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 ).
CITATION STYLE
El Amri, W. Z., Tautz, O., Ritter, H., & Melnik, A. (2022). Transfer Learning with Jukebox for Music Source Separation. In IFIP Advances in Information and Communication Technology (Vol. 647 IFIP, pp. 426–433). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-08337-2_35
Mendeley helps you to discover research relevant for your work.