**Noise Reduction Using LMS Algorithm**

**AIM:**

This paper describes
one of the noise reduction techniques, which is widely used in reducing the noise
of audio signal. This paper also describes practical implementation of LMS
algorithm in both Software and Hardware (On Texas Instrument Processor).

**INTRODUCTION**

As we know that Noise
is a very big problem for communication system. Due to the noise, the message
signal can’t be easily retrieved. Hence for a good communication system, it is
very important to reduce the noise as much as possible. Coming to digital
communication, various noise reduction techniques are used for this purpose.
One of widely used technique is Least Mean Square (LMS) techniques, which will
be discussed here.

**THE LMS ALGORITHM:**

This was invented in 1960 by Stanford University professor Bernard
Widrow and his first Ph.D. student, Ted
Hoff.

**Least mean squares (LMS)**algorithms are a class of adaptive filter used to mimic a desired filter by finding the filter coefficients that relate to producing the least mean squares of the error signal (difference between the desired and the actual signal). It is a stochastic gradient descent method in that the filter is only adapted based on the error at the current time.

*variable*coefficients w.

The Least Mean Squares Algorithm (LMS) updates each
coefficient on a sample-by-sample basis based on the error

*e(n).*
If Âµ is too small, the filter reacts slowly.

If Âµ is too large, the filter resolution is poor.

The selected value of Âµ is a compromise.

**SIMULATION:**

Any of the simulation tools can be used for this
purpose, either MATLAB or CODE COMPOSER STUDIO.

For realising the input and output waveform, MATLAB simulation
tools is going to be used.

**Steps:**

1)
Open
the following Simulink model: “AcousticNoiseCancellation”.(This model is
already designed in newer version of MATLAB ,if not so, then you can make this
model)

**2)**

**Setting the Step size (mu)**

The rate of convergence of the LMS Algorithm is
controlled by the “Step size (mu)”.

This is the critical variable.

3)
Trace of Input to Model

INPUT=
SIGNAL + NOISE

4)
Trace of LMS Filter Output

5)
Trace of LMS Filter error.

The step by step MATLAB
is shown in figure

STEP2

STEP4

STEP3 STEP4 STEP5

**INTRODUCTION TO LABORATORY:**

To implement the LMS
Algorithm, we can use Texas Instrument DSP Processor i.e. c6713. First

We should make the
model on simulink. then we will
interface with processor.

**We will build the model “AcousticNoiseReductionDSKC6713”**

**STEP 2:**

**Using Frames**

1).This model uses frames of
data rather than individual bytes.

2).The “Samples per frame”
is set to 64.

STEP2

**3)**

**When the model is built, the**

*frames*are shown as double lines.

**STEP3**

**Setting up the C6713 DSK**

•
Plug
an microphone and computer loudspeakers / headphones into the C6713 DSK.

•
Put
the microphone next to a source of random noise e.g. an off-station radio.

•
Speak
into the microphone.

•
Listen
to the output.

Then
run the model, and you can analyze the output in headphone.

**CONCLUSION**

Thus,
we wind up this session by concluding that this LMS technique of noise
reduction is easiest technique and waiting for more future application. Hence
we can use this technique for innovative applications, where noise reduction is
more important. As an ECE engineer, I hope that we will use this technique in
many applications.

**REFRENCES:**

1) Digital Signal Processing, A Practical Approach by
Emmanuel C. Ifeachor and Barrie W. Jervis. ISBN 0201-59619-9.

2)Digital Signal Processing with C and the TMS320C30
by Rulph Chassaing. ISBN 0-471-55780-3

## 0 comments:

## Post a comment