KUIELab-MDX-Net: A Two-Stream Neural Network for Music Demixing

TL;DR

KUIELab-MDX-Net is a two-stream neural network for music demixing that balances high separation performance with reduced computational resource requirements, combining time-frequency and time-domain approaches.

Contribution

It introduces a novel two-stream architecture that effectively blends time-frequency and time-domain methods for music source separation, achieving competitive results with fewer resources.

Findings

Achieved second place on leaderboard A in the Music Demixing Challenge 2021.

Achieved third place on leaderboard B in the same challenge.

Performed well on MUSDB18 benchmark with efficient resource use.

Abstract

Recently, many methods based on deep learning have been proposed for music source separation. Some state-of-the-art methods have shown that stacking many layers with many skip connections improve the SDR performance. Although such a deep and complex architecture shows outstanding performance, it usually requires numerous computing resources and time for training and evaluation. This paper proposes a two-stream neural network for music demixing, called KUIELab-MDX-Net, which shows a good balance of performance and required resources. The proposed model has a time-frequency branch and a time-domain branch, where each branch separates stems, respectively. It blends results from two streams to generate the final estimation. KUIELab-MDX-Net took second place on leaderboard A and third place on leaderboard B in the Music Demixing Challenge at ISMIR 2021. This paper also summarizes experimental results on another benchmark, MUSDB18. Our source code is available online.