{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,30]],"date-time":"2025-11-30T08:47:13Z","timestamp":1764492433608},"reference-count":29,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2014,1,1]],"date-time":"2014-01-01T00:00:00Z","timestamp":1388534400000},"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":[[2014]]},"DOI":"10.1109\/taslp.2014.2375575","type":"journal-article","created":{"date-parts":[[2014,12,2]],"date-time":"2014-12-02T20:42:07Z","timestamp":1417552927000},"page":"1-1","source":"Crossref","is-referenced-by-count":52,"title":["Histogram of gradients of Time-Frequency Representations for Audio Scene Detection"],"prefix":"10.1109","author":[{"given":"Alain","family":"Rakotomamonjy","sequence":"first","affiliation":[]},{"given":"Gilles","family":"Gasso","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2013.6701819"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2011.6082331"},{"key":"ref12","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":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4959924"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2226160"},{"key":"ref15","first-page":"886","volume":"1","author":"dalal","year":"2005","journal-title":"Computer Vision and Pattern Recognition 2005 CVPR 2005 IEEE Computer Society Conf"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2005.01.024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2008.03.020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2010.04.026"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8655(03)00147-8"},{"key":"ref4","author":"cauchi","year":"2011","journal-title":"Non-negative matrix factorization applied to auditory scenes classification"},{"key":"ref28","article-title":"Constant-Q transform toolbox for music processing","author":"schoerkhuber","year":"2010","journal-title":"Proc 4th Sound Music Comput Conf"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1149290.1149292"},{"key":"ref27","article-title":"PLP and RASTA and MFCC and inversion in Matlab","author":"ellis","year":"2005"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2013.6701893"},{"key":"ref5","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":"ref29","author":"vedaldi","year":"2008","journal-title":"?VLFeat An open and portable library of computer vision algorithms ?"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2013.6701857"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2017438"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1121\/1.2750160"},{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1109\/9780470043387","author":"wang","year":"2006","journal-title":"Computational Auditory Scene Analysis Principles Algorithms and Applications"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2013.6701890"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1121\/1.400476"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2012.10.009"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539949"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"2237","DOI":"10.21437\/Eurospeech.2003-626","article-title":"Context awareness using environmental noise classification","author":"ma","year":"2003","journal-title":"Proc EUROSPEECH"},{"key":"ref25","article-title":"A theoretical analysis of feature pooling in vision algorithms","author":"boureau","year":"2010","journal-title":"Proc Int Conf Mach Learn"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/7010069\/06971128.pdf?arnumber=6971128","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,30]],"date-time":"2023-07-30T11:38:00Z","timestamp":1690717080000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6971128\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/taslp.2014.2375575","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014]]}}}