Scribd
Upload
20 views12 pages

GRP 3 DSP Assignment2 21april2025

The document outlines a project on active noise control using the LMS adaptive filter, aimed at enhancing speech clarity by reducing background noise. It details the implementation process in MATLAB, including the algorithm, system overview, and results showing improved audio quality. The project highlights applications in mobile communication, voice assistants, and medical audio processing.

Uploaded by

Achal Naikwadi
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
20 views12 pages

GRP 3 DSP Assignment2 21april2025

The document outlines a project on active noise control using the LMS adaptive filter, aimed at enhancing speech clarity by reducing background noise. It details the implementation process in MATLAB, including the algorithm, system overview, and results showing improved audio quality. The project highlights applications in mobile communication, voice assistants, and medical audio processing.

Uploaded by

Achal Naikwadi
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 12

Assignment -2: Application of DSP

Group No.: 03

Active noise control using LMS


Adaptive Filter

Presentee:
1. Ojasvi Sonone
2. Chetana Toke
3. Roshni Singh
4. Achal Naikwadi
Index

● Introduction
● Project Objective
● System Overview
● LMS Algorithm
● MATLAB Implementation
● Results and Graphs
● Observations and Conclusions
Introduction to Noise Control

● Removes unwanted background noise from


input audio.

● Improves speech clarity in real-world


environments.

● Used in phones, hearing aids, teleconferencing,


and others.

● DSP role: Real-time noise reduction using


adaptive filters.
Project Objective

Implement adaptive noise cancellation using LMS algorithm


Use pre-recorded audio files of Noisy speech and Reference noise
Output: Enhanced speech with reduced noise
System Overview

● Two inputs: ● LMS filter:


○ Primary: Noisy speech ○ Learns noise pattern from reference
○ Reference: Background noise ○ Subtracts estimated noise from speech
LMS Algorithm

Goal: Minimize error between desired and estimated signal

Updates filter weights based on: Key terms:


● μ: step size
● y(n) = w(n)^T * x(n)
● x(n): reference noise
● e(n) = d(n) - y(n)
● d(n): noisy input
● w(n+1) = w(n) + μ * x(n) * e(n)
● e(n): output (cleaned)
MATLAB Implementation

● Filter Length: 32
● Step Size: 0.01

Steps:
● Load & preprocess audio
● Resample, convert to mono
● Trim to equal length
● Apply LMS filter
● Save & play filtered output
Results and Graphs

Waveform Analysis:

1. Noisy Speech Input :

○ Voice mixed with


significant background
noise

○ Amplitude fluctuations
from speech and noise
Results and Graphs

Waveform Analysis:
2. Reference Noise Input:

○ Only background noise


signal

○ Used to train the LMS


filter
Results and Graphs

Waveform Analysis:

3. Filtered Output :
○ Speech becomes clearer

○ LMS successfully reduces


noise while retaining
speech integrity
Observations and Conclusion

● LMS filter adaptively reduced noise using reference input


● MATLAB-based implementation was effective
● Clear improvement in speech quality

Applications:
● Mobile communication
● Voice assistants
● Medical audio processing
Any Questions…….?

Thank You!!

You might also like