{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,20]],"date-time":"2026-09-20T08:33:09Z","timestamp":1789893189284,"version":"4.0.1"},"reference-count":54,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"ANR Deep in France Project"},{"name":"Regional Project GRR"},{"DOI":"10.13039\/501100002924","name":"FEDER","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002924","id-type":"DOI","asserted-by":"publisher"}]},{"name":"DAISI"}],"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.2017.2690561","type":"journal-article","created":{"date-parts":[[2017,5,23]],"date-time":"2017-05-23T21:03:22Z","timestamp":1495573402000},"page":"1253-1265","source":"Crossref","is-referenced-by-count":31,"title":["Supervised Representation Learning for Audio Scene Classification"],"prefix":"10.1109","volume":"25","author":[{"given":"Alain","family":"Rakotomamonjy","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/2020408.2020577"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1587\/transfun.E92.A.708"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1109\/LSP.2009.2027163","article-title":"Semi-supervised nonnegative matrix factorization","volume":"17","author":"lee","year":"2010","journal-title":"IEEE Signal Process Lett"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7177950"},{"key":"ref31","first-page":"244","article-title":"Noise robust speaker recognition with convolutive sparse coding","author":"hurmalainen","year":"2015","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref30","first-page":"865","article-title":"Discriminative NMF and its application to single-channel source separation","author":"weninger","year":"2014","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2007.19.10.2756"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2016.7738818"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18178\/ijmlc.2016.6.2.583"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/2339530.2339582"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.885253"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2003.1285860"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74494-8_52"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2375575"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2013.6701819"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"788","DOI":"10.1038\/44565","article-title":"Learning the parts of objects by non-negative matrix factorization","volume":"401","author":"lee","year":"1999","journal-title":"Nature"},{"key":"ref21","first-page":"11","article-title":"Analysis of CNN-based speech recognition system using raw speech as input","author":"palaz","year":"2015","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref24","first-page":"1457","article-title":"Non-negative matrix factorization with sparseness constraints","volume":"5","author":"hoyer","year":"2004","journal-title":"J Mach Learn Res"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/312624.312649"},{"key":"ref26","first-page":"556","article-title":"Algorithms for non-negative matrix factorization","author":"lee","year":"2001","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00168"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2010.2091281"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126344"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472720"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2014.2324759"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2615921"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2013.6701890"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2015.7362477"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s10898-013-0035-4"},{"key":"ref12","first-page":"3325","article-title":"Robust sound event classification using LBP-HOG based bag-of-audio-words feature representation","author":"lim","year":"2015","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2226160"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4959924"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2011.6082331"},{"key":"ref16","first-page":"317","article-title":"Characterisation of acoustic scenes using a temporally-constrained shift-invariant model","author":"benetos","year":"2012","journal-title":"Proc Int Conf Digital Audio Effects"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472918"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2013.6701893"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref4","first-page":"248","article-title":"ImageNet: A large-scale hierarchical image database","author":"deng","year":"2009","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2016.7760424"},{"key":"ref6","article-title":"Non-negative matrix factorization applied to auditory scenes classification","author":"cauchi","year":"2011"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1149290.1149292"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2017438"},{"key":"ref7","first-page":"2502","article-title":"Combining frame and segment based models for environmental sound classification","author":"hu","year":"2012","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref49","article-title":"Deep learning using linear support vector machines","author":"tang","year":"2013"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.5430\/air.v2n1p107"},{"key":"ref46","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref45","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7177954"},{"key":"ref47","article-title":"Torch7: A MATLAB-like environment for machine learning","author":"collobert","year":"2011","journal-title":"NIPS Workshop BigLearn"},{"key":"ref42","article-title":"LIBSVM: A library for support vector machines","author":"chang","year":"2001"},{"key":"ref41","first-page":"19","article-title":"Online learning for matrix factorization and sparse coding","volume":"11","author":"mairal","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2011.229"},{"key":"ref43","first-page":"396","article-title":"Handwritten digit recognition with a back-propagation network","author":"lecun","year":"1990","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\/7933016\/07933051.pdf?arnumber=7933051","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:15:00Z","timestamp":1642004100000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7933051\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,6]]},"references-count":54,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2017.2690561","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,6]]}}}