{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T01:10:45Z","timestamp":1780708245532,"version":"3.54.1"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8683158","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T16:01:56Z","timestamp":1555516916000},"page":"21-25","source":"Crossref","is-referenced-by-count":75,"title":["Learning Sound Event Classifiers from Web Audio with Noisy Labels"],"prefix":"10.1109","author":[{"given":"Eduardo","family":"Fonseca","sequence":"first","affiliation":[{"name":"Music Technology Group, Universitat Pompeu Fabra, Barcelona"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manoj","family":"Plakal","sequence":"additional","affiliation":[{"name":"Google, Inc, New York, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel P. W.","family":"Ellis","sequence":"additional","affiliation":[{"name":"Google, Inc, New York, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Frederic","family":"Font","sequence":"additional","affiliation":[{"name":"Music Technology Group, Universitat Pompeu Fabra, Barcelona"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xavier","family":"Favory","sequence":"additional","affiliation":[{"name":"Music Technology Group, Universitat Pompeu Fabra, Barcelona"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xavier","family":"Serra","sequence":"additional","affiliation":[{"name":"Music Technology Group, Universitat Pompeu Fabra, Barcelona"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"A closer look at weak label learning for audio events","author":"shah","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966293"},{"key":"ref12","article-title":"Training general-purpose audio tagging networks with noisy labels and iterative self-verification","author":"dorfer","year":"0","journal-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events 2018 Workshop (DCASE2018)"},{"key":"ref13","article-title":"DCASE 2018 task 2: iterative training, label smoothing, and background noise normalization for audio event tagging","author":"tho nguyen","year":"0","journal-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events 2018 Workshop (DCASE2018)"},{"key":"ref14","article-title":"Audio tagging system using densely connected convolutional networks","author":"jeong","year":"0","journal-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events 2018 Workshop (DCASE2018)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502245"},{"key":"ref16","first-page":"486","article-title":"Freesound datasets: a platform for the creation of open audio datasets","author":"fonseca","year":"2017","journal-title":"Proceedings of the 18th International Society for Music Information Retrieval Conference (ISMIR 2017)"},{"key":"ref17","article-title":"Training deep neural networks on noisy labels with bootstrapping","author":"reed","year":"2015","journal-title":"ICLRE"},{"key":"ref18","first-page":"5552","article-title":"Joint optimization framework for learning with noisy labels","author":"tanaka","year":"2018","journal-title":"proceedings of CVPR"},{"key":"ref19","article-title":"Generalized cross entropy loss for training deep neural networks with noisy labels","author":"zhang","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref28","first-page":"1919","article-title":"Robust loss functions under label noise for deep neural networks","author":"ghosh","year":"0"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref27","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"ICLRE"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2015.7336899"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2292894"},{"key":"ref5","article-title":"General-purpose tagging of freesound audio with audioset labels: task description, dataset, and baseline","author":"fonseca","year":"0","journal-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events 2018 Workshop (DCASE2018)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2017.8081532"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6287884"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0162075"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00906"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.696"},{"key":"ref21","article-title":"Data-efficient weakly supervised learning for low-resource audio event detection using deep learning","author":"morfi","year":"0","journal-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events 2018 Workshop (DCASE2018)"},{"key":"ref24","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":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2657381"},{"key":"ref26","article-title":"A simple fusion of deep and shallow learning for acoustic scene classification","author":"fonseca","year":"2018","journal-title":"Proceedings of the 15th Sound & Music Computing Conference (SMC 2018)"},{"key":"ref25","first-page":"630","article-title":"Identity mappings in deep residual networks","author":"he","year":"2016","journal-title":"European Conference on Computer Vision"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Brighton, UK","start":{"date-parts":[[2019,5,12]]},"end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08683158.pdf?arnumber=8683158","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T19:14:50Z","timestamp":1756754090000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683158\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683158","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}