Automatic DJ Transitions with Differentiable Audio Effects and Generative Adversarial Networks
This addresses the challenge for DJs and music producers by automating song transitions, though it is an incremental improvement over existing methods.
The paper tackled the problem of creating seamless transitions between music tracks for DJ mixes by using a generative adversarial network with differentiable audio effects. The model achieved competitive results in a listening test compared to several baselines.
A central task of a Disc Jockey (DJ) is to create a mixset of mu-sic 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. In particular, the generator of the model 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 away that the resulting mix resembles real mixes created by humanDJ, 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.