Style-based drum synthesis with GAN inversion

Drysdale, Jake and Tomczak, Maciej and Hockman, Jason (2021) Style-based drum synthesis with GAN inversion. In: International Society of Music Information Retrieval Conference 2021, 8th - 12th November 2021, Online.

[img]
Preview
Text
000041.pdf - Published Version
Available under License Creative Commons Attribution.

Download (1MB)

Abstract

Neural audio synthesizers exploit deep learning as an alternative to traditional synthesizers that generate audio from hand-designed components, such as oscillators and wavetables. For a neural audio synthesizer to be applicable to music creation, meaningful control over the output is essential. This paper provides an overview of an unsupervised approach to deriving useful feature controls learned by a generative model. A system for generation and transformation of drum samples using a style-based generative adversarial network (GAN) is proposed. The system provides functional control of audio style features, based on principal component analysis (PCA) applied to the intermediate latent space. Additionally, we propose the use of an encoder trained to invert input drums back to the latent space of the pre-trained GAN. We experiment with three modes of control and provide audio results on a supporting website.

Item Type: Conference or Workshop Item (Paper)
Dates:
DateEvent
1 September 2021Accepted
8 November 2021Published Online
Subjects: CAH11 - computing > CAH11-01 - computing > CAH11-01-01 - computer science
CAH11 - computing > CAH11-01 - computing > CAH11-01-04 - software engineering
CAH11 - computing > CAH11-01 - computing > CAH11-01-05 - artificial intelligence
CAH25 - design, and creative and performing arts > CAH25-02 - performing arts > CAH25-02-02 - music
Divisions: Faculty of Computing, Engineering and the Built Environment > School of Computing and Digital Technology
Depositing User: Jason Hockman
Date Deposited: 04 Apr 2022 09:17
Last Modified: 22 Mar 2023 12:00
URI: https://www.open-access.bcu.ac.uk/id/eprint/13023

Actions (login required)

View Item View Item

Research

In this section...