Steerable discovery of neural audio effects fork

This is a fork of the Steerable discovery of neural audio effects repository with the following changes:

• A Tensorflow implementation of the same neural network has been created.
• Changes to the original Pytorch version have been implemented (export to libtorch and onnx, removing film layer, code refactoring/simplification).

All changes are subject to the MIT license.

Steerable discovery of neural audio effects

Christian J. Steinmetz and Joshua D. Reiss

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