Voice Identification And Recognition System, Matlab

VOICE IDENTIFICATION AND
RECOGNITION SYSTEM
A SIMPLE YET COMPLEX APPROACH TO MODERN SOPHISTICATION
VOICE IDENTIFICATION AND RECOGNITION SYSTEM 1

GROUP MEMBERS
• SOHAIB TALLAT SP13-BCE-040
• FARHAN SHAHID SP13-BCE-013
• ABDUL SAMAD SP13-BCE-002
• MATTI ULLAH ABBASI SP13-BCE-025

INTRODUCTION AND INSPIRATION
• As we know that simplicity has taken its tool, it is now the age of sophisticated technologies therefore
nowadays efficient security systems have to be utilised in our life.
• The “VOICE IDENTIFICATION AND RECOGNITION SYSTEM” has been developed to cater our needs for
controlling access to services such as: banking, databases systems etc. which are used to secure
confidential information.
• We were inspired to make this project for making lock mechanism systems speech automated,
especially for the ease of physically disabled people.

ABSTRACT
• Approaches for making Voice recognition sytems:
a. Linear Prediction Coding (LPC)
b. Mel-Frequecy Cepstrum Coefficients (MFCC) and others.
• Principle Used: Mel-Frequecy Cepstrum Coefficients (MFCC)
• Working

THE VOICE IDENTIFICATION ALGORITHM
• Priciples of Speaker Recognition:
a. Identification
b. Verification
Input
speech
Feature
extraction
Reference
model
(Speaker #1)
Similarity
Reference
model
(Speaker #N)
Similarity
Maximum
selection
Identification
result
(Speaker ID)
Reference
model
(Speaker #M)
Similarity
Input
speech
Feature
extraction
Verification
result
(Accept/Reject)
Decision
ThresholdSpeaker ID
(#M)
Figure 1: Speaker Identification
Figure 2: Speaker Recognition

FEATURE EXTRACTION
• Feature extraction is the process that extracts a small amount of data from the voice signal that can
later be used to represent each speaker.
• A wide range of possibilities exist for parametrically representing the speech signal for the speaker
recognition task, such as Mel Frequency Cepstrum Coefficients (MFCC).
0 0.002 0.004 0.006 0.008 0.01 0.012 0.014 0.016 0.018
-0.5
-0.4
-0.3
-0.2
-0.1
0
0.1
0.2
0.3
0.4
0.5
Time (second)
Figure 3: Example Of Speech Signal

MEL-FREQUENCY CEPSTRUM COEFFICIENTS (MFCC)
PROCESSOR
mel
cepstrum
mel
spectrum
framecontinuous
speech
Frame
Blocking
Windowing FFT spectrum
Mel-frequency
Wrapping
Cepstrum

MFCC PROCESSOR ELABORATED
• Frame Blocking
• Windowing
• Fast Fourier Transform
• Mel- Frequency Wrapping
• Cepstrum
0 1000 2000 3000 4000 5000 6000 7000
0
0.2
0.4
0.6
0.8
1
1.2
1.4
1.6
1.8
2
Mel-spaced filterbank
Frequency (Hz)
Figure 4: Example of mel-spaced
frequency bank

FEATURE MATCHING
• Feature matching involves the actual procedure to identify the unknown speaker by comparing
extracted features from his/her voice input with the ones from a set of known speakers
• The goal of pattern recognition is to classify objects of interest into one of a number of categories or
classes.
• The objects of interest are called patterns and in our case are sequences of acoustic vectors that are
extracted from an input speech.
• Classes are referred to individual speakers.

PATTERN RECOGNITION TECHNIQUE
• Feature matching technique used in “VOICE IDENTIFICATION AND RECOGNITION SYSTEM” is Vector
Quantization (VQ).
• VQ is a process of mapping vectors from a large vector space to a finite number of regions in that space.
Each region is called a cluster and can be represented by its center called a codeword. The collection of
all codewords is called a codebook.

RECOGNITION PROCESS
Speaker 1
Speaker 1
centroid
sample
Speaker 2
centroid
sample
Speaker 2
VQ distortion
Figure 5: Conceptual Diagram Illustrating Vector
Quantization codebook Formation

LINDE-BUZO-GREY ALGORITHM
The Linde–Buzo–Gray algorithm (introduced by Yoseph Linde,
Andrés Buzo and Robert M. Gray in 1980) is a vector quantization
algorithm to derive a good codebook.
Find
centroid
Split each
centroid
Cluster
vectors
Find
centroids
Compute D
(distortion)


D
D'D
Stop
D’ = D
m = 2*m
No
Yes
Yes
No
m < M

THE GRAPHICAL USER INTERFACE
• There are many ways to make your own custom Graphical User Interface (GUI); you can do it manually
or you can use another efficient approach that is the “Guide” approach.
Figure 6: Guide Quick Start Window
Figure 7: Our Custom GUI

EMBEDDING CODE TO THE GUI
• Note that in the figure we have six essential buttons, which perform their unique task.
a. “Add New Sound To The Database”
b. “Speaker Recognition From Mike”
c. “DATABASE INFORMATION”
d. “PLOT DATABASE”
e. “Delete Database”
f. “EXIT”
Figure 7: Our Custom GUI

ADDING BACK GROUND TO THE GUI
CODE:
% create an axes that spans the whole gui
ah = axes('unit', 'normalized', 'position', [0 0 1 1]);
% import the background image and show it on the axes
bg = imread('project image 3.jpg'); imagesc(bg);
% prevent plotting over the background and turn the axis off
set(ah,'handlevisibility','off','visible','off')
% making sure the background is behind all the other uicontrols
uistack(ah, 'bottom');
Figure 8: Our Custom Background

Figure 9: Our Final Program

APPLICATION DEPLOYMENT
Figure 10: Standalone application deployment window Figure 11: Our Custom Splash screen

REFERENCES
• L.R. Rabiner and B.H. Juang, Fundamentals of Speech Recognition, Prentice-Hall, Englewood Cliffs, N.J., 1993.
• S.B. Davis and P. Mermelstein, “Comparison of parametric representations for monosyllabic word recognition
in continuously spoken sentences”, IEEE Transactions on Acoustics, Speech, Signal Processing, Vol. ASSP-28,
No. 4, August 1980
• Y. Linde, A. Buzo & R. Gray, “An algorithm for vector quantizer design”, IEEE Transactions on Communications,
Vol. 28, pp.84-95, 1980
• S. Furui, “Speaker independent isolated word recognition using dynamic features of speech spectrum”, IEEE
Transactions on Acoustic, Speech, Signal Processing, Vol. ASSP-34, No. 1, pp. 52-59, February 1986
• F.K. Song, A.E. Rosenberg and B.H. Juang, “A vector quantisation approach to speaker recognition”, AT&T
Technical Journal, Vol. 66-2, pp. 14-26, March 1987
• comp.speech Frequently Asked Questions WWW site,
http://svr-www.eng.cam.ac.uk/comp.speech/

Voice Identification And Recognition System, Matlab

Voice Identification And Recognition System, Matlab

More Related Content

Similar to Voice Identification And Recognition System, Matlab (20)

Recently uploaded (20)

Voice Identification And Recognition System, Matlab