Transfer Learning with Jukebox for Music Source Separation

11/28/2021
by   Wadhah Zai El Amri, et al.
0

In this work, we demonstrate how to adapt a publicly available pre-trained Jukebox model for the problem of audio source separation from a single mixed audio channel. Our neural network architecture for transfer learning is fast to train and results demonstrate comparable performance to other state-of-the-art approaches. We provide an open-source code implementation of our architecture (https://rebrand.ly/transfer-jukebox-github).

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset