{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T10:08:46Z","timestamp":1773655726103,"version":"3.50.1"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/N014111\/1"],"award-info":[{"award-number":["EP\/N014111\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Research Scholarship from the China Scholarship Council","award":["201406150082"],"award-info":[{"award-number":["201406150082"]}]},{"name":"Studentship","award":["1976218"],"award-info":[{"award-number":["1976218"]}]},{"name":"EPSRC Doctoral Training Partnership","award":["EP\/N509772\/1"],"award-info":[{"award-number":["EP\/N509772\/1"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2019,11]]},"DOI":"10.1109\/taslp.2019.2930913","type":"journal-article","created":{"date-parts":[[2019,7,26]],"date-time":"2019-07-26T20:04:21Z","timestamp":1564171461000},"page":"1791-1802","source":"Crossref","is-referenced-by-count":57,"title":["Weakly Labelled AudioSet Tagging With Attention Neural Networks"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2864-0475","authenticated-orcid":false,"given":"Qiuqiang","family":"Kong","sequence":"first","affiliation":[]},{"given":"Changsong","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Yong","family":"Xu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3393-2544","authenticated-orcid":false,"given":"Turab","family":"Iqbal","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8393-5703","authenticated-orcid":false,"given":"Wenwu","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9708-1075","authenticated-orcid":false,"given":"Mark D.","family":"Plumbley","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref38","article-title":"Temporal attention model for neural machine translation","author":"sankaran","year":"2016"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461975"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952585"},{"key":"ref31","first-page":"805","article-title":"Automatic tagging using deep convolutional neural networks","author":"choi","year":"0","journal-title":"Proc Int Conf Music Inf Retrieval"},{"key":"ref30","article-title":"Domestic audio tagging with convolutional neural networks","author":"cak?r","year":"0","journal-title":"Proc Workshop Detection Classif Acoust Scenes Events"},{"key":"ref37","article-title":"Bag-of-audio-words approach for multimedia event classification","author":"pancoast","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/463"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2013.06.003"},{"key":"ref34","article-title":"Identify, locate and separate: Audio-visual object extraction in large video collections using weak supervision","author":"parekh","year":"2018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1121\/1.2750160"},{"key":"ref27","article-title":"CP-JKU submissions for DCASE-2016: A hybrid approach using binaural I-vectors and deep convolutional neural networks","author":"eghbal-zadeh","year":"0"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2592698"},{"key":"ref2","first-page":"153","article-title":"A survey of music information retrieval systems","author":"typke","year":"0","journal-title":"Proc Int Conf Music Inf Retrieval"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2010.2098858"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2428998"},{"key":"ref22","first-page":"9","article-title":"A multi-device dataset for urban acoustic scene classification","author":"mesaros","year":"0","journal-title":"Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2016.7760424"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1111\/2041-210X.13103"},{"key":"ref23","first-page":"69","article-title":"General-purpose tagging of Freesound audio with audioset labels: Task description, dataset, and baseline","author":"fonseca","year":"0","journal-title":"Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE)"},{"key":"ref26","first-page":"3511","article-title":"Non-speech environmental sound classification using SVMS with a new set of features","volume":"8","author":"uzkent","year":"2012","journal-title":"Int J Innov Comput Inf Control"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8655(00)00119-7"},{"key":"ref50","article-title":"A comparison of multi-instance learning algorithms","author":"dong","year":"2006"},{"key":"ref51","first-page":"179","article-title":"Multi-instance kernels","volume":"2","author":"g\u00e4rtner","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref59","first-page":"467","article-title":"Relay backpropagation for effective learning of deep convolutional neural networks","author":"shen","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref58","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref57","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"hinton","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.3390\/app6060162"},{"key":"ref55","article-title":"Network in network","author":"lin","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref54","first-page":"807","article-title":"Rectified linear units improve restricted Boltzmann machines","author":"nair","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref53","article-title":"A structured self-attentive sentence embedding","author":"lin","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref52","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref11","first-page":"1038","article-title":"Audio event detection using weakly labelled data","author":"kumar","year":"0","journal-title":"Proc ACM Multimedia Conf"},{"key":"ref40","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952234"},{"key":"ref13","first-page":"50","article-title":"Deep neural network baseline for DCASE challenge 2016","author":"kong","year":"0","journal-title":"IEEE AASP Challenge Detect Classif Acoust Scenes Events"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461392"},{"key":"ref16","first-page":"188","article-title":"Multi-level attention model for weakly supervised audio classification","author":"yu","year":"0","journal-title":"Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE)"},{"key":"ref17","first-page":"570","article-title":"A framework for multiple-instance learning","author":"maron","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2015.7336899"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2428998"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2013.6701819"},{"key":"ref6","first-page":"85","article-title":"DCASE 2017 challenge setup: Tasks, datasets and baseline system","author":"mesaros","year":"0","journal-title":"Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2778423"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.09.003"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref49","first-page":"1119","article-title":"Solving multiple-instance problem: A lazy learning approach","author":"wang","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.08.026"},{"key":"ref45","first-page":"455","article-title":"Neural networks for multi-instance learning","author":"zhou","year":"0","journal-title":"Proc Int Conf Intell Inf Technol"},{"key":"ref48","first-page":"2127","article-title":"Attention-based deep multiple instance learning","author":"ilse","year":"0","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682847"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(96)00034-3"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2015.02.005"},{"key":"ref44","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":"ref43","first-page":"1073","article-title":"EM-DD: An improved multiple-instance learning technique","author":"zhang","year":"2002","journal-title":"Proc Adv Neural Inf Process Syst"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8784423\/08777125.pdf?arnumber=8777125","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T21:05:11Z","timestamp":1657746311000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8777125\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":59,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2019.2930913","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,11]]}}}