{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T15:39:11Z","timestamp":1783611551106,"version":"3.55.0"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2015,3,1]],"date-time":"2015-03-01T00:00:00Z","timestamp":1425168000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100003816","name":"Huawei Technologies","doi-asserted-by":"publisher","award":["YB2012120147"],"award-info":[{"award-number":["YB2012120147"]}],"id":[{"id":"10.13039\/501100003816","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Fundamental Research Funds for the Central Universities China","award":["WK2100000002"],"award-info":[{"award-number":["WK2100000002"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2015,3]]},"DOI":"10.1109\/taslp.2015.2389618","type":"journal-article","created":{"date-parts":[[2015,1,7]],"date-time":"2015-01-07T19:56:44Z","timestamp":1420660604000},"page":"540-552","source":"Crossref","is-referenced-by-count":228,"title":["Robust Sound Event Classification Using Deep Neural Networks"],"prefix":"10.1109","volume":"23","author":[{"given":"Ian","family":"McLoughlin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haomin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhipeng","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2047680"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/1961189.1961199"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4613-2247-4"},{"key":"ref32","author":"moore","year":"1992","journal-title":"An Introduction to the Psychology of Hearing"},{"key":"ref31","first-page":"331","article-title":"A model of loudness applicable to time-varying sounds","volume":"50","author":"glasberg","year":"2002","journal-title":"J Audio Eng Soc"},{"key":"ref30","first-page":"1364","article-title":"Deep learning vector quantization for acoustic information retreival","author":"huang","year":"2014","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process (ICASSP?14)"},{"key":"ref37","author":"palm","year":"2012","journal-title":"Prediction as A Candidate for Learning Deep Hierarchical Models of Data"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"2255","DOI":"10.21437\/Eurospeech.1999-568x","article-title":"Data collection in real acoustical environments for sound scene understanding and hands-free speech recognition","author":"nakamura","year":"1999","journal-title":"Proc EUROSPEECH"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.70791"},{"key":"ref34","first-page":"2","article-title":"Processing images and sounds with matching pursuits","author":"bergeaud","year":"1995","journal-title":"Proc Int Symp Opt Sci Eng Instrum"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.857575"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1460096.1460115"},{"key":"ref40","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9781139003858","volume":"151","author":"schneider","year":"2013","journal-title":"Convex Bodies The Brunn?Minkowski Theory"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2010.2100380"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2013.02.015"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2226160"},{"key":"ref15","author":"dennis","year":"2014","journal-title":"Sound event recognition in unstructured environments using spectrogram image processing"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511609640"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4959998"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854293"},{"key":"ref19","article-title":"Acoustic event detection and localization with regression forests","author":"phan","year":"2014","journal-title":"Proc Annu Conf Int Speech Commun Assoc (Interspeech)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947698"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref3","year":"2010","journal-title":"Audio classification for information retrieval using sparse features"},{"key":"ref27","first-page":"173","article-title":"Paralinguistic event detection from speech using probabilistic time-series smoothing and masking","author":"gupta","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref6","author":"walters","year":"2011","journal-title":"Auditory-Based Processing of Communication Sounds"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2011.6082352"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2116010"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.851880"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2002.806626"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00011"},{"key":"ref9","first-page":"36","article-title":"Sound event detection in multisource environments using source separation","author":"heittola","year":"2011","journal-title":"Workshop Mach Listen Multisource Environ"},{"key":"ref1","first-page":"1414","article-title":"Machine hearing: An emerging field","volume":"42","author":"lyon","year":"2010","journal-title":"IEEE Signal Process Mag"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1661400"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1121\/1.414456"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-1-4614-3831-1_1","volume":"158","author":"sidiropoulos","year":"2013","journal-title":"Analysis, Retrieval and Delivery of Multimedia Content"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/76.927433"},{"key":"ref24","author":"walters","year":"2014","journal-title":"Aim-c A C++ Implementation of the Auditory Image Model"},{"key":"ref41","first-page":"212","volume":"202","author":"sorin","year":"2003","journal-title":"?Extended advanced front end algorithm description version 1 1 ?"},{"key":"ref23","first-page":"781","article-title":"Aim-mat: The auditory image model in Matlab","volume":"90","author":"bleeck","year":"2004","journal-title":"Acta Acust United with Acust"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2109382"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2017438"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/7050384\/07003973.pdf?arnumber=7003973","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,16]],"date-time":"2025-05-16T13:01:31Z","timestamp":1747400491000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7003973\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,3]]},"references-count":43,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2015.2389618","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,3]]}}}