Physical Modeling Using Recurrent Neural Networks with Fast Convolutional Layers

Loading...
Thumbnail Image

Access rights

openAccess

URL

Journal Title

Journal ISSN

Volume Title

A4 Artikkeli konferenssijulkaisussa

Date

2022

Major/Subject

Mcode

Degree programme

Language

en

Pages

8
138-145

Series

Proceedings of the 25th International Conference on Digital Audio Effects (DAFx20in22), Proceedings of the International Conference on Digital Audio Effects

Abstract

Discrete-time modeling of acoustic, mechanical and electrical systems is a prominent topic in the musical signal processing literature. Such models are mostly derived by discretizing a mathematical model, given in terms of ordinary or partial differential equations, using established techniques. Recent work has applied the techniques of machine-learning to construct such models automatically from data for the case of systems which have lumped states described by scalar values, such as electrical circuits. In this work, we examine how similar techniques are able to construct models of systems which have spatially distributed rather than lumped states. We describe several novel recurrent neural network structures, and show how they can be thought of as an extension of modal techniques. As a proof of concept, we generate synthetic data for three physical systems and show that the proposed network structures can be trained with this data to reproduce the behavior of these systems.

Description

Keywords

Other note

Citation

Schlecht, S, Parker, J, Schäfer, M & Rabenstein, R 2022, Physical Modeling Using Recurrent Neural Networks with Fast Convolutional Layers . in Proceedings of the 25th International Conference on Digital Audio Effects (DAFx20in22) . Proceedings of the International Conference on Digital Audio Effects, DAFx, pp. 138-145, International Conference on Digital Audio Effects, Vienna, Austria, 07/09/2022 . < https://dafx2020.mdw.ac.at/proceedings/papers/DAFx20in22_paper_38.pdf >