YasinRezvani/Audio_Denoising_Using_FFT_and_CNNPublic

NotificationsYou must be signed in to change notification settings
Fork0
Star8

Combines FFT-based filtering with a custom CNN model to denoise audio signals and explore the strengths of each approach.

License

MIT license

8 stars 0 forks Branches Tags Activity

Star

Notifications

You must be signed in to change notification settings

Branches Tags

Folders and files

Name		Name	Last commit message	Last commit date
Latest commit History 11 Commits
LICENSE		LICENSE
README.md		README.md
audio_with_noise.wav		audio_with_noise.wav
denoised_audio_tensorflow.wav		denoised_audio_tensorflow.wav
filtered_audio_pulse.wav		filtered_audio_pulse.wav
main.ipynb		main.ipynb

Repository files navigation

Audio_Denoising_Using_FFT_and_CNN

Supervisor:Dr. Esmaeel Tahanian
Course: Engineering Mathematics
Organization:Shahrood University of Technology

This project develops an audio denoising system integrating Fourier transform-based signal processing and deep learning Autoencoders to suppress noise while maintaining acoustic integrity. It utilizes Fourier analysis for spectral noise reduction and trains an Autoencoder model on noisy audio data to reconstruct clean signals. Implemented in Python and TensorFlow.

Demo 🎉

Audio_Denoising_Using_FFT_And_CNN.mp4