Transfer Learning with Jukebox for Music Source Separation
Audio and Speech Processing
2022-09-22 v3 Machine Learning
Sound
Abstract
In this work, we demonstrate how a publicly available, pre-trained 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)
Keywords
Cite
@article{arxiv.2111.14200,
title = {Transfer Learning with Jukebox for Music Source Separation},
author = {W. Zai El Amri and O. Tautz and H. Ritter and A. Melnik},
journal= {arXiv preprint arXiv:2111.14200},
year = {2022}
}
Comments
Conference paper (AIAI 2022), 4 pages, 2 figures, 2 tables