{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,7,18]],"date-time":"2024-07-18T07:44:55Z","timestamp":1721288695310},"reference-count":138,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2013,9,1]],"date-time":"2013-09-01T00:00:00Z","timestamp":1377993600000},"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":["Proc. IEEE"],"published-print":{"date-parts":[[2013,9]]},"DOI":"10.1109\/jproc.2013.2251591","type":"journal-article","created":{"date-parts":[[2013,7,16]],"date-time":"2013-07-16T18:06:16Z","timestamp":1373997976000},"page":"1939-1954","source":"Crossref","is-referenced-by-count":37,"title":["An Overview on Perceptually Motivated Audio Indexing and Classification"],"prefix":"10.1109","volume":"101","author":[{"given":"Gael","family":"Richard","sequence":"first","affiliation":[]},{"given":"Shiva","family":"Sundaram","sequence":"additional","affiliation":[]},{"given":"Shrikanth","family":"Narayanan","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2004.840604"},{"key":"ref38","author":"fant","year":"1960","journal-title":"Acoustic Theory of Speech Production"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.2009.5293267"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.860842"},{"key":"ref31","author":"fuhrmann","year":"2012","journal-title":"Automatic musical instrument recognition from polyphonic music audio signals"},{"key":"ref30","author":"peeters","year":"2004","journal-title":"A Large Set of Audio Features for Sound Description (Similarity and Classification) in the Cuidado Project"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1997.596192"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8655(00)00119-7"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2006.871126"},{"key":"ref34","author":"hawkins","year":"2004","journal-title":"Intelligence"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"1611","DOI":"10.1109\/TNNLS.2012.2201748","article-title":"Multiclass feature selection with Kernel Gram-matrix-based criteria","volume":"23","author":"ramona","year":"2012","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1162\/153244303322753616"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2007613"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366654"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.40"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2014795"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1177\/0305735699271007"},{"key":"ref23","author":"levitin","year":"2008","journal-title":"The Science of a Human Obsession"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.70791"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50023-4"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1145\/1460096.1460115"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2011.2112333"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1037\/h0046162"},{"key":"ref51","article-title":"The perception of timbre","author":"schouten","year":"1968","journal-title":"Proc 6th Int Congr Acoust"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1525\/mp.2010.27.3.223"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1121\/1.1929229"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1121\/1.407371"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/BF00419633"},{"key":"ref55","year":"1960","journal-title":"USA Standard Acoustical Terminology"},{"key":"ref54","doi-asserted-by":"crossref","author":"bregman","year":"1990","journal-title":"Auditory Scene Analysis The Perceptual Organization of Sound","DOI":"10.7551\/mitpress\/1486.001.0001"},{"key":"ref53","author":"moore","year":"2003","journal-title":"An Introduction to the Psychology of Hearing"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1121\/1.1919362"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1155\/ASP\/2006\/90495"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1121\/1.1915893"},{"key":"ref3","volume":"1","author":"huang","year":"2001","journal-title":"Spoken Language Processing A Guide to Theory Algorithm and System Development"},{"key":"ref6","first-page":"3","author":"patterson","year":"1992","journal-title":"Complex sounds and auditory images"},{"key":"ref5","first-page":"191","article-title":"Comparative evaluation of various MFCC implementations on the speaker verification task","author":"ganchev","year":"2005","journal-title":"Proc Specom"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1155\/2007\/63685"},{"key":"ref49","first-page":"985","author":"licklider","year":"1951","journal-title":"Basic Correlates of the Auditory Stimulus"},{"key":"ref7","author":"slaney","year":"1993","journal-title":"An Efficient Implementation of the Patterson-Holdsworth Auditory Filter Bank"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1982.1171644"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2006.262661"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.854103"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2118753"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2017438"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2052803"},{"key":"ref41","first-page":"20","article-title":"Comparison of different strategies for a SVM-based audio segmentation","author":"ramona","year":"2009","journal-title":"Proc Eur Signal Process Conf"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2002.806626"},{"key":"ref43","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1109\/93.556537","article-title":"Content-based classification, search, and retrieval of audio","volume":"3","author":"wold","year":"1996","journal-title":"IEEE Trans Multimedia"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2009.5346542"},{"key":"ref126","first-page":"135","volume":"3","author":"schedl","year":"2012","journal-title":"Multimodal Music Processing"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1017\/ATSIP.2012.7"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2025099"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/89.917689"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1121\/1.3249188"},{"key":"ref129","first-page":"217","volume":"3","author":"goto","year":"2012","journal-title":"Multimodal Music Processing"},{"key":"ref71","author":"aucouturier","year":"2006","journal-title":"Dix exp'eriences sur la mod'elisation du timbre polyphonique [Ten experiments on the modelling of polyphonic timbre]"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2097250"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1080\/09298210802479268"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1986.1164910"},{"key":"ref130","first-page":"183","article-title":"Dancereproducer: An automatic mashup music video generation system by reusing dance video clips on the web","author":"nakano","year":"2011","journal-title":"Proc 4th Sound Music Comput Conf"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2011.2158801"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.804546"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/89.650305"},{"key":"ref133","article-title":"Constant-q transform toolbox for music processing","author":"schoerkhuber","year":"2010","journal-title":"Proc 4th Sound Music Comput Conf"},{"key":"ref134","article-title":"A Matlab toolbox for musical feature extraction from audio","author":"lartillot","year":"2007","journal-title":"Proc Int Conf Digital Audio Effects"},{"key":"ref131","first-page":"37","volume":"3","author":"essid","year":"2012","journal-title":"Multimodal Music Processing"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.910786"},{"key":"ref132","first-page":"113","article-title":"Psychoacoustical roughness: Implementation of an optimized model","volume":"83","author":"daniel","year":"1997","journal-title":"Acustica"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1200029"},{"key":"ref136","article-title":"jaudio: A feature extraction library","author":"mcennis","year":"2005","journal-title":"Proc Int Conf Music Inf Retrieval"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1017\/S1355771800003071"},{"key":"ref138","first-page":"441","article-title":"YAAFE, an easy to use and efficient audio feature extraction software","author":"mathieu","year":"2010","journal-title":"Proc Int Conf Music Inf Retrieval"},{"key":"ref137","article-title":"FEAPI, a low level features extraction plugin API","author":"lerch","year":"2005","journal-title":"Proc Int Conf Digital Audio Effects"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1121\/1.381428"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.800560"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1155\/2007\/64960"},{"key":"ref63","first-page":"81","article-title":"Automatic mood detection from acoustic music data","author":"liu","year":"2003","journal-title":"Proc 4th Int Conf Music Inf Retrieval"},{"key":"ref64","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1007\/0-387-32845-9_6","author":"herrera-boyer","year":"2006","journal-title":"Signal Processing Methods for Music Transcription"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ISSPA.2003.1224833"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.860351"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1186\/1687-4722-2010-546047"},{"key":"ref68","author":"martin","year":"1999","journal-title":"Sound-Source Recognition A Theory and Computational Model"},{"key":"ref2","volume":"3","author":"moore","year":"2007","journal-title":"An Introduction to the Psychology of Hearing"},{"key":"ref69","author":"richard","year":"2008","journal-title":"Audio indexing"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/5.842996"},{"key":"ref109","year":"2011","journal-title":"Emotional Interaction System"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4517544"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1111\/1469-8986.3720204"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2008.4607691"},{"key":"ref107","first-page":"547","article-title":"Multivariate autoregressive mixture models for music auto-tagging","author":"coviello","year":"2012","journal-title":"Proc Int Symp Music Inf Retrieval"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4517543"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4959975"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2005.1511825"},{"key":"ref105","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1007\/s10844-005-0321-9","article-title":"Drum loops retrieval from spoken queries","volume":"24","author":"gillet","year":"2005","journal-title":"J Intell Inf Syst"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1097-4571(199009)41:6<391::AID-ASI1>3.0.CO;2-9"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1145\/1743384"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366338"},{"key":"ref103","first-page":"61","article-title":"A statistical multidimensional humming transcription using phone level hidden Markov models for query by humming systems","volume":"1","author":"shih","year":"2003","journal-title":"Proc Int Conf Multimedia Expo"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2208663"},{"key":"ref111","first-page":"123","article-title":"Emotion perceived and emotion felt: Same or different?","volume":"10","author":"gabrielsson","year":"2002","journal-title":"Musicae Scientiae"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2118752"},{"key":"ref110","author":"picard","year":"1997","journal-title":"Affective Computing"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1145\/500141.500149"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1145\/1101149.1101292"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2034776"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00011"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"ref11","year":"2006","journal-title":"Computational Auditory Scene Analysis Principles Algorithms and Applications"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1199990"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2004.833861"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"668","DOI":"10.1155\/S1110865703305013","article-title":"Joint acoustic and modulation frequency","volume":"7","author":"atlas","year":"2003","journal-title":"EURASIP J Appl Signal Process"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/89.326616"},{"key":"ref118","first-page":"195","volume":"3","author":"weninger","year":"2012","journal-title":"Multimodal Music Processing"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00032-6"},{"key":"ref82","first-page":"36","article-title":"Sound event detection in multisource environments using source separation","author":"heittola","year":"2011","journal-title":"Proc 1st Int Workshop Mach Listening in Multisource Environ (CHiME)"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2010.5583001"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IIH-MSP.2009.256"},{"key":"ref81","doi-asserted-by":"crossref","first-page":"1937","DOI":"10.1016\/j.sigpro.2011.09.016","article-title":"Informed source separation through spectrogram coding and data embedding","volume":"92","author":"liutkus","year":"2012","journal-title":"Signal Process"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/18.119739"},{"key":"ref84","author":"salton","year":"1968","journal-title":"Automatic Information Organization and Retrieval"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.2307\/40285360"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858055"},{"key":"ref83","author":"rijsbergen","year":"1979","journal-title":"Information Retrieval"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5946961"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.01.010"},{"key":"ref116","article-title":"Affective classification of generic audio using regression models","author":"malandrakis","year":"2012","journal-title":"Proc Int Conf Acoust Speech Signal Process"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.914120"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6287886"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1121\/1.416900"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.1004822"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1661198"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1121\/1.2750160"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2009.09.008"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1145\/957039.957040"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-006-0032-2"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICICIC.2008.69"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-008-0201-8"}],"container-title":["Proceedings of the IEEE"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5\/6582526\/06560388.pdf?arnumber=6560388","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,29]],"date-time":"2021-11-29T20:23:18Z","timestamp":1638217398000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6560388\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,9]]},"references-count":138,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/jproc.2013.2251591","relation":{},"ISSN":["0018-9219","1558-2256"],"issn-type":[{"value":"0018-9219","type":"print"},{"value":"1558-2256","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,9]]}}}
