Scribd
Upload
180 views13 pages

Speech Recognition System Using Matlab

This document describes a speech recognition system created using MATLAB. The system uses cross-correlation and Mel frequency cepstral coefficients (MFCCs) to match input speech patterns to sample audio files of numbers 1 through 5. Graphs are generated comparing the input to each sample. If the input most closely matches a sample, the corresponding number is sounded. Otherwise, a denial sound is played, demonstrating the system's ability to recognize and differentiate between spoken numbers.

Uploaded by

Charitha Reddy
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
180 views13 pages

Speech Recognition System Using Matlab

This document describes a speech recognition system created using MATLAB. The system uses cross-correlation and Mel frequency cepstral coefficients (MFCCs) to match input speech patterns to sample audio files of numbers 1 through 5. Graphs are generated comparing the input to each sample. If the input most closely matches a sample, the corresponding number is sounded. Otherwise, a denial sound is played, demonstrating the system's ability to recognize and differentiate between spoken numbers.

Uploaded by

Charitha Reddy
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 13

PROJECT TITLE:

SPEECH RECOGNITION SYSTEM USING


MATLAB

SUBMITTED TO:-

SUBMITTED BY:
ABSTRACT
The development in wireless communication and mobile devices has improved
the voice recognition system. The term voice recognition system has two main
significant terms, pattern matching and feature extraction. This report
classifies and computes an algorithm using MATLAB to match the patterns
and recognize speech using cross correlation technique. Correlation is a
statistical measure where two or more signals are compared to check if there
is a similarity between them. Speech recognition is a part of biometrics and
has become one of the major aspects to provide security to the devices and
applications. Speech recognition is a concept where we extract the spoken
words and match it with the sample.
INTRODUCTION
Speech Recognition is a method of capturing the talked words using a gadget
and converting them into a digitally stored set of words. This system is used in
almost every project where you need to speak and tell your password to the
system to unlock the things we want. At present, there is a need for expanding
and need to confirm and identify the voice of persons automatically. For every
individual securing the personal details from the theft is the national priority.
This report tells about the concept Mel frequency cepstral coefficients (MFCCs)
as the feature for the recorded speech. It is a developing innovation that
guarantees a viable answer for our security needs. We can utilize a biometric to
get to our home, our record, or to conjure an altered setting for any safe range or
application.
BIOMETRICS:
Biometrics is the method of measuring the physical qualities of a person, which
got it’s name from the Greek words bio (life) and metric (to quantify) which
includes speech recognition, iris and face scans, and fingerprint recognition.

Biometric qualities can be further classified in two principle classes:

Physiological: These biometrics is the other sort utilized for


distinguishing proof or check purposes. Varying the proof indicates to
figuring out who a person in detail is. This technique is ordinarily utilized
as a part of criminal examinations.

Behavioural: It is utilized for confirmation purposes. Here it is deciding


whether a man is who they say they are. This method takes a unique
pattern at times of how certain gestures are made by a person.
METHADOLOGY:
Speech recognition is now a days widely used in nearly every security project
where a machine can recognize a person‘s voice as password to unlock it. For
example, in user‘s daily life, if user want to turn the car engine on or off using
the voice commands then Speech Recognition plays play an role. So we must
develop an application that would understand the system and recognize whether
the user commands ON or OFF. To develop such application we are using cross
correlation technique for recognition of speech and simulate it in MATLAB.
Correlation compares two signals, considering the five samples and comparing
them with the test sample gives us the result. All the sound samples must be in
.wav format. To recognize the words from the sound we use the Mel frequency
cepstral coefficients (MFCCs) concept is used.

Some of the modes which are available for Speech Recognition System are:
1. Speaker Dependent or Independent System: The system must be trained in
order to recognize precisely what has been said. So to train a system, the
speaker is asked to record some words or sentences that will be analysed and
that results will be stored.

2. Isolated Word Recognition: It is one of the simplest and has less chances in
terms of CPU requirement. Word is surrounded by the boundaries and are very
well known.

3. Continuous Speech Recognition:- It assumes that system is able to


recognize and identify a different sequence of words in a sentence.

4. Keyword Spotting:- It is able to recognise a sentence a word similar to a


particular command. It is made to cover a gap between isolated and continuous
systems.

5. Vocabulary Size:- If the vocabulary size is large, the system can make more
errors. So the size of the vocabulary matters a lot.
CROSS-CORRELATION TECHNIQUE:
Cross-correlation is the concept of checking the similarity of two signals or
waves as a function of the displacement which are relative to each other.
Basically this technique helps us to identify a shorter signal in a longer signal
very easily. This concept is having applications equally in both the pattern
recognition as well as single particle analysis. The term cross-correlation is used
for checking or establishing a relationship between the sections of any two
random arbitrary vectors.

In MATLAB ‘xcorr’ function is used for finding the cross-correlation function


for the given sequence of a random process which includes autocorrelation.

Here the function r = xcorr(x,y) gives the cross-correlation of two time


sequences. Cross-correlation measures the closeness amongst the two or more
signals(vectors).
MATLAB CODE:-

%Speech Recognition Using Correlation Method


%DSPP('test.wav')
function DSPP(filename)
voice=audioread(filename);
x=voice;
x=x';
x=x(1,:);
x=x';
y1=audioread('one.wav');
y1=y1';
y1=y1(1,:);
y1=y1';
z1=xcorr(x,y1);
m1=max(z1);
l1=length(z1);
t1=-((l1-1)/2):1:((l1-1)/2);
t1=t1';
%subplot(3,2,1);
plot(t1,z1);
title('Cross Correlation With One');
y2=audioread('two.wav');
y2=y2';
y2=y2(1,:);
y2=y2';
z2=xcorr(x,y2);
m2=max(z2);
l2=length(z2);
t2=-((l2-1)/2):1:((l2-1)/2);
t2=t2';
%subplot(3,2,2);
figure
plot(t2,z2);
title('Cross Correlation With Two');
y3=audioread('three.wav'); y3=y3';
y3=y3(1,:);
y3=y3';
z3=xcorr(x,y3);
m3=max(z3);
l3=length(z3);
t3=-((l3-1)/2):1:((l3-1)/2);
t3=t3';
%subplot(3,2,3);
figure
plot(t3,z3);
title('Cross Correlation With Three');
y4=audioread('four.wav');
y4=y4';
y4=y4(1,:);
y4=y4';
z4=xcorr(x,y4);
m4=max(z4);
l4=length(z4);
t4=-((l4-1)/2):1:((l4-1)/2);
t4=t4';
%subplot(3,2,4);
figure
plot(t4,z4);
title('Cross Correlation With Four');
y5=audioread('five.wav');
y5=y5';
y5=y5(1,:);
y5=y5';
z5=xcorr(x,y5);
m5=max(z5);
l5=length(z5);
t5=-((l5-1)/2):1:((l5-1)/2);
t5=t5';
%subplot(3,2,5);
figure
plot(t5,z5);
title('Cross Correlation With Two');
m6=300;
a=[m1 m2 m3 m4 m5 m6];
m=max(a);
h=audioread('allow.wav');
if m<=m1
soundsc(audioread('one.wav'),50000)
soundsc(h,50000)
elseif m<=m2
soundsc(audioread('two.wav'),50000)
soundsc(h,50000)
elseif m<=m3
soundsc(audioread('three.wav'),50000)
soundsc(h,50000)
elseif m<=m4
soundsc(audioread('four.wav'),50000)
soundsc(h,50000)
elseif m<m5
soundsc(audioread('five.wav'),50000)
soundsc(h,50000)
else
soundsc(audioread('denied.wav'),50000)
end
RESULTS:-
After running the above written code in MATLAB, we have got the graphs
comparing the test file and the sample audio files. There are a total of two test
files and five sample files which has audio from one to five. Here to show both
the allowed and denied cases we have taken two test files of which one is from
the five sample files and another test file is a random file which is does not
match with any sample files. When a test file is given as the input, the loop
starts where first the spoken word from the audio files are computed and
correlated with each other and using MATLAB the graph where frequency of
speech is displayed.

Initially we compare the first test file‘test.wav’ file which matches with the
second sample and check the output graphs. When the input speech
recognition(test.wav‘) is given in the command window of MATLAB, the
comparison will start.

The obtained graphs are:-


In the second graph we can see that the test file is matched with the second
sample, now the system will give us the access.

Now we shall enter a random signal and check the denied


results
Since we have sent a sample that does not matches with stored five samples,
so the system denies the access.
CONCLUSION:
This successfully explains us about various features, behaviour and
characteristics of voice signals and also defines the concept of cross -
correlation. In this report, an algorithm has been created with the help of
MATLAB programming which requires .wav format voice input signals where
comparison with the test sound file using correlation technique takes place. In
order to remove further limitation of audio formats there is a requirement for the
study of various types and formats of voice signals which will be further used
for communicating with the machines which include the prototype that is the
hardware part and not the MATLAB simulation.

REFERENCES

1. Mahdi Shaneh and Azizollah Taheri, Voice Command Recognition System


based on MFCC and VQ Algorithms, World Academy of Science, Engineering
and Technology Journal, 2009.

2. “SPEECH RECOGNITION USING MATLAB” By Aseem Saxena, Amit


Kumar Sinha, Shashank Chakrawarti, Surabhi Charu, International Journal of
Advances In Computer Science and Cloud Computing, ISSN: 2321-4058
Volume- 1, Issue- 2, Nov-2013.

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy