Adversarial Guitar Amplifier Modelling with Unpaired Data

dc.contributorAalto-yliopistofi
dc.contributorAalto Universityen
dc.contributor.authorWright, Alecen_US
dc.contributor.authorVälimäki, Vesaen_US
dc.contributor.authorJuvela, Laurien_US
dc.contributor.departmentDepartment of Information and Communications Engineeringen
dc.contributor.groupauthorAudio Signal Processingen
dc.contributor.groupauthorSpeech Synthesisen
dc.date.accessioned2023-10-11T09:34:37Z
dc.date.available2023-10-11T09:34:37Z
dc.date.issued2023-06-10en_US
dc.description.abstractWe propose an audio effects processing framework that learns to emulate a target electric guitar tone from a recording. We train a deep neural network using an adversarial approach, with the goal of trans-forming the timbre of a guitar, into the timbre of another guitar after audio effects processing has been applied, for example, by a guitar amplifier. The model training requires no paired data, and the resulting model emulates the target timbre well whilst being capable of real-time processing on a modern personal computer. To verify our approach we present two experiments, one which carries out un-paired training using paired data, allowing us to monitor training via objective metrics, and another that uses fully unpaired data, corresponding to a realistic scenario where a user wants to emulate a guitar timbre only using audio data from a recording. Our listening test results confirm that the models are perceptually convincing.en
dc.description.versionPeer revieweden
dc.format.extent5
dc.format.extent1-5
dc.format.mimetypeapplication/pdfen_US
dc.identifier.citationWright, A, Välimäki, V & Juvela, L 2023, Adversarial Guitar Amplifier Modelling with Unpaired Data . in ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) ., 10094600, Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, IEEE, pp. 1-5, IEEE International Conference on Acoustics, Speech, and Signal Processing, Rhodes Island, Greece, 04/06/2023 . https://doi.org/10.1109/ICASSP49357.2023.10094600en
dc.identifier.doi10.1109/ICASSP49357.2023.10094600en_US
dc.identifier.isbn978-1-7281-6328-4
dc.identifier.otherPURE UUID: 4ea3dbb8-0104-4e06-b8c2-3bf8e75d8e9ben_US
dc.identifier.otherPURE ITEMURL: https://research.aalto.fi/en/publications/4ea3dbb8-0104-4e06-b8c2-3bf8e75d8e9ben_US
dc.identifier.otherPURE LINK: http://www.scopus.com/inward/record.url?scp=85174526791&partnerID=8YFLogxKen_US
dc.identifier.otherPURE FILEURL: https://research.aalto.fi/files/124108653/Wright2023_Adversarial_guitar_amplifier_modelling_with_unpaired_data.pdfen_US
dc.identifier.urihttps://aaltodoc.aalto.fi/handle/123456789/123899
dc.identifier.urnURN:NBN:fi:aalto-202310116245
dc.language.isoenen
dc.relation.ispartofIEEE International Conference on Acoustics, Speech, and Signal Processingen
dc.relation.ispartofseriesICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)en
dc.rightsopenAccessen
dc.subject.keywordTrainingen_US
dc.subject.keywordComputational modelingen_US
dc.subject.keywordNeural networksen_US
dc.subject.keywordData modelsen_US
dc.subject.keywordReal-time systemsen_US
dc.subject.keywordRecordingen_US
dc.subject.keywordTimbreen_US
dc.titleAdversarial Guitar Amplifier Modelling with Unpaired Dataen
dc.typeConference article in proceedingsfi
dc.type.versionacceptedVersion
Files