{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T06:21:28Z","timestamp":1772864488907,"version":"3.50.1"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2017,6,1]],"date-time":"2017-06-01T00:00:00Z","timestamp":1496275200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/3.0\/legalcode"}],"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"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2017,6]]},"DOI":"10.1109\/taslp.2017.2690563","type":"journal-article","created":{"date-parts":[[2017,5,23]],"date-time":"2017-05-23T21:03:22Z","timestamp":1495573402000},"page":"1230-1241","source":"Crossref","is-referenced-by-count":58,"title":["Unsupervised Feature Learning Based on Deep Models for Environmental Audio Tagging"],"prefix":"10.1109","volume":"25","author":[{"given":"Yong","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiang","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenwu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Foster","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siddharth","family":"Sigtia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philip J. B.","family":"Jackson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark D.","family":"Plumbley","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.940770"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref33","first-page":"339","article-title":"Learning features from music audio with deep belief networks","author":"hamel","year":"2010","journal-title":"Proc 11th Int Soc Music Inf Retrieval Conf"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.857575"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2005.1540194"},{"key":"ref30","article-title":"Improving neural networks by preventing co-adaptation of feature detectors","author":"hinton","year":"2012"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2337842"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.7717\/peerj.488"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639100"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2011.6082331"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1109\/TASLP.2014.2364452","article-title":"A regression approach to speech enhancement based on deep neural networks","volume":"23","author":"xu","year":"2015","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/BF01428124"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"452","DOI":"10.1109\/ICME.2000.869637","article-title":"Automatic audio segmentation using a measure of audio novelty","author":"foote","year":"2000","journal-title":"Proc IEEE Int Conf Multimedia Expo"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960723"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2015.7336899"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref21","first-page":"215","article-title":"An analysis of single-layer networks in unsupervised feature learning","author":"coates","year":"2011","journal-title":"Proc 14th Int Conf Artif Intell Statist"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639346"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854927"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref25","first-page":"2670","article-title":"Dynamic noise aware training for speech enhancement based on deep neural networks","author":"xu","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref10","first-page":"139","article-title":"Segmentation, clustering, and displaying in a personal audio database for musicians","author":"xia","year":"2011","journal-title":"Proc Int Soc Music Inf Retrieval"},{"key":"ref11","year":"0"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964310"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2015.7362358"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2015.7280624"},{"key":"ref15","first-page":"399","article-title":"Automatic identification of instrument classes in polyphonic and poly instrument audio","author":"hamel","year":"2009","journal-title":"Proc Int Soc Music Inf Retrieval"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854950"},{"key":"ref17","first-page":"805","article-title":"Automatic tagging using deep convolutional neural networks","author":"choi","year":"2016","journal-title":"Proc Int Soc Music Inf Retrieval"},{"key":"ref18","article-title":"CQT-based convolutional neural networks for audio scene classification and domestic audio tagging","author":"lidy","year":"2016","journal-title":"IEEE AASP Challenge Detect Classif Acoust Scenes Events"},{"key":"ref19","article-title":"Domestic audio tagging with convolutional neural networks","author":"cak?r","year":"2016","journal-title":"IEEE AASP Challenge Detect Classif Acoust Scenes Events"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178773"},{"key":"ref3","first-page":"45","article-title":"Automatic sound classification inspired by auditory scene analysis","author":"allegro","year":"2001","journal-title":"Proc Workshop on Consistent and Reliable Acoustic Cues for Sound Analysis"},{"key":"ref6","first-page":"1639","article-title":"A text retrieval approach to contnent-based audio retrieval","author":"riley","year":"2008","journal-title":"Proc Int Soc Music Inf Retrieval"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/FSKD.2010.5569371"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1101149.1101292"},{"key":"ref7","first-page":"2023","article-title":"Unsupervised classification of music genre using hidden markov model","author":"shao","year":"2004","journal-title":"Proc IEEE Int Conf Multimedia Expo"},{"key":"ref49","first-page":"557","article-title":"Support vector machines for multiple-instance learning","author":"andrew","year":"2003","journal-title":"Proc 15th Int Conf Neural Inf Proc"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366653"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-84996-202-5_5"},{"key":"ref45","article-title":"Discriminative training of GMM parameters for audio scene classification and audio tagging","author":"yun","year":"2016","journal-title":"IEEE AASP Challenge Detection and Classification of Acoustic Scenes and Events"},{"key":"ref48","article-title":"YouTube-8M: A large-scale video classification benchmark","author":"abu-el-haija","year":"2016"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/2812802"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2109382"},{"key":"ref41","first-page":"1918","article-title":"The CHiME corpus: A resource and a challenge for computational hearing in multisource environments","author":"christensen","year":"2010","journal-title":"Proc 11th Annu Conf Int Speech Commun Assoc"},{"key":"ref44","first-page":"594","article-title":"Song-level features and support vector machines for music classification","author":"mandel","year":"2005","journal-title":"Proc 6th Int Conf Music Inf Retrieval"},{"key":"ref43","author":"murohy","year":"2012","journal-title":"Machine Learning A Probabilistic Perspective"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/7933016\/07933054.pdf?arnumber=7933054","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:26:14Z","timestamp":1642004774000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/7933054\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,6]]},"references-count":49,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2017.2690563","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,6]]}}}