International Journal of Research and Development in Engineering Sciences (IJRDES ) | Unified Noise Reduction Framework Using U-Net for Audio and Image

Unified Noise Reduction Framework Using U-Net for Audio and Image

Unified framework for noise reduction in both audio and image domains using advanced deep learning techniques, specifically a U-Net architecture. The application is designed to facilitate the denoising process for various types of noise, including Salt and Pepper, Gaussian, Impulse, White Noise, and Environmental Noise in audio signals, as well as for noisy images. The framework leverages TensorFlow and Keras for model training and inference, utilizing U-Net models for audio and image denoising tasks. Users can record or upload noisy audio files, which are processed through a series of denoising techniques, including spectral subtraction, Wiener filtering and U-Net. The denoised audio can be played back, visualized, and saved for further use. In the image processing module, users can load noisy images and their corresponding ground truth images. The application employs a U-Net model to predict and display denoised images, allowing for visual comparison with the original noisy images. Additionally, edge detection is performed on the images using the Canny edge detection algorithm, providing insights into the structural integrity of the denoised outputs. The graphical user interface (GUI) is built using Tkinter, offering an intuitive experience for users to navigate through audio and image processing functionalities.

Research Type: Action Research
Paper Type: Experimental Research Paper
Vol.7 , Issue 5 , Pages: 10 - 14, Sep 2025
Published on: 18 Sep, 2025
Issue Type: Regular

Cite Score

:

100
No. of authors

:

75
No. of Downloads

:

43

Cite Score

:

100
No. of authors

:

75
No. of Downloads

:

43

Cite Score

:

100
No. of authors

:

75
No. of Downloads

:

43

About Authors:

G.Sravya

India

Viswam Engineering College

"""

Copyright © 2025, This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC-BY-NY-SA). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

*Corresponding Author: G.Sravya, gsravya@gmail.com

Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.

Conflict of interest: The author declares that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Publisher’s note: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article, or claim that may be made by its manufacturer, is not guaranteed or endorsed by the publisher.