{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,19]],"date-time":"2026-09-19T02:26:10Z","timestamp":1789784770415,"version":"4.0.1"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2018,4,1]],"date-time":"2018-04-01T00:00:00Z","timestamp":1522540800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2018,4,1]],"date-time":"2018-04-01T00:00:00Z","timestamp":1522540800000},"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":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8462448","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T18:24:48Z","timestamp":1537554288000},"page":"321-325","source":"Crossref","is-referenced-by-count":17,"title":["A Joint Separation-Classification Model for Sound Event Detection of Weakly Labelled Data"],"prefix":"10.1109","author":[{"given":"Qiuqiang","family":"Kong","sequence":"first","affiliation":[{"name":"Center for Vision, Speech and Signal Processing, University of Surrey, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Xu","sequence":"additional","affiliation":[{"name":"Center for Vision, Speech and Signal Processing, University of Surrey, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenwu","family":"Wang","sequence":"additional","affiliation":[{"name":"Center for Vision, Speech and Signal Processing, University of Surrey, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mark D.","family":"Plumbley","sequence":"additional","affiliation":[{"name":"Center for Vision, Speech and Signal Processing, University of Surrey, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"DCASE 2017 challenge setup: Tasks, datasets and baseline system","author":"mesaros","year":"2017","journal-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events (DCASE) Workshop"},{"key":"ref11","first-page":"641","article-title":"A joint detection-classification model for audio tagging of weakly labelled data","author":"kong","year":"2017","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref12","author":"xu","year":"2017","journal-title":"Attention and localization based on a deep convolutional recurrent model for weakly supervised audio tagging"},{"key":"ref13","author":"wang","year":"2006","journal-title":"Computational Auditory Scene Analysis Principles Algorithms and Applications"},{"key":"ref14","author":"simonyan","year":"2014","journal-title":"Very Deep Convolutional Networks for Large-scale Image Recognition"},{"key":"ref15","author":"choi","year":"2016","journal-title":"Automatic tagging using deep convolutional neural networks"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298668"},{"key":"ref18","author":"lin","year":"2013","journal-title":"Network in Network"},{"key":"ref19","first-page":"695","article-title":"Seed, expand and constrain: Three principles for weakly-supervised image segmentation","author":"kolesnikov","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2016.7760424"},{"key":"ref3","article-title":"Sound event detection in multisource environments using source separation","author":"heittola","year":"2011","journal-title":"CHiMEWorkshop on Machine Listening in Multisource Environments"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1186\/1687-4722-2013-1"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2428998"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2015.7336899"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964310"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853860"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2007.4425280"},{"key":"ref9","first-page":"776","article-title":"Audio Set: An ontology and human-labeled dataset for audio events","author":"gemmeke","year":"2017","journal-title":"IEEE ICASSP"},{"key":"ref20","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/0-387-22794-6_12"}],"event":{"name":"ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Calgary, AB, Canada","start":{"date-parts":[[2018,4,15]]},"end":{"date-parts":[[2018,4,20]]}},"container-title":["2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8450881\/8461260\/08462448.pdf?arnumber=8462448","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,4]],"date-time":"2025-08-04T18:37:41Z","timestamp":1754332661000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8462448\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8462448","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}