Automatic DJ Transitions with Differentiable Audio Effects and Generative Adversarial Networks

2021/10/13 by Boyu Chen, Chen, Bo-Yu, Wei‐Han Hsu +9 · 1 citation
Computer Science · #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Music Technology and Sound Studies #Music and Audio Processing #Sound (cs.SD) #Speech and Audio Processing #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2110.06525

openalex publication_date 2021/10/13 · openalex created_date 2022/10/07 · openalex updated_date 2026/07/28

Abstract

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.

Cited by

• Fx-Encoder++: Extracting Instrument-Wise Audio Effects Representations from Mixtures

Related

• Automatic Music Mixing using a Generative Model of Effect Embeddings
• Diff-MST: Differentiable Mixing Style Transfer
• A Computational Analysis of Real-World DJ Mixes using Mix-To-Track Subsequence Alignment
• Automatic music mixing with deep learning and out-of-domain data
• Music Mixing Style Transfer: A Contrastive Learning Approach to Disentangle Audio Effects