DiffMoog: a Differentiable Modular Synthesizer for Sound Matching

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Uzrad, Noy, Barkan, Oren, Elharar, Almog, Shvartzman, Shlomi, Laufer, Moshe, Wolf, Lior, Koenigstein, Noam
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913205430779904
author Uzrad, Noy
Barkan, Oren
Elharar, Almog
Shvartzman, Shlomi
Laufer, Moshe
Wolf, Lior
Koenigstein, Noam
author_facet Uzrad, Noy
Barkan, Oren
Elharar, Almog
Shvartzman, Shlomi
Laufer, Moshe
Wolf, Lior
Koenigstein, Noam
contents This paper presents DiffMoog - a differentiable modular synthesizer with a comprehensive set of modules typically found in commercial instruments. Being differentiable, it allows integration into neural networks, enabling automated sound matching, to replicate a given audio input. Notably, DiffMoog facilitates modulation capabilities (FM/AM), low-frequency oscillators (LFOs), filters, envelope shapers, and the ability for users to create custom signal chains. We introduce an open-source platform that comprises DiffMoog and an end-to-end sound matching framework. This framework utilizes a novel signal-chain loss and an encoder network that self-programs its outputs to predict DiffMoogs parameters based on the user-defined modular architecture. Moreover, we provide insights and lessons learned towards sound matching using differentiable synthesis. Combining robust sound capabilities with a holistic platform, DiffMoog stands as a premier asset for expediting research in audio synthesis and machine learning.
format Preprint
id arxiv_https___arxiv_org_abs_2401_12570
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DiffMoog: a Differentiable Modular Synthesizer for Sound Matching
Uzrad, Noy
Barkan, Oren
Elharar, Almog
Shvartzman, Shlomi
Laufer, Moshe
Wolf, Lior
Koenigstein, Noam
Audio and Speech Processing
Artificial Intelligence
Sound
This paper presents DiffMoog - a differentiable modular synthesizer with a comprehensive set of modules typically found in commercial instruments. Being differentiable, it allows integration into neural networks, enabling automated sound matching, to replicate a given audio input. Notably, DiffMoog facilitates modulation capabilities (FM/AM), low-frequency oscillators (LFOs), filters, envelope shapers, and the ability for users to create custom signal chains. We introduce an open-source platform that comprises DiffMoog and an end-to-end sound matching framework. This framework utilizes a novel signal-chain loss and an encoder network that self-programs its outputs to predict DiffMoogs parameters based on the user-defined modular architecture. Moreover, we provide insights and lessons learned towards sound matching using differentiable synthesis. Combining robust sound capabilities with a holistic platform, DiffMoog stands as a premier asset for expediting research in audio synthesis and machine learning.
title DiffMoog: a Differentiable Modular Synthesizer for Sound Matching
topic Audio and Speech Processing
Artificial Intelligence
Sound
url https://arxiv.org/abs/2401.12570