# Transfer Learning with Jukebox for Music Source Separation

arXiv: https://arxiv.org/abs/2111.14200 · HTML: https://mlsanity.com/paper/2111.14200/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 19 references that are in the map.
- First posted on arXiv 28 Nov 2021.

## Builds on (most cited first, 10 of 10)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Jukebox: A Generative Model for Music](https://mlsanity.com/paper/2005.00341/) (2020)
- [Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separation](https://mlsanity.com/paper/1806.03185/) (2018)
- [Towards Learning a Universal Non-Semantic Representation of Speech](https://mlsanity.com/paper/2002.12764/) (2020)
- [Demucs: Deep Extractor for Music Sources with extra unlabeled data remixed](https://mlsanity.com/paper/1909.01174/) (2019)
- [Music Demixing Challenge 2021](https://mlsanity.com/paper/2108.13559/) (2021)
- [All for One and One for All: Improving Music Separation by Bridging Networks](https://mlsanity.com/paper/2010.04228/) (2020)
- [Critic Guided Segmentation of Rewarding Objects in First-Person Views](https://mlsanity.com/paper/2107.09540/) (2021)

## Built on by (most cited first, 4 of 4)

- [MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training](https://mlsanity.com/paper/2306.00107/) (2023)
- [MARBLE: Music Audio Representation Benchmark for Universal Evaluation](https://mlsanity.com/paper/2306.10548/) (2023)
- [Zero-Shot Duet Singing Voices Separation with Diffusion Models](https://mlsanity.com/paper/2311.07345/) (2023)
- [Shape complexity estimation using VAE](https://mlsanity.com/paper/2304.02766/) (2023)

## Abstract (arXiv)

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)