Neural Proxies for Sound Synthesizers: Learning Perceptually Informed Preset Representations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Combes, Paolo, Weinzierl, Stefan, Obermayer, Klaus
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912578489286656
author Combes, Paolo
Weinzierl, Stefan
Obermayer, Klaus
author_facet Combes, Paolo
Weinzierl, Stefan
Obermayer, Klaus
contents Deep learning appears as an appealing solution for Automatic Synthesizer Programming (ASP), which aims to assist musicians and sound designers in programming sound synthesizers. However, integrating software synthesizers into training pipelines is challenging due to their potential non-differentiability. This work tackles this challenge by introducing a method to approximate arbitrary synthesizers. Specifically, we train a neural network to map synthesizer presets onto an audio embedding space derived from a pretrained model. This facilitates the definition of a neural proxy that produces compact yet effective representations, thereby enabling the integration of audio embedding loss into neural-based ASP systems for black-box synthesizers. We evaluate the representations derived by various pretrained audio models in the context of neural-based nASP and assess the effectiveness of several neural network architectures, including feedforward, recurrent, and transformer-based models, in defining neural proxies. We evaluate the proposed method using both synthetic and hand-crafted presets from three popular software synthesizers and assess its performance in a synthesizer sound matching downstream task. While the benefits of the learned representation are nuanced by resource requirements, encouraging results were obtained for all synthesizers, paving the way for future research into the application of synthesizer proxies for neural-based ASP systems.
format Preprint
id arxiv_https___arxiv_org_abs_2509_07635
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Neural Proxies for Sound Synthesizers: Learning Perceptually Informed Preset Representations
Combes, Paolo
Weinzierl, Stefan
Obermayer, Klaus
Sound
Machine Learning
Audio and Speech Processing
68T07
H.5.5; J.5; I.5.4
Deep learning appears as an appealing solution for Automatic Synthesizer Programming (ASP), which aims to assist musicians and sound designers in programming sound synthesizers. However, integrating software synthesizers into training pipelines is challenging due to their potential non-differentiability. This work tackles this challenge by introducing a method to approximate arbitrary synthesizers. Specifically, we train a neural network to map synthesizer presets onto an audio embedding space derived from a pretrained model. This facilitates the definition of a neural proxy that produces compact yet effective representations, thereby enabling the integration of audio embedding loss into neural-based ASP systems for black-box synthesizers. We evaluate the representations derived by various pretrained audio models in the context of neural-based nASP and assess the effectiveness of several neural network architectures, including feedforward, recurrent, and transformer-based models, in defining neural proxies. We evaluate the proposed method using both synthetic and hand-crafted presets from three popular software synthesizers and assess its performance in a synthesizer sound matching downstream task. While the benefits of the learned representation are nuanced by resource requirements, encouraging results were obtained for all synthesizers, paving the way for future research into the application of synthesizer proxies for neural-based ASP systems.
title Neural Proxies for Sound Synthesizers: Learning Perceptually Informed Preset Representations
topic Sound
Machine Learning
Audio and Speech Processing
68T07
H.5.5; J.5; I.5.4
url https://arxiv.org/abs/2509.07635