Skip to content

harshit2997/11785-Speech-Denoising

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

11785-Speech-Denoising

This is the repository for the course project for 11785-Introduction to Deep Learning. We worked on image denoising using deep learning. This repository contains the Jupyter notebooks used for the project. They are organized as below:

  • Acoustic_Features_Analysis.ipynb : Get acoustic features for clean, noisy, and processed samples. Measure MAE and imrovement in it because of processing
  • Test_Data_Metrics.ipynb : Measure pairwise metrics of clean and processed data
  • FullSubNet/FullSubNet_Inference.ipynb : Run inference on noisy audio files using FullSubNet model
  • FullSubNet/11785_S23_FullSubNet_Training_Example.ipynb : Train or fine tune FullSubNet models
  • Demucs/11785_S23_Demucs_Training_and_Inference.ipynb : Train/fine tune and run inference on Demucs models More details on Demucs training and denoising can be found https://github.com/YunyangZeng/TAPLoss/tree/master/Demucs/denoiser

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 4

  •  
  •  
  •  
  •