https://github.com/csteinmetz1/steerable-nafx

Steerable discovery of neural audio effects
https://github.com/csteinmetz1/steerable-nafx

audio-processing neural-audio-effects

Last synced: 17 days ago
JSON representation

Steerable discovery of neural audio effects

• Host: GitHub
• URL: https://github.com/csteinmetz1/steerable-nafx
• Owner: csteinmetz1
• License: apache-2.0
• Created: 2021-09-11T15:31:06.000Z (about 3 years ago)
• Default Branch: main
• Last Pushed: 2022-03-02T12:14:05.000Z (over 2 years ago)
• Last Synced: 2024-08-01T02:35:09.958Z (3 months ago)
• Topics: audio-processing, neural-audio-effects
• Language: Jupyter Notebook
• Homepage: https://csteinmetz1.github.io/steerable-nafx
• Size: 27.1 MB
• Stars: 201
• Watchers: 8
• Forks: 17
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        


# Steerable discovery of neural audio effects 

[Christian J. Steinmetz](https://www.christiansteinmetz.com/)  and  [Joshua D. Reiss](http://www.eecs.qmul.ac.uk/~josh/)

 [![arXiv](https://img.shields.io/badge/arXiv-2112.02926-b31b1b.svg)](https://arxiv.org/abs/2112.02926)  [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/csteinmetz1/steerable-nafx/blob/master/steerable-nafx.ipynb)  [![Demo](https://img.shields.io/badge/Web-Demo-blue)](https://csteinmetz1.github.io/steerable-nafx)

 [![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/akhaliq/steerable-nafx)








## Abstract

Applications of deep learning for audio effects often focus on modeling analog effects or learning to control effects to emulate a trained audio engineer. 

However, deep learning approaches also have the potential to expand creativity through neural audio effects that enable new sound transformations. 

While recent work demonstrated that neural networks with random weights produce compelling audio effects, control of these effects is limited and unintuitive.

To address this, we introduce a method for the steerable discovery of neural audio effects.

This method enables the design of effects using example recordings provided by the user. 

We demonstrate how this method produces an effect similar to the target effect, along with interesting inaccuracies, while also providing perceptually relevant controls.









 

Watch the demo video.



## Citation

If you use steerable-nafx in your work please consider citing us.

```

@inproceedings{steinmetz2021steerable,

        title={Steerable discovery of neural audio effects},

        author={Steinmetz, Christian J. and Reiss, Joshua D.},

        booktitle={5th Workshop on Creativity and Design at NeurIPS},

        year={2021}}

```

* Accepted to the [NeurIPS 2021 Workshop for Machine Learning for Creativity and Design](https://neuripscreativityworkshop.github.io/2021/)