BLIND SIGNAL SEPARATION BASED ON ME AND STATISTICAL ESTIMATION

在线阅读 下载PDF 导出详情
摘要 TherearetwomajorapproachesforBlindSignalSeparation(BSS)problem:MaximumEntropy(ME)andMinimumMutualInformation(MMI)algorithms.BasedontherecursivearchitectureandtherelationshipbetweentheMEandMMIalgorithms,anExtendedME(EME)algorithmisproposedbyusingprobabilitydensityfunction(pdf)estimationoftheoutputstodeducethecorrespondingiterativeformulasinBSS.Basedonthesimulationresults,itcanbeconcludedthattheproposedalgorithmhasbetterperformancesthanthetraditionalMEalgorithminconvolutemixtureBSSproblems.
作者
机构地区 不详
出版日期 1999年02月12日(中国期刊网平台首次上网日期,不代表论文的发表时间)