{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T11:12:52Z","timestamp":1783249972007,"version":"3.54.6"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2018,11,1]],"date-time":"2018-11-01T00:00:00Z","timestamp":1541030400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2018,11,1]],"date-time":"2018-11-01T00:00:00Z","timestamp":1541030400000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2018,11,1]],"date-time":"2018-11-01T00:00:00Z","timestamp":1541030400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2018,11,1]],"date-time":"2018-11-01T00:00:00Z","timestamp":1541030400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Moore-Sloan Data Science Environment at NYU"},{"name":"National Science Foundation","award":["1544753"],"award-info":[{"award-number":["1544753"]}]},{"name":"National Science Foundation","award":["1633259"],"award-info":[{"award-number":["1633259"]}]},{"name":"Google Faculty Award"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2018,11]]},"DOI":"10.1109\/taslp.2018.2858559","type":"journal-article","created":{"date-parts":[[2018,8,13]],"date-time":"2018-08-13T18:39:06Z","timestamp":1534185546000},"page":"2180-2193","source":"Crossref","is-referenced-by-count":114,"title":["Adaptive Pooling Operators for Weakly Labeled Sound Event Detection"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6261-9747","authenticated-orcid":false,"given":"Brian","family":"McFee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6345-4593","authenticated-orcid":false,"given":"Justin","family":"Salamon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juan Pablo","family":"Bello","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","article-title":"pescadores\/pescador:\n 1.1.0","author":"mcfee","year":"2017"},{"key":"ref72","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref71","first-page":"265","article-title":"Tensorflow: A system for large-scale machine\n learning","volume":"16","author":"abadi","year":"2016","journal-title":"Proc Symp Oper Syst Des Implementation"},{"key":"ref70","article-title":"Keras","author":"chollet","year":"2015"},{"key":"ref76","first-page":"65","article-title":"A simple sequentially rejective multiple test procedure","volume":"6","author":"holm","year":"1979","journal-title":"Scandinavian J Statist"},{"key":"ref74","first-page":"1","article-title":"Statistical comparisons of classifiers over multiple data sets","volume":"7","author":"dem\u0161ar","year":"2006","journal-title":"J Mach Learn Res"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2307436"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.2307\/2279372"},{"key":"ref38","first-page":"81","article-title":"Multiple instance\n learning with manifold bags.","author":"babenko","year":"2011","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952260"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2690575"},{"key":"ref31","article-title":"Bidirectional GRU for sound event detection","author":"lu","year":"2017"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472917"},{"key":"ref37","first-page":"1417","article-title":"Multiple\n instance boosting for object detection","author":"zhang","year":"2006","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(96)00034-3"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170052"},{"key":"ref60","article-title":"Feed-forward networks with attention can solve some long-term memory problems","author":"raffel","year":"2016","journal-title":"Proc Int Conf Learni Represent Workshop Track"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178783"},{"key":"ref61","article-title":"Differentiable pooling for hierarchical feature learning","author":"zeiler","year":"0"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.3390\/app6060162"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2016.7727634"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2015.7280624"},{"key":"ref65","first-page":"155","article-title":"Medleydb: A multitrack dataset for annotation-intensive mir research","volume":"14","author":"bittner","year":"2014","journal-title":"Proc Multiple-Instance Learn Music Inf Retrieval"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref29","first-page":"51","article-title":"Audio event detection using multiple-input\n convolutional neural network","author":"jeong","year":"2017","journal-title":"Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE)"},{"key":"ref67","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proceedings of the 32nd Intl Conf on Machine Learning"},{"key":"ref68","first-page":"248","article-title":"A software framework for musical data augmentation.","author":"mcfee","year":"2015","journal-title":"Proc Multiple-Instance Learn Music Inf Retrieval"},{"key":"ref69","article-title":"librosa 0.5.1","author":"mcfee","year":"2017"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2015.7336885"},{"key":"ref1","article-title":"SONYC: A system for the monitoring, analysis\n and mitigation of urban noise pollution","author":"bello","year":"0","journal-title":"Commun ACM"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2690576"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2011.6082331"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639360"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2013.6701847"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2013.6701861"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472079"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7177950"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952264"},{"key":"ref51","article-title":"Framecnn: A weakly-supervised learning framework for frame-wise acoustic event detection and\n classification","author":"chou","year":"2017"},{"key":"ref59","article-title":"Neural\n machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref58","article-title":"Orthogonality-regularized masked NMF for learning on weakly labeled audio data","author":"sobieraj","year":"2018","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref57","first-page":"641","article-title":"A joint separation-classification model\n for sound event detection of weakly labelled data","author":"kong","year":"2018","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref56","first-page":"12","article-title":"Sound event detection using weakly labeled dataset with stacked convolutional and recurrent\n neural network","author":"adavanne","year":"2017","journal-title":"Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE)"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952704"},{"key":"ref54","article-title":"Large-scale weakly supervised audio\n classification using gated convolutional neural network","author":"xu","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref53","article-title":"Knowledge transfer from weakly labeled audio using convolutional neural network for sound events and scenes","author":"kumar","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref52","article-title":"DCASE 2017 submission: Multiple instance\n learning for sound event detection","author":"salamon","year":"2017"},{"key":"ref10","first-page":"85","article-title":"Dcase 2017 challenge setup: Tasks, datasets\n and baseline system","author":"mesaros","year":"2017","journal-title":"Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-63450-0_11"},{"key":"ref40","first-page":"577","article-title":"Multiple-instance learning for music information retrieval","author":"mandel","year":"2008","journal-title":"Proc Multiple-Instance Learn Music Inf Retrieval"},{"key":"ref12","article-title":"Acoustic event detection and classification","author":"temko","year":"2007"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2015.06.026"},{"key":"ref14","first-page":"20","article-title":"Experiments on the DCASE Challenge 2016:\n Acoustic scene classification and sound event detection in real life recording","author":"elizalde","year":"2016","journal-title":"Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.857575"},{"key":"ref16","first-page":"1267","article-title":"Acoustic event detection in real life\n recordings","author":"mesaros","year":"2010","journal-title":"Proc Eur Signal Process Conf"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1186\/1687-4722-2013-1"},{"key":"ref18","first-page":"1","article-title":"An MFCC-GMM approach for event detection and classification","author":"vuegen","year":"2013","journal-title":"Proc IEEE Workshop Appl Signal Process Audio Acoust"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472919"},{"key":"ref4","article-title":"Birdvox-full-night: A dataset and benchmark for avian flight call\n detection","author":"lostanlen","year":"2018","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0166866"},{"key":"ref6","first-page":"158","author":"radhakrishnan","year":"0","journal-title":"Proc IEEE Workshop Appl Signal Process Audio Acoust"},{"key":"ref5","year":"2017"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.5626\/JCSE.2012.6.1.40"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2871183"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952234"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref46","first-page":"1609","article-title":"Multi-instance multi-label learning with application to scene classification","author":"zhou","year":"2007","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref45","first-page":"718","article-title":"A k-nearest neighbor based algorithm for multi-label classification","volume":"2","author":"zhang","year":"2005","journal-title":"Proc IEEE Int Conf Granular Comput"},{"key":"ref48","first-page":"1038","article-title":"Audio event detection using weakly labeled data","author":"kumar","year":"2016","journal-title":"Proc ACM Multimedia Conf"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966293"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.248"},{"key":"ref41","first-page":"577","article-title":"Support vector machines for multiple-instance learning","author":"andrews","year":"2003","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1121\/1.4707424"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654904"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielaam\/6570655\/8429900\/8434391-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8429900\/08434391.pdf?arnumber=8434391","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,8]],"date-time":"2022-04-08T18:54:23Z","timestamp":1649444063000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8434391\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11]]},"references-count":76,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2018.2858559","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,11]]}}}