Abstract

In this work, we demonstrate how a publicly available, pretrained Jukebox model can be adapted for the problem of audio source separation from a single mixed audio channel. Our neural network architecture, which is using transfer learning, is quick to train and the results demonstrate performance comparable to other state-of-the-art approaches that require a lot more compute resources, training data, and time. We provide an open-source code implementation of our architecture (https://github.com/wzaielamri/unmix)

Resources

  • Code Our code is published online, along with all necessary checkpoints and a detailed installation guide.

Citation

@InProceedings{zai2022unmix,
author="{Zai El Amri}, Wadhah
and Tautz, Oliver
and Ritter, Helge
and Melnik, Andrew",
title="Transfer Learning with Jukebox for Music Source Separation",
booktitle="Artificial Intelligence Applications and Innovations",
year="2022",
publisher="Springer International Publishing",
pages="426--433",
isbn="978-3-031-08337-2"
}