":{"date-parts":[[2020,7,24]]}},"container-title":["2020 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9200848\/9206590\/09207532.pdf?arnumber=9207532","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T21:53:18Z","timestamp":1656453198000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9207532\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/ijcnn48605.2020.9207532","relation":{},"subject":[],"published":{"date-parts":[[2020,7]]}}}