independent component analysis using kurtosis:after this how to seperate the original signal from noisy signal...using independent component analysis using kurtosis...

clc;
clear all;
close all;
Fs = 10000;
fprintf('say a sentence immediately after hitting enter: ');
input('');
x= wavrecord(1 * 10000, 10000, 'double'); % Record and store the uttered speech
t=(0:(1*10000)-1)*1/(1*10000); 
subplot(3,1,1);
plot(x);
b=awgn(x,10,'measured');
subplot(3,1,2);
plot(b);