Differentiable Modelling of Percussive Audio with Transient and Spectral Synthesis
dc.contributor.author | Shier, J | en_US |
dc.contributor.author | Caspe, F | en_US |
dc.contributor.author | Robertson, A | en_US |
dc.contributor.author | Sandler, M | en_US |
dc.contributor.author | Mcpherson, A | en_US |
dc.contributor.author | Saitis, C | en_US |
dc.contributor.author | Forum Acusticum | en_US |
dc.date.accessioned | 2023-09-08T11:09:27Z | |
dc.date.available | 2023-06-07 | en_US |
dc.identifier.uri | https://qmro.qmul.ac.uk/xmlui/handle/123456789/90592 | |
dc.description.abstract | Differentiable digital signal processing (DDSP) techniques, including methods for audio synthesis, have gained attention in recent years and lend themselves to interpretability in the parameter space. However, current differentiable synthesis methods have not explicitly sought to model the transient portion of signals, which is important for percussive sounds. In this work, we present a unified synthesis framework aiming to address transient generation and percussive synthesis within a DDSP framework. To this end, we propose a model for percussive synthesis that builds on sinusoidal modeling synthesis and incorporates a modulated temporal convolutional network for transient generation. We use a modified sinusoidal peak picking algorithm to generate time-varying non-harmonic sinusoids and pair it with differentiable noise and transient encoders that are jointly trained to reconstruct drumset sounds. We compute a set of reconstruction metrics using a large dataset of acoustic and electronic percussion samples that show that our method leads to improved onset signal reconstruction for membranophone percussion instruments. | en_US |
dc.rights | This item is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. | |
dc.rights | Attribution 3.0 United States | * |
dc.rights.uri | http://creativecommons.org/licenses/by/3.0/us/ | * |
dc.subject | Drum Synthesis | en_US |
dc.subject | Differentiable DSP | en_US |
dc.subject | Neural Networks | en_US |
dc.title | Differentiable Modelling of Percussive Audio with Transient and Spectral Synthesis | en_US |
dc.type | Conference Proceeding | |
dc.rights.holder | © 2023 The Author(s). | |
pubs.author-url | https://jordieshier.com/ | en_US |
pubs.notes | Not known | en_US |
pubs.publication-status | Accepted | en_US |
dcterms.dateAccepted | 2023-06-07 | en_US |
rioxxterms.funder | Default funder | en_US |
rioxxterms.identifier.project | Default project | en_US |
qmul.funder | UKRI Centre for Doctoral Training in Artificial Intelligence and Music::Engineering and Physical Sciences Research Council | en_US |
qmul.funder | UKRI Centre for Doctoral Training in Artificial Intelligence and Music::Engineering and Physical Sciences Research Council | en_US |
Files in this item
This item appears in the following Collection(s)
Except where otherwise noted, this item's license is described as This item is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.