DrumGAN VST: A Plugin for Drum Sound Analysis/Synthesis With Autoencoding Generative Adversarial Networks

TL;DR

DrumGAN VST is a deep learning-based plugin that synthesizes and manipulates drum sounds by encoding and generating audio through a GAN, simplifying sound design in music production.

Contribution

The paper introduces DrumGAN VST, a novel plugin that uses a GAN with an encoding network for high-level control and resynthesis of drum sounds in real-time.

Findings

Operates at 44.1 kHz sample rate

Provides independent, continuous control over instrument classes

Enables resynthesis and manipulation of existing sounds

Abstract

In contemporary popular music production, drum sound design is commonly performed by cumbersome browsing and processing of pre-recorded samples in sound libraries. One can also use specialized synthesis hardware, typically controlled through low-level, musically meaningless parameters. Today, the field of Deep Learning offers methods to control the synthesis process via learned high-level features and allows generating a wide variety of sounds. In this paper, we present DrumGAN VST, a plugin for synthesizing drum sounds using a Generative Adversarial Network. DrumGAN VST operates on 44.1 kHz sample-rate audio, offers independent and continuous instrument class controls, and features an encoding neural network that maps sounds into the GAN's latent space, enabling resynthesis and manipulation of pre-existing drum sounds. We provide numerous sound examples and a demo of the proposed VST plugin.