Coder Social home page Coder Social logo

dnp's Introduction

DNP

Audio Denoising with Deep Network Priors

This repository provides a PyTorch implementation of "Audio Denoising with Deep Network Priors" (paper)

The method trains on noisy audio signal and provides a the clean underlying signal. Comparison with traditional unsupervised methods can be found here

The method is completely unsupervised and only trains on the specific audio clip that is being denoised.

The algorithm is based on the observation that modeling noise in the signal is harder than a clean signal. During the fitting we observe flactuations in different stages of the train. By calculating the amount of difference between outputs in the time-frequency domain we create a robust spectral mask used for denoising the noisy output. Accumulator

Dependencies

A conda environment file is available in the repository.

  • Python 3.6 +
  • Pytorch 1.0
  • Torchvision
  • librosa
  • tqdm
  • scipy
  • soundfile

Usage

1. Cloning the repository & setting up conda environment

$ git clone https://github.com/mosheman5/DNP.git
$ cd DNP/

For creating and activating the conda environment:

$ conda env create -f environment.yml
$ conda activate DNP

2. Testing

To test on the demo speech file:

$ python DNP.py --run_name demo --noisy_file demo.wav --samples_dir samples --save_every 50 --num_iter 5000 --LR 0.001

To test on any other audio file insert the file path after the --noisy_file option.

A jupyter notebook with visualization is available: dnp.ipynb

Reference

If you found this code useful, please cite the following paper:

@article{michelashvili2019DNP,
  title={Audio Denoising with Deep Network Priors},
  author={Michael Michelashvili and Lior Wolf},
  journal={arXiv preprint arXiv:1904.07612},
  year={2019}
}

Acknowledgement

The implemantation of the network architecture is taken from Wave-U-Net

dnp's People

Contributors

mosheman5 avatar

Watchers

 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.