AUTOMATIC DJ TRANSITIONS WITH DIFFERENTIABLE AUDIO EFFECTS AND GENERATIVE ADVERSARIAL NETWORKS
Journal
ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Journal Volume
2022-May
ISBN
9781665405409
Date Issued
2022-01-01
Author(s)
Abstract
A central task of a Disc Jockey (DJ) is to create a mixset of music with seamless transitions between adjacent tracks. In this paper, we explore a data-driven approach that uses a generative adversarial network to create the song transition by learning from real-world DJ mixes. The generator uses two differentiable digital signal processing components, an equalizer (EQ) and a fader, to mix two tracks selected by a data generation pipeline. The generator has to set the parameters of the EQs and fader in such a way that the resulting mix resembles real mixes created by human DJ, as judged by the discriminator counterpart. Result of a listening test shows that the model can achieve competitive results compared with a number of baselines.
Subjects
audio effects | deep learning | differentiable signal processing | DJ mix | generative adversarial network
Type
conference paper