End-to-end Music Remastering System Using Self-supervised and Adversarial Training

TL;DR

This paper introduces an end-to-end music remastering system that uses self-supervised and adversarial training to transform the mastering style of songs, reducing reliance on expert engineers.

Contribution

It presents a novel self-supervised learning approach combined with adversarial training for music remastering, enabling style transfer without extensive labeled data.

Findings

Generated audio closely matches target mastering style

Quantitative metrics show improved style similarity

Subjective listening confirms realistic remastering quality

Abstract

Mastering is an essential step in music production, but it is also a challenging task that has to go through the hands of experienced audio engineers, where they adjust tone, space, and volume of a song. Remastering follows the same technical process, in which the context lies in mastering a song for the times. As these tasks have high entry barriers, we aim to lower the barriers by proposing an end-to-end music remastering system that transforms the mastering style of input audio to that of the target. The system is trained in a self-supervised manner, in which released pop songs were used for training. We also anticipated the model to generate realistic audio reflecting the reference's mastering style by applying a pre-trained encoder and a projection discriminator. We validate our results with quantitative metrics and a subjective listening test and show that the model generated samples of mastering style similar to the target.