Virtual Analog Modeling of Distortion Circuits Using Neural Ordinary Differential Equations

dc.contributorAalto-yliopistofi
dc.contributorAalto Universityen
dc.contributor.authorWilczek, Janen_US
dc.contributor.authorWright, Alecen_US
dc.contributor.authorVälimäki, Vesaen_US
dc.contributor.authorHabets, Emanuël A.P.en_US
dc.contributor.departmentWolfSounden_US
dc.contributor.departmentDept Signal Process and Acousten_US
dc.contributor.departmentFriedrich-Alexander University Erlangen-Nürnbergen_US
dc.contributor.editorEvangelista, Gianpaoloen_US
dc.contributor.editorHolighaus, Nickien_US
dc.date.accessioned2022-10-19T06:41:35Z
dc.date.available2022-10-19T06:41:35Z
dc.date.issued2022en_US
dc.descriptionFunding Information: ∗ This work was supported by a fellowship within the IFI programme of the German Academic Exchange Service (DAAD). † This research is part of the activities of the Nordic Sound and Music Computing Network—NordicSMC (NordForsk project no. 86892). ‡A joint institution of the Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) and Fraunhofer Institute for Integrated Circuits (IIS). Publisher Copyright: Copyright: © 2022 Jan Wilczek et al.
dc.description.abstractRecent research in deep learning has shown that neural networks can learn differential equations governing dynamical systems. In this paper, we adapt this concept to Virtual Analog (VA) modeling to learn the ordinary differential equations (ODEs) governing the first-order and the second-order diode clipper. The proposed models achieve performance comparable to state-of-the-art recurrent neural networks (RNNs) albeit using fewer parameters. We show that this approach does not require oversampling and allows to increase the sampling rate after the training has completed, which results in increased accuracy. Using a sophisticated numerical solver allows to increase the accuracy at the cost of slower processing. ODEs learned this way do not require closed forms but are still physically interpretable.en
dc.description.versionPeer revieweden
dc.format.extent8
dc.format.extent9-16
dc.format.mimetypeapplication/pdfen_US
dc.identifier.citationWilczek , J , Wright , A , Välimäki , V & Habets , E A P 2022 , Virtual Analog Modeling of Distortion Circuits Using Neural Ordinary Differential Equations . in G Evangelista & N Holighaus (eds) , Proceedings of the 25th International Conference on Digital Audio Effects (DAFx20in22) . 2022 edn , 12 , Proceedings of the International Conference on Digital Audio Effects , DAFx , Vienna, Austria , pp. 9-16 , International Conference on Digital Audio Effects , Vienna , Austria , 07/09/2022 . < https://dafx2020.mdw.ac.at/proceedings/papers/DAFx20in22_paper_12.pdf >en
dc.identifier.isbn978-3-200-08599-2
dc.identifier.issn2413-6700
dc.identifier.issn2413-6689
dc.identifier.otherPURE UUID: 0e2d8446-9d9b-4a4a-9ea6-1f4455e9833cen_US
dc.identifier.otherPURE ITEMURL: https://research.aalto.fi/en/publications/0e2d8446-9d9b-4a4a-9ea6-1f4455e9833cen_US
dc.identifier.otherPURE LINK: http://www.scopus.com/inward/record.url?scp=85138773865&partnerID=8YFLogxKen_US
dc.identifier.otherPURE LINK: https://dafx2020.mdw.ac.at/proceedings/papers/DAFx20in22_paper_12.pdfen_US
dc.identifier.otherPURE FILEURL: https://research.aalto.fi/files/89272276/Wilczek_et_alii_VIRTUAL_ANALOG_MODELING_OF_DISTORTION_CIRCUITS_USING_NEURAL_ORDINARY_DIFFERENTIAL_EQUATIONS.pdfen_US
dc.identifier.urihttps://aaltodoc.aalto.fi/handle/123456789/117173
dc.identifier.urnURN:NBN:fi:aalto-202210195961
dc.language.isoenen
dc.relation.ispartofInternational Conference on Digital Audio Effectsen
dc.relation.ispartofseriesProceedings of the 25th International Conference on Digital Audio Effects (DAFx20in22)en
dc.relation.ispartofseriesissue 2022en
dc.relation.ispartofseriesProceedings of the International Conference on Digital Audio Effectsen
dc.rightsopenAccessen
dc.titleVirtual Analog Modeling of Distortion Circuits Using Neural Ordinary Differential Equationsen
dc.typeConference article in proceedingsfi
dc.type.versionpublishedVersion
Files