{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T22:20:06Z","timestamp":1773526806344,"version":"3.50.1"},"reference-count":70,"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"}],"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.2017.2690570","type":"journal-article","created":{"date-parts":[[2017,5,23]],"date-time":"2017-05-23T21:03:22Z","timestamp":1495573402000},"page":"1216-1229","source":"Crossref","is-referenced-by-count":77,"title":["Feature Learning With Matrix Factorization Applied to Acoustic Scene Classification"],"prefix":"10.1109","volume":"25","author":[{"given":"Victor","family":"Bisot","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Romain","family":"Serizel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Slim","family":"Essid","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gael","family":"Richard","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref70","article-title":"Supervised nonnegative matrix\n factorization for acoustic scene classification","author":"bisot","year":"2016"},{"key":"ref39","article-title":"DCASE 2016 acoustic scene classification using convolutional\n neural networks","author":"valenti","year":"2016"},{"key":"ref38","article-title":"CP-JKU submissions for DCASE-2016: A\n hybrid approach using binaural i-vectors and deep convolutional neural networks","author":"eghbal-zadeh","year":"2016"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2015.7362358"},{"key":"ref32","article-title":"The wonders of the normalized compression dissimilarity\n representation","author":"olivetti","year":"2013","journal-title":"IEEE AASP Challenge Detection and Classification of Acoustic Scenes and Events"},{"key":"ref31","article-title":"Auditory scene\n classification using machine learning techniques","author":"li","year":"2013","journal-title":"IEEE AASP Challenge Detection and Classification of Acoustic Scenes and Events"},{"key":"ref30","article-title":"A tone-fit feature representation for scene classification","author":"krijnders","year":"2013","journal-title":"IEEE AASP Challenge Detection and Classification of Acoustic Scenes and Events"},{"key":"ref37","article-title":"Acoustic scene and event recognition using recurrent neural networks","author":"vu","year":"2016"},{"key":"ref36","article-title":"Acoustic\n scene classification using parallel combination of LSTM and CNN","author":"bae","year":"2016"},{"key":"ref35","article-title":"Acoustic scene classification using deep\n neural network and frame-concatenated acoustic feature","author":"takahashi","year":"2016"},{"key":"ref34","article-title":"The up system for the 2016 DCASE challenge using deep recurrent neural network and multiscale kernel\n subspace learning","author":"marchi","year":"2016"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2005.00503.x"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/BF01589116"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2007.19.10.2756"},{"key":"ref63","first-page":"441","article-title":"Yaafe, an easy to use and efficient audio feature extraction\n software","author":"mathieu","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855206"},{"key":"ref64","first-page":"2825","article-title":"Scikit-learn: Machine learning in python","volume":"12","author":"pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2017438"},{"key":"ref65","first-page":"19","article-title":"Online learning for matrix factorization\n and sparse coding","volume":"11","author":"mairal","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref66","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"0","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2015.7336886"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459469"},{"key":"ref68","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref69","article-title":"Improving neural networks by preventing co-adaptation of\n feature detectors","author":"hinton","year":"2012"},{"key":"ref2","author":"wang","year":"2006","journal-title":"Computational Auditory Scene Analysis Principles Algorithms and Applications"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2326181"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2006.1692967"},{"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","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472918"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/HSCMA.2014.6843241"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.156"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2199972"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.854103"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1162\/089976698300017467"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-36668-3_44"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2012.02.010"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7177950"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2006.873291"},{"key":"ref56","first-page":"27","article-title":"Fisher non-negative matrix factorization\n for learning local features","author":"wang","year":"0","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref55","first-page":"1033","article-title":"Supervised dictionary learning","author":"mairal","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7177933"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471649"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2006.275588"},{"key":"ref10","article-title":"Recognition of everyday\n auditory scenes: Potentials, latencies and cues","author":"peltonen","year":"0","journal-title":"Proc 110th Audio Eng Soc Convention"},{"key":"ref40","article-title":"Non-negative matrix factorization applied to auditory scene\n classification","author":"cauchi","year":"2011"},{"key":"ref11","first-page":"1272","article-title":"Audio context recognition using audio\n event histograms","author":"heittola","year":"0","journal-title":"Proc Eur Signal Process Conf"},{"key":"ref12","first-page":"142","article-title":"Histogram of gradients of time-frequency representations for audio scene classification","volume":"23","author":"rakotomamonjy","year":"2015","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2015.7362477"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2013.6701857"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2013.6701890"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553463"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1137\/S003614450037906X","article-title":"Atomic\n decomposition by basis pursuit","volume":"43","author":"chen","year":"2001","journal-title":"SIAM Rev"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7177954"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-93"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2006.262661"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7532497"},{"key":"ref6","first-page":"1","article-title":"A database and challenge for acoustic scene classification and event detection","author":"giannoulis","year":"0","journal-title":"Proc 21st Eur Signal Process Conf"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1026653.1026659"},{"key":"ref8","first-page":"ii-1941","article-title":"Computational auditory scene recognition","volume":"2","author":"peltonen","year":"0","journal-title":"Proc Int Conf Acoust Speech Signal Process"},{"key":"ref49","article-title":"Sparse nmf-half-baked or well done?","author":"roux","year":"2015"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2016.7760424"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1121\/1.2750160"},{"key":"ref46","first-page":"257","article-title":"The why and how of nonnegative matrix factorization","volume":"12","author":"gillis","year":"2014","journal-title":"Regularization Optimization Kernels and Support Vector Machines"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00168"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2004.1381036"},{"key":"ref47","author":"cichocki","year":"2009","journal-title":"Nonnegative Matrix and Tensor Factorizations Applications to Exploratory Multi-Way Data Analysis and Blind Source Separation"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806389"},{"key":"ref41","article-title":"Characterisation of acoustic scenes using a temporally constrained shift-invariant model","author":"benetos","year":"0","journal-title":"Proc Digit Audio Effects"},{"key":"ref44","volume":"1","author":"friedman","year":"2001","journal-title":"The Elements of Statistical Learning"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2007613"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/7933016\/07933045.pdf?arnumber=7933045","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":"https:\/\/ieeexplore.ieee.org\/document\/7933045\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,6]]},"references-count":70,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2017.2690570","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,6]]}}}