Real-time black-box modelling with recurrent neural networks

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Researchers

Research units

Abstract

This paper proposes to use a recurrent neural network for black-box modelling of nonlinear audio systems, such as tube amplifiers and distortion pedals. As a recurrent unit structure, we test both Long Short-Term Memory and a Gated Recurrent Unit. We compare the proposed neural network with a WaveNet-style deep neural network, which has been suggested previously for tube amplifier modelling. The neural networks are trained with several minutes of guitar and bass recordings, which have been passed through the devices to be modelled. A real-time audio plugin implementing the proposed networks has been developed in the JUCE framework. It is shown that the recurrent neural networks achieve similar accuracy to the WaveNet model, while requiring significantly less processing power to run. The Long Short-Term Memory recurrent unit is also found to outperform the Gated Recurrent Unit overall. The proposed neural network is an important step forward in computationally efficient yet accurate emulation of tube amplifiers and distortion pedals.

Details

Original languageEnglish
Title of host publicationProceedings of the International Conference on Digital Audio Effects
Publication statusPublished - 2 Sep 2019
MoE publication typeA4 Article in a conference publication
EventInternational Conference on Digital Audio Effects - Birmingham, United Kingdom
Duration: 2 Sep 20196 Sep 2019
Conference number: 22

Publication series

NameProceedings of the International Conference on Digital Audio Effects
ISSN (Print)2414-6382
ISSN (Electronic)2413-6689

Conference

ConferenceInternational Conference on Digital Audio Effects
Abbreviated titleDAFX
CountryUnited Kingdom
CityBirmingham
Period02/09/201906/09/2019

Download statistics

No data available

ID: 36768416