摘要
Foraccuracyandrapidityofaudioeventdetectioninthemass-dataaudioprocessingtasks,agenericmethodofrapidlyrecognizingaudioeventbasedon2D-HaaracousticsuperfeaturevectorandAdaBoostisproposed.Firstly,itcombinescertainnumberofcontinuousaudioframestobean'acousticfeatureimage',secondly,usesAdaBoost.MHorfastRandomAdaBoostfeatureselectionalgorithmtoselecthighrepresentative2D-Haarpatterncombinationstoconstructsuperfeaturevectors;thirdly,analyzesthecommonalityanddifferencesbetweensubcategories,thenextractscommonfeaturesandreducesdifferentfeaturestoobtainagenericaudioeventtemplate,whichcansupporttheaccurateidentificationofmultiplesub-classesanddetectandlocatethespecificaudioeventfromtheaudiostreamaccurately.Experimentalresultsshowthattheuseof2D-Haaracousticfeaturesupervectorcanmakerecognitionaccuracy5%higherthanonesthatMFCC,PLP,LPCCandothertraditionalacousticfeaturesyielded,andcanmakethetrainingprocessing7-20timesfasterandtherecognitionprocessing5-10timesfaster,itcanevenachieveanaverageprecisionof93.38%,anaveragerecallof95.03%undertheoptimalparameterconfigurationfoundbygridmethod.Aboveall,itcanprovideanaccurateandfastmass-dataprocessingmethodforaudioeventdetection.
出版日期
2015年02月12日（中国Betway体育网页登陆平台首次上网日期，不代表论文的发表时间）
