Transfer Learning with Jukebox for Music Source Separation
Published in Part of the IFIP Advances in Information and Communication Technology book series (IFIPAICT,volume 647), 2022
Recommended citation: Wadhah Zai El Amri, Oliver Tautz, Helge Ritter, Andrew Melnik (2022). "Transfer Learning with Jukebox for Music Source Separation." Part of the IFIP Advances in Information and Communication Technology book series (IFIPAICT,volume 647). https://link.springer.com/chapter/10.1007/978-3-031-08337-2_35
Accepted to the IFIP Advances in Information and Communication Technology book series (IFIPAICT,volume 647).
Authors: Wadhah Zai El Amri, Oliver Tautz, Helge Ritter, Andrew Melnik.
Topics: Machine Learning, Deep Learning, Audio Signal Processing, Transfer Learning.
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)
___________________________________________________________________
Preprint:
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"
}