A Differentiable Neural Network Approach To Parameter Estimation Of Reverberation

Søren Vøgg Lyster, Cumhur Erkut

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

122 Downloads (Pure)


Differentiable Digital Signal Processing is a library and set of machine learning tools that disentangle the loudness and pitch of an audio signal for timbre transfer or for applying digital audio effects. This paper presents a DDSP-based neural network that incorporates a feedback delay network plugin written in JUCE in an audio processing layer, with the purpose of tuning a large set of reverberator parameters to emulate the reverb of a target audio signal. We first describe the implementation of the proposed network, together with its multiscale loss. We then report two experiments that try to tune the reverberator plugin: a "dark" reverb where the filters are set to cut frequencies in the middle and high range, and a "brighter", more metallic sounding reverb with less damping. We conclude with the observations about advantages and shortcomings of the neural network.

TitelProceedings of the 19th Sound and Music Computing Conference, June 5-12th, 2022, Saint-Étienne (France) : SMC/JIM/IFC 2022
RedaktørerRomain Michon, Laurent Pottier, Yann Orlarey
Antal sider7
ForlagSound and Music Computing Network
ISBN (Elektronisk)978-2-9584126-0-9
StatusUdgivet - 2022
Begivenhed19th Sound and Music Computing Conference, SMC 2022 - Saint-Etienne, Frankrig
Varighed: 5 jun. 202212 jun. 2022


Konference19th Sound and Music Computing Conference, SMC 2022
NavnProceedings of the Sound and Music Computing Conference

Bibliografisk note

Publisher Copyright:
Copyright: © 2022 Søren Vøgg Lyster et al.


Dyk ned i forskningsemnerne om 'A Differentiable Neural Network Approach To Parameter Estimation Of Reverberation'. Sammen danner de et unikt fingeraftryk.