Echo and Noise cancellation in MATLAB

Hi Experts!

I have a project about Echo cancelling Project and I have done some coding for designing the filters for echo cancellation. I couldn't get any help from internet.

The project says as :

The received_signal is professor's voice with noise and echo while Test Signals are just signals for sent and received.

And i have developed the following code.

Echo Canceling Project

1. Load the .mat file (serial number 33)

clear all; clc;
data=load("F33.mat");

2.Play the sound ,received_signal

%sound(data.Received_Signal,data.Fs)
% the sound was of professor with noise and echo

3. Using Test Signal , find Impulse Response.

y(n)= Received_Test_Signal
x(n)= Test_Signal
h(n)=x(n)∗y(n)
hn=conv(data.Received_Test_Signal,data.Test_Signal,"full");
plot(impz(hn));
title('Impulse Response of Test Signals');

Values of coefficients ai and 5001 x 1 of x(n) means it will have value of n1 to n5001.

[a]=(data.Test_Signal);

4.Recover the signal x(n)

% Using the Approach of LMS for finding the filter
d=100;
x = data.Test_Signal(d+1:end) ;% desired echo-free signal
y = data.Received_Signal(d+1:end) + 0.4*data.Received_Signal(1:end-d) ;% signal with echo
% Using LMS
M = 3*d;% FIR filter length
delta = 0.0001 ;% LMS  step size
hzf = zeros(M,1);% Initial filter IR values
ev = [];
for i=M+1:length(x)
xn = x(i);% desired sample value
yn = y(i-M+1:i);
xnhat = hzf'*yn ;% filter output value
en = xn - xnhat ;% current error
hzf = hzf + delta*yn*en; % update
% Plotting
ev = [ev abs(en)];
if rem(i,100)==0 ;% too slow to plot every iteration
    subplot(2,1,1);
    plot(hzf);
    title('Impulse response');
    subplot(2,1,2);
  plot(ev) ;
    title('|error|');
    pause(0.001);
 end
end

% filtering

xn_=conv(data.Received_Signal,hzf)
z=filter(hzf,1,data.Received_Signal)

5. The zplane , for order and stability

figure(2)
zplane(hzf)
n=filtord(hzf)
% stable 
isstable(hzf)

6. Structure for filter

% the filter is an IIR filter given by 
figure(2)
plot(hzf)

7. IIR to FIR filter

% We have to use Window method to limit the infinite Impulse Response of
% the inverse filter. i.e hamming window method
windw=[ones(1,100)]
FIR_approx=hzf.*windw
plot(FIR_approx)

8. Applying to y(n) to remove echo

ec_removed=filter(1,FIR_approx(:),data.Received_Signal)
sound(ec_removed)

9. Plot the Recovered signal against Frequency

plot(fft2(data.Received_Signal)) 
xlabel('-----Frequency(Hz)--->');

10. Using fdatool , Remove noise from x(n). Serial Number =33, Using Chebyshev 1 with order 34

%recov=filter(1,FilterDesign,data.Received_Signal)
%sound(recov)