You are on page 1of 11

AKSUM UNIVERSITY

AKSUM INSTITUTE OF
TECHNOLOGY
FACULTY OF ELECTRICAL AND COMPUTER ENGINEERING
DEPARTMENT OF ELECTRONICS AND COMMUNICATION
ENGINEERING

Title: Noise Reduction Using Adaptive Filter


4 YEAR SEMISTER PROJECT PROPOSAL
th

Name ID
1,TADESE ATOMSSA...........................................................0904885

2,G/MARIAM MULIE..........................................................0902229

3,ALMAZ ALEMNEH............................................................0900505

Advisor name Yonatan Gidey

1
Abstract
In practical application, the statistical characteristics of signal and noise are usually unknown
or can’t have been learned so that we hardly design fix coefficient digital filter. in allusion to
this problem, the theory of adaptive filter and adaptive noise cancellation are researched
deeply. According to the recursive least mean square algorithm realizes the design and
simulation of the adaptive algorithm in noise reduction and analyse the result to prove its
performance is better than the use of fixed filters designed by conventional methods. In any
communication system noise always had been a major area of concern. Noise signals affect
the transmitted signals during transmission. Every signal that we acquire at the receiver end
of any communication system is somehow affected by noise. Noise is the unwanted part of
the signal. Signals can be of various types in communication systems depending upon the
requirement of the system. Signals carrying information during transmission of voice or
speech or image or video. Each of these signals gets affected during transmission. So for de-
noising of these signals of deferent types we need different noise reduction mechanism. We
have adopted adaptive noise reduction mechanism for signals carrying information in speech
communication. In speech communication the speech data signal transmitted will be useless
until and unless proper noise reduction mechanism is adopted at the receiver end. There are
so many mechanisms for such noise reduction. In this paper, we have adopted a new adaptive
filtering with RLS algorithm for noise reduction. This algorithm, we have proposed is based
by using averages of both data and correction terms to find the updated values of the tap
weights of the ANR controller of the speech signal.

Key words: Adaptive Filter, Noise Reduction, Adaptive Algorithm, RLS Algorithm

2
Contents
Abstract......................................................................................................................................2
INTRODUCTION......................................................................................................................4
Background.............................................................................................................................4
Statement of the Problem.......................................................................................................5
Objective of the Project..........................................................................................................5
General Objective...............................................................................................................5
Specific Objective...............................................................................................................5
Scope of the Project................................................................................................................5
Significance of the Project......................................................................................................5
Methodology...........................................................................................................................6
Literture review......................................................................................................................7
summary.................................................................................................................................8
Time schedule.........................................................................................................................9
List of References.................................................................................................................10

3
INTRODUCTION
Background
In the process of digital signal processing, often to deal with some unforeseen signal, noise,
or time varying signals, if by a two FIR and IIR filter of fixed coefficients cannot achieve
optimal filtering. under each circumstance ,we must design adaptive filters ,to track the
change of signal and noise .adaptive filter is that uses a filter parameter of moment ago to
automatically adjust the filter parameter of the present moment, to adapt to the statical
properties of that the signal and noise unknown or random changes, in order to achieve
optimal filter. Based on in-depth study of adaptive filter, based on recursive least mean
square are applied to adaptive filter technology to the noise ,and its performance is usually
better than using conventional methods designed to fixed filter. Noise consists of unwanted
waveforms that can disturb our communication. Noise can be internal or external to the
system. Sound noise: interferes with your normal hearing.

NOISE reduction: Noise reduction is a method to reduce or cancel out undesirable


components of the signal.

4
Statement of the Problem
 Adaptive noise reduction with adaptive algorithm is one of the most popular
algorithms to solve many problems.
 The main motivation in the use of adaptive filtering is Standard DSP techniques,
however, are not enough to solve these problems quickly and obtain acceptable
results.
 Adaptive filtering techniques must be implemented to promote accurate solutions
and a timely convergence to that solution.
 To implement and effective use of ANC to minimize noise from noisy signal.

Objective of the Project


General Objective
 The main goal of the project is Reducing noise from the signal which is corrupted by
noise using adaptive filter.

Specific Objective
 To design different systems that iteratively reduce the noise from the noisy signal such
as adaptive system identification, adaptive noise cancellations predicting coding,
adaptive inverse system and each having respective function to reduce the noise
 To converge the error signal that is interfered on the input signal by comparing it to the
desired signal.
 This adaptive noise reducing system would be used to increase the signal to noise ratio
(SNR) signal by decreasing the power of the noise.

Scope of the Project


 Writing an adaptive algorithm using MATLAB.
 Generate model for system identification to determine the suitable step size.
 Apply different noise reducing systems.
 Data will be simulated using adaptive algorithm to reduce noise in an speech signal.

Significance of the Project


 Knowing the importance of adaptive filter for reduction of noise signal from the noisy
signal.
 To get aware of how to program noise reduction using adaptive filter in mat lab.
 Overcoming the difficulties of noise reduction using a digital filtering method called
direct filtering that are not adapted the environment to filter out the noise and other DSP
filtering mechanisms.
 Reducing noise from noisy signal without knowing the characteristics of the signal.

5
Methodology
For successful completion of this project RLS adaptive filter algorithm systems able to

 Adaptive system identification identify unknown system.


 Noise cancellation filter remove noise from signal.
 Adaptive inverse system identification adapts to inverse the un known system.

All the above methods of filtering systems are designed/simulated by mat lab code

start

problem

literature review

data collection

data analysis

system modelling

select matlab
soft ware

end
simulation run

6
LITERATURE REVIEW

Diggikar, A. B., and S. S. Ardhapurkar (2012), deals with Adaptive noise canceller are used
in the design and implementation of adaptive filtering algorithm for noise reduction in speech
signal. The output of the speech signal is applied to the field programmable gate array
(FPGA).In this for the execution of the speech signal code VHDL is used is performed on the
basis of Signal to Noise ratio (SNR) and Mean Square Error (MSE). In recent years acoustic
noises become more evident due to wide spread use of industrial equipments. An Active (also
called as Adaptive) noise reduction (ANC) is a technique that effectively attenuates low
frequencies unwanted noise whereas passive methods are either ineffective or tends to be
very expensive or bulky

Vijaykumar et al(2007), project analyzes the Modified Adaptive Filtering Algorithm for
Noise reduction in Speech, Speech signal is applied to the Adaptive filter and different types
of noise signals are applied to the adaptive filter. Difference between the speech signal output
and noise signal output are compared. One relationship between the strength of the speech
signal and the masking sound is called the signal-to-noise ratio, expressed in decibels.

Pramanik et al (2012), we have showed a de-noising or noising reduction mechanisms using


Mean Power Calculation (MPC) for voice communication. This algorithm is applicable for
voice communication only. For testing purpose we tested it with real time recorded voice
communication only. Later on we have thought of implementing de-nosing mechanisms for
image and video transmission.

 for this project we will use three (3) references.


[1] Haykin, Simon, Adaptive Filter Theory, Prentice Hall, Upper Saddle River, New Jersey, 1996.

[2] Honig, Michael L., Messerschmitt, David G., Adaptive Filters, Structures, Algorithms and
Applications, Kluwer Academic Publishers, Boston, 1984.

[3] S.I.A.Sugiyama, “an adaptive noise canceller low signals distortion “IEEE Trans.Signal
processing, vol. 47, pp. 665 mar 1999.

7
Material/software needed
 Mat lab 2013

summary
 generally as the signal into the filter continues, the adaptive filter coefficients adjust
themselves to achieve the desired result, such as identifying an unknown filter or
cancelling noise in the input signal.
 In noise cancellation, adaptive filters let you remove noise from a signal in real time.
Here, the desired signal, the one to clean up, combines noise and desired information
Predicting signals requires that you make some key assumptions. Assume that the
signal is either steady or slowly varying over time, and periodic over time as well.

8
Time schedule(work plan)
Activity March April
Collecting data about our 
project i.e downloading info
Organising the general 
working principles of our
project
Asking Our advisor about  
the project in every weeks
Finding mat lab codes 
related to topics of our
project
Starting to run our mat lab 
codes
Arranging the info in the 
project
Starting to show simulation 
results

9
List of References
[1], Haykin, Simon, Adaptive Filter Theory, Prentice Hall, Upper Saddle River, New Jersey, 1996.

[2], Honig, Michael L., Messerschmitt, David G., Adaptive Filters, Structures, Algorithms and
Applications, Kluwer Academic Publishers, Boston, 1984.

[3], S.I.A.Sugiyama, “an adaptive noise canceller low signals distortion “IEEE Trans.Signal
processing, vol. 47, pp. 665 mar 1999.

10
11

You might also like