欢迎来到天天文库
浏览记录
ID:52470618
大小:1.22 MB
页数:14页
时间:2020-03-27
《Autotagging music with conditional restricted Boltzmann machines有条件限制Boltzmann机器地自动调音音乐.pdf》由会员上传分享,免费在线阅读,更多相关内容在教育资源-天天文库。
1、AutotaggingmusicwithconditionalrestrictedBoltzmannmachinesMichaelMandel1RazvanPascanu1HugoLarochelle2YoshuaBengio1Dept.IRO,UniversitedeMontreal1Comp.Sc.Dept.UniversityofToronto2Abstractbutfailsforitemsthatareneworniche,thisistheso-calledcoldstartproblem[2].Thispaperdescribestwoapplicationso
2、fconditionalOnepromisingwaytoovercomethecoldstartisrestrictedBoltzmannmachines(CRBMs)tothetaskthroughcontent-basedanalysisandtaggingoftheofautotaggingmusic.Therstconsistsoftrainingaitemsinthecollection,knownasautotagging.Re-CRBMtopredicttagsthatauserwouldapplytoasearchershaveinvestigatedanumb
3、erofautotaggingclipofasongbasedontagsalreadyappliedbyothertechniquesformusicoverthelastdecade[3,4,5].users.Bylearningtherelationshipsbetweentags,thisWhileafewautotaggingtechniquesattempttocap-modelisabletopre-processtrainingdatatosigni-turetherelationshipbetweentags(e.g.[6]),manycantlyimprove
4、theperformanceofasupportvectortreateachtagasaseparateclassicationorrankingmachine(SVM)autotagging.Thesecondistheuseofproblem(e.g.[7]).TheproblemofpredictingtheadiscriminativeRBM,atypeofCRBM,toautotagpresenceorrelevanceofmultipletagssimultaneouslymusic.Bysimultaneouslyexploitingtherelationship
5、sisknownasthemulti-labelclassicationproblem[8].amongtagsandbetweentagsandaudio-basedfea-Thispaperexplorestechniquesforautotaggingmu-tures,thismodelisabletosignicantlyoutperformsicthatincorporatetherelationshipsbetweentags.SVMs,logisticregression,andmulti-layerperceptrons.Weapproachthisproble
6、mintwoways,bothofwhichInordertobeappliedtothisproblem,thediscrimina-arebasedonconditionalrestrictedBoltzmannma-tiveRBMwasgeneralizedtothemulti-labelsettingchines(RBMs)describedinSection2.Therstap-andfourdierentlearningalgorithmsforitwereeval-proach,describedinSection2.1,isanovelmodeluated,th
7、erstsuchin-depthanalysisofwhichwearetrainedtopredictthetagsthatauserwillapplytoaware.musicbasedonthetagsotherusershaveappliedtoit.Itisapurelytextualmodelinthatitdoesnotutilizetheaudioatalltomakepredictions.Thesepredicted1Introductionta
此文档下载收益归作者所有