A Conditioned UNet for Music Source Separation

TL;DR

This paper introduces QSCNet, a conditioned UNet model for music source separation that outperforms previous methods like Banquet, especially in terms of SNR and parameter efficiency, enabling more flexible separation tasks.

Contribution

The paper presents QSCNet, a novel conditioned UNet architecture for music source separation, demonstrating its superiority over existing methods like Banquet in performance and efficiency.

Findings

QSCNet outperforms Banquet by over 1dB SNR.

QSCNet uses less than half the parameters of Banquet.

Conditioned UNets are effective for flexible music source separation.

Abstract

In this paper we propose a conditioned UNet for Music Source Separation (MSS). MSS is generally performed by multi-output neural networks, typically UNets, with each output representing a particular stem from a predefined instrument vocabulary. In contrast, conditioned MSS networks accept an audio query related to a stem of interest alongside the signal from which that stem is to be extracted. Thus, a strict vocabulary is not required and this enables more realistic tasks in MSS. The potential of conditioned approaches for such tasks has been somewhat hidden due to a lack of suitable data, an issue recently addressed with the MoisesDb dataset. A recent method, Banquet, employs this dataset with promising results seen on larger vocabularies. Banquet uses Bandsplit RNN rather than a UNet and the authors state that UNets should not be suitable for conditioned MSS. We counter this argument and propose QSCNet, a novel conditioned UNet for MSS that integrates network conditioning elements in the Sparse Compressed Network for MSS. We find QSCNet to outperform Banquet by over 1dB SNR on a couple of MSS tasks, while using less than half the number of parameters.