I need help Im trying to have a trouble issue here like I dont want to use numbers to detect that speaker. I want to use names. This is my code. In the training part

clear all;
close all;
clc;
warning off
Fs=8000;%Sampling frequency in hertz
ch=1;%Number of channels--2 options--1 (mono) or 2 (stereo)
datatype='uint8';
nbits=16;%8,16,or 24
Nseconds=5;
%% Create a recorder object
recorder=audiorecorder(Fs,nbits,ch);
datatype='uint8';
%% Record user's voice for 7 sec
disp('Get Ready')
pause(3)
disp('Please Record your voice');
drawnow();
pause(1);
recordblocking(recorder,Nseconds);
disp('Recorded');



%%Play users voice
play(recorder);
data= getaudiodata(recorder);
%Store recorded audio signal in numeric array
data=getaudiodata(recorder,datatype);
plot(data)
figure;


%%Training Function
f = voiceFeatures(data);


%%Save Users data
user=input('Enter the users number:');

try
    load database
    F=[F;f];
    C=[C;user];
    save database
catch 
    F=f;
    C=user;
    save database F C
    
    
end
msgbox('Your voice is registered')

[kim]

In this code I want to register names not numbers in the database so that when I test it it will detect who the voice is that. anyone can help me what should I write in the code. Thank you

Answer 1

[Walter Roberson]

user = cellstr(input('Enter the users name:', 's'));

[kim]

How can I limit my user name about 5 users to register? and when the user is full it cant accept any users or one will be deleted from the users to add one and so on. @Walter Roberson

[Walter Roberson]

try
    load database
    F=[F;f];
    C=[C;user];
    if numel(F) > 5
        F = F(end-4:end);
        C = C(end-4:end);
    end
    save database
catch 
    F=f;
    C=user;
    save database F C
end

[kim]

Also please help me in the testing part of when I record my voice it will recognized it and file my similar audio in the database and it will say access granted or access denied if it doesnt match. Please help me revise my code. @Walter Roberson here is the below is the code.

clear all
close all
clc

%% Creating a recorder object
recorder = audiorecorder(16000, 8, 1); % 16000 Hz, 8 bits, 1 channels

%% Record the user's voice for 5s
disp("Please say something.")
drawnow(); % update figures and process callbacks
pause(1) % pauses for 1s
recordblocking(recorder, 7); % records the audio to recorder object for 5s.
disp('Recorded')

%% Play the user's voice
play(recorder); % plays the audio from the recorder object
data = getaudiodata(recorder); % data is stored in a 8000 x 2 matrix.
% plot(data); % plots the data
% xlabel("Frequency") 
% ylabel("Normalized values between -1 to 1")
% title("Audio sample")

%% Feature Extraction
f_test = voiceFeatures(data)

%% Find the closest feature from database.
load database
D = [];
for i = 1:size(F, 1)
    distance = abs(F(i) - f_test); % calculates the distance between the stored value in the database and the test value.
    D = [D distance]; % adds the distance d to the vector D.
end

%% Smallest distance
smallest_distance = inf; % initially, we take the smallest distance to be infinity.
index = 0; % initially, we take the index to be 0
for i = 1:length(D)
    if D(i) < smallest_distance % if the current distance is smaller than the smallest distance.
        smallest_distance = D(i); % then replace the smallest distance with the current distance.
        index = i; % change the index to the current distance's index.
    end
end

detected_class = C(index);
disp('The detected class is ');
detected_class

[Walter Roberson]

Why are you not vectorizing the distance calculation? D = abs(F - f_test)

Why are you not using min() instead of that loop to calculate smallest distance?

Have you taken the MATLAB Onramp course yet? Learn

[kim]

I am a student, starters. we have no much time learning this because its our project for this semester. Our teacher didnt teach us very well thats why didnt learn enough

[kim]

what should I do or put it in the code, this one will be a great help. please... @Walter Roberson

[Walter Roberson]

[smallest_distance, index] = min(D);

[kim]

@Walter Roberson

clear all
close all
clc

%% Creating a recorder object
recorder = audiorecorder(16000, 8, 1); % 16000 Hz, 8 bits, 1 channels

%% Record the user's voice for 5s
disp("Please say something.")
drawnow(); % update figures and process callbacks
pause(1) % pauses for 1s
recordblocking(recorder, 2); % records the audio to recorder object for 2s.
disp('Recorded')

%% Play the user's voice
play(recorder); % plays the audio from the recorder object
data = getaudiodata(recorder); % data is stored in a 8000 x 2 matrix.
% plot(data); % plots the data
% xlabel("Frequency") 
% ylabel("Normalized values between -1 to 1")
% title("Audio sample")

%% Feature Extraction
f_test = voiceFeatures(data)

%% Find the closest feature from database.
load database
D=[];
for(i=1:size(F,1))%returns the length of 1st dimension of F
    distance = abs(F(i) - f_test) % calculates the distance between the stored value in the database and the test value.
   D = [D distance];% adds the distance d to the vector D.
end

%% Smallest distance
[smallest_distance, index] = min(D);
ind=0;
for i=1:1 length(D)
    if(D(i)<smallest_distance % if the current distance is smaller than the smallest distance.
        smallest_distance = D(i); % then replace the smallest distance with the current distance.
     index = i; % change the index to the current distance's index.
    end
end
%% Output
file_number=F(ind);
sc=strcat('The file number of ', data, ' in training is: ');
disp(sc)
file_number

detected_user = D(index);
disp('The detected user is ');
detected_user;

is this correct?

[Walter Roberson]

No, it is not correct.

for i=1:1 length(D)

means the same thing as

    for i=1:1
        length(D)

which computes the length of D and displays it.

But that loop is completely unneeded since you already calculated the minimum distance using min()

Also, you use

   file_number=F(ind);

but ind is always 0 in your code.

[kim]

in this code I want to use names not numbers in detecting I have training. and this testing part is a continuation. how can I detect the name of the users voice? @Walter Roberson

[Walter Roberson]

You cannot do that. There is no code in the world that can take recorded speech data and directly convert it into the name of the speaker, without going through a numeric step of analyzing coefficients and comparing against recorded coefficients to determine closest match.

As such, code is always going to arrive at an index of which match or matches are closest, and you would then always use that index to look into the list of names to pull out the name associated with the match.

Answer 2

[Image Analyst]

It sounds like you might be able to use a dictionary