Title | Voice Recognition Using Matlab |
---|---|
Course | Signals And Systems |
Institution | Delhi Technological University |
Pages | 20 |
File Size | 541.1 KB |
File Type | |
Total Downloads | 82 |
Total Views | 145 |
Download Voice Recognition Using Matlab PDF
VOICE RECOGNITION IN MATLAB USING CORRELATION
A PROJECT REPORT SUBMITTED IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE AWARD OF THE DEGREE OF
BACHELOR OF TECHNOLOGY IN
SIGNALS AND SYSTEMS
Submitted by:
TURSÉLIO PIRES MAHOQUE 2K19/EC/196 Under the supervision of
DR. PRIYANKA JAIN
DEPARTEMENT OF ELECTRONICS AND COMMUNICATION ENGINEERING DELHI TECHNOLOGICAL UNIVERSITY (Formerly Delhi College of Engineering) Bawana Road, Delhi-110042
NOVEMBER, 2020
i DELHI TECHNOLOGICAL UNIVERSITY (Formerly Delhi College of Engineering) Bawana Road, Delhi-110042
CANDIDATE'S DECLARATION I, TURSÉLIO PIRES MAHOQUE, 2K19/EC/196, Second year student of B. Tech. Signals and Systems, hereby declare that the project Dissertation
titled
“VOICE
RECOGNITION
IN
MATLAB
USING
CORRELATION" which is submitted by me to the Department of Electronics and Communication Engineering, Delhi Technological University, Delhi in partial fulfilment of the requirement for the award of the degree of Bachelor of Technology, is original and not copied from any source without proper citation.
Place: Delhi MAHOQUE Date: November 23rd, 2020
TURSÉLIO
PIRES
ii DELHI TECHNOLOGICAL UNIVERSITY (Formerly Delhi College of Engineering) Bawana Road, Delhi-110042
CERTIFICATE I
hereby certify
that
the
Project
Dissertation titled "
VOICE
RECOGNITION IN MATLAB USING CORRELATION " which is submitted by
TURSÉLIO
PIRES
MAHOQUE,
2K19/EC/196,
Department
of
Electronics and Communication Engineering, Delhi Technological University, Delhi in partial fulfilment of the requirement for the award of the degree of Bachelor of Technology, is a record of the project work carried out by the student under my supervision.
Place: Delhi Date: November 23rd, 2020
DR. PRIYANKA JAIN SUPERVISOR
iii
ACKNOWLEDGEMENT
I would like to express my deepest gratitude to the Almighty God, for keeping giving me His blessings, allowing me to have the opportunity to be a student at DTU. My deepest appreciation to my family, specially my mom, for their endless love, support and encouragement. I would like to extend my sincere thanks to my Signals and Systems lecturer, Dr Priyanka Jain, for always provide her guidance, and lecturing with great enthusiasm and patience, leaving no space to doubts, enabling me to do the project and the report in the best possible way.
iv
ABSTRACT
This paper presents a software built using the Matlab with the purpose of realizing the task of recognizing voice, using the correlation function. The input signal is correlated with each of the sample files present in the database, and if a correspondence is found, it grants access, of not, it denies access.
v
TABLE OF CONTENTS Candidate's declaration...................................................................................................i Certificate.........................................................................................................................ii Acknowledgment............................................................................................................iii Abstract...........................................................................................................................iv CHAPTER 1: INTRODUCTION..................................................................................1 1.1.
General................................................................................................................1
1.2.
Objectives...........................................................................................................1
CHAPTER 2: PROJECT DESCRIPTION...................................................................2 2.1.
Literature review.................................................................................................2
2.1.1.
Voice recognition............................................................................................2
2.1.1.1. 2.1.2.
Types of voice recognition systems.............................................................3 Correlation.......................................................................................................3
2.1.2.1.
Autocorrelation............................................................................................3
2.1.2.2.
Cross-correlation.........................................................................................4
2.2.
Matlab code.........................................................................................................4
2.3.
Matlab code explanation.....................................................................................8
CHAPTER 3: TESTS RESULTS AND CONCLUSION...........................................10 3.1.
Test and results..................................................................................................10
3.2.
Conclusion........................................................................................................12
REFERENCES..............................................................................................................13
vi LIST OF FIGURES Y Figure 1: Examples of autocorrelation of signals.............................................................3 Figure 2: Examples of autocorrelation of signals.............................................................4 Figure 3:(a) Command window of MATLAB before pressing enter (b) Command window of MATLAB after pressing enter.......................................................................10 Figure 4: Plotted graphs of the correlations....................................................................11 Figure 5: :(a) Command window of MATLAB before pressing enter (b) Command window of MATLAB after pressing enter.......................................................................11 Figure 6: Plotted graphs of the correlations...................................................................12
1
CHAPTER 1
INTRODUCTION
1.1.
GENERAL
Communication technology continues to evolve at a rapid pace, and, as voice recognition part of it, it follows the same principle. It can be safely stated that voice recognition is becoming a feature of great importance in the life of the humankind. It is one of the basic components of security systems, automated systems, voice assistant softwares, etc. As the technology advances, there is a need of creating things that do more with less, and the present projects fits in this definition, performing the voice recognition based of one simple function, the correlation function. This project is based on a similar one found on the YouTube channel named “The Engineering Projects”.
1.2.
OBJECTIVES
The project had as its objectives the following aspects:
To design a voice recognition system in Matlab using correlation;
To explain the theory and working of behind voice recognition.
2
CHAPTER 2
PROJECT DESCRIPTION
2.1.
LITERATURE REVIEW
2.1.1. Voice recognition Alternatively referred to as speech recognition, voice recognition is a computer software program or hardware device with the ability to decode the human voice. (Computer Hope, 2020) In a more technical way, voice or speech recognition can be defined as an interdisciplinary subfield of computer science and computational linguistics that develops methodologies and technologies that enable the recognition and translation of spoken language into text by computers. It is also known as automatic speech recognition (ASR), computer speech recognition or speech to text (STT). It incorporates knowledge
and
research
in
the computer
science, linguistics and computer
engineering fields. The first ASR device was used in 1952 and recognized single digits spoken by a user (it was not computer driven). Today, ASR programs are used in many industries, including healthcare, military (e.g., F-16 fighter jets), telecommunications, personal computing (e.g., hands-free computing), digital assistance (such as Siri from Apple, Bixby from Samsung, Cortana from Lenovo).
3 2.1.1.1.
Types of voice recognition systems
There are, in general, five (5) types of recognition systems, namely:
Speaker dependent system - The voice recognition requires training before it can be used, which requires you to read a series of words and phrases.
Speaker independent system - The voice recognition software recognizes most users' voices with no training.
Discrete speech recognition - The user must pause between each word so that the speech recognition can identify each separate word.
Continuous speech recognition - The voice recognition can understand a normal rate of speaking.
Natural language - The speech recognition not only can understand the voice, but can also return answers to questions or other queries that are being asked.
2.1.2. Correlation Correlation is a measure of similarity between two signals, i.e., indicates the measure up to which the given signal resembles another signal. Correlation is a mathematical operation that is very similar to convolution. Just as with convolution, correlation uses two signals to produce a third signal. (Smith, 1998) There are two types of convolution: Autocorrelation and cross-correlation.
2.1.2.1.
Autocorrelation
This is a type of correlation in which the given signal is correlated with itself, usually the time-shifted version of itself (Sneha, 2017).
Figure 1: Examples of autocorrelation of signals
4 Mathematical expression for the autocorrelation of continuous-time signal x (t) is given as: ∞
R xx (τ )= ∫ x ( t ) x ¿ ( t−τ )dτ −∞
Where * denotes complex conjugate Similarly, for a discrete-time signal: ∞
R xx [ m ]= ∑ x [ n] x ¿ [ n−m ] n=−∞
2.1.2.2.
Cross-correlation
This is a kind of correlation, in which the signal in-hand is correlated with another signal so as to know how much resemblance exists between them.
Figure 2: Examples of autocorrelation of signals
Mathematical expression for the cross-correlation of continuous time signals x (t) and y (t) is given by: ∞
R xy (τ )= ∫ x ( t ) y ¿ (t−τ ) dτ −∞
Similarly, for a discrete-time signal: ∞
R xx [ m ]= ∑ x [ n] x ¿ [ n−m ] n=−∞
2.2.
MATLAB CODE 1. function speechrecognition(filename) 2. fprintf('TURSÉLIO PIRES MAHOQUE- 2K19/EC/196 \n')
5 3. fprintf('Voice Recognition Using Correlation \n') 4. fprintf('') 5. fprintf('') 6. %Write Following Command on Command Window in order to start the program 7. %speechrecognition('test.wav') 8. voice=audioread(filename); 9. x=voice; 10.
x=x';
11.
x=x(1,:);
12.
x=x';
13.
z=xcorr(x,x);
14.
l=length(z);
15.
t=-((l-1)/2):1:((l-1)/2);
16.
t=t';
17.
y1=audioread('one.wav');
18.
y1=y1';
19.
y1=y1(1,:);
20.
y1=y1';
21.
z1=xcorr(x,y1);
22.
m1=max(z1);
23.
l1=length(z1);
24.
t1=-((l1-1)/2):1:((l1-1)/2);
25.
t1=t1';
26.
subplot(3,2,1);
27.
plot(t1,z1);
28.
title('Sample 1');
29.
grid on;
30.
y2=audioread('two.wav');
31.
y2=y2';
32.
y2=y2(1,:);
6 33.
y2=y2';
34.
z2=xcorr(x,y2);
35.
m2=max(z2);
36.
l2=length(z2);
37.
t2=-((l2-1)/2):1:((l2-1)/2);
38.
t2=t2';
39.
subplot(3,2,2);
40.
plot(t2,z2);
41.
title('Sample 2');
42.
grid on;
43.
y3=audioread('three.wav');
44.
y3=y3';
45.
y3=y3(1,:);
46.
y3=y3';
47.
z3=xcorr(x,y3);
48.
m3=max(z3);
49.
l3=length(z3);
50.
t3=-((l3-1)/2):1:((l3-1)/2);
51.
t3=t3';
52.
subplot(3,2,3);
53.
plot(t3,z3);
54.
title('Sample 3');
55.
grid on;
56.
y4=audioread('four.wav');
57.
y4=y4';
58.
y4=y4(1,:);
59.
y4=y4';
60.
z4=xcorr(x,y4);
61.
m4=max(z4);
62.
l4=length(z4);
63.
t4=-((l4-1)/2):1:((l4-1)/2);
64.
t4=t4';
7 65.
subplot(3,2,4);
66.
plot(t4,z4);
67.
title('Sample 4');
68.
grid on;
69.
y5=audioread('five.wav');
70.
y5=y5';
71.
y5=y5(1,:);
72.
y5=y5';
73.
z5=xcorr(x,y5);
74.
m5=max(z5);
75.
l5=length(z5);
76.
t5=-((l5-1)/2):1:((l5-1)/2);
77.
t5=t5';
78.
subplot(3,2,5);
79.
plot(t5,z5);
80.
title('Sample 5');
81.
grid on;
82.
subplot(3,2,6);
83.
plot(t,z,’r’);
84.
title('Input signal');
85.
grid on;
86.
m6=300;
87.
a=[m1 m2 m3 m4 m5 m6];
88.
m=max(a);
89.
h=audioread('granted.wav');
90.
if m...