Guitar tone stack modeling with a neural state-space filter

Tantep Sinjanakhom*, Eero-Pekka Damskägg, Stylianos Mimilakis, Athanasios Gotsopoulos, Vesa Välimäki

*Corresponding author for this work

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

43 Downloads (Pure)

Abstract

In this work, we present a data-driven approach to modeling tone stack circuits in guitar amplifiers and distortion pedals. To this aim, the proposed modeling approach uses a feedforward fully connected neural network to predict the parameters of a coupled-form state-space filter, ensuring the numerical stability of the resulting time-varying system. The neural network is conditioned on the tone controls of the target tone stack and is optimized jointly with the coupled-form state-space filter to match the target frequency response. To assess the proposed approach, we model three popular tone stack schematics with both matched-order and over-parameterized filters and conduct an objective comparison with well-established approaches that use cascaded biquad filters. Results from the conducted experiments demonstrate improved accuracy of the proposed modeling approach, especially in the case of
over-parameterized state-space filters while guaranteeing numerical stability. Our method can be deployed, after training, in real-time audio processors.
Original languageEnglish
Title of host publicationProceedings of the 27th International Conference on Digital Audio Effects (DAFx24)
EditorsE. De Sena, J. Mannall
Place of PublicationGuildford, UK
PublisherUniversity of Surrey
Pages171-176
Number of pages6
Volume27
Edition2024
Publication statusPublished - 3 Sept 2024
MoE publication typeA4 Conference publication
EventInternational Conference on Digital Audio Effects - University of Surrey, Guildford, United Kingdom
Duration: 3 Sept 20247 Sept 2024
Conference number: 27
https://dafx24.surrey.ac.uk/

Publication series

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

Conference

ConferenceInternational Conference on Digital Audio Effects
Abbreviated titleDAFX
Country/TerritoryUnited Kingdom
CityGuildford
Period03/09/202407/09/2024
Internet address

Keywords

  • Audio signal processing
  • analog circuits
  • Digital signal processing
  • Machine learning

Fingerprint

Dive into the research topics of 'Guitar tone stack modeling with a neural state-space filter'. Together they form a unique fingerprint.

Cite this