Time-Varying Audio Effect Modeling by End-to-End Adversarial Training

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Bourdin, Yann, Legrand, Pierrick, Roche, Fanny
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909967346302976
author Bourdin, Yann
Legrand, Pierrick
Roche, Fanny
author_facet Bourdin, Yann
Legrand, Pierrick
Roche, Fanny
contents Deep learning has become a standard approach for the modeling of audio effects, yet strictly black-box modeling remains problematic for time-varying systems. Unlike time-invariant effects, training models on devices with internal modulation typically requires the recording or extraction of control signals to ensure the time-alignment required by standard loss functions. This paper introduces a Generative Adversarial Network (GAN) framework to model such effects using only input-output audio recordings, removing the need for modulation signal extraction. We propose a convolutional-recurrent architecture trained via a two-stage strategy: an initial adversarial phase allows the model to learn the distribution of the modulation behavior without strict phase constraints, followed by a supervised fine-tuning phase where a State Prediction Network (SPN) estimates the initial internal states required to synchronize the model with the target. Additionally, a new objective metric based on chirp-train signals is developed to quantify modulation accuracy. Experiments modeling a vintage hardware phaser demonstrate the method's ability to capture time-varying dynamics in a fully black-box context.
format Preprint
id arxiv_https___arxiv_org_abs_2512_15313
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Time-Varying Audio Effect Modeling by End-to-End Adversarial Training
Bourdin, Yann
Legrand, Pierrick
Roche, Fanny
Sound
Machine Learning
Deep learning has become a standard approach for the modeling of audio effects, yet strictly black-box modeling remains problematic for time-varying systems. Unlike time-invariant effects, training models on devices with internal modulation typically requires the recording or extraction of control signals to ensure the time-alignment required by standard loss functions. This paper introduces a Generative Adversarial Network (GAN) framework to model such effects using only input-output audio recordings, removing the need for modulation signal extraction. We propose a convolutional-recurrent architecture trained via a two-stage strategy: an initial adversarial phase allows the model to learn the distribution of the modulation behavior without strict phase constraints, followed by a supervised fine-tuning phase where a State Prediction Network (SPN) estimates the initial internal states required to synchronize the model with the target. Additionally, a new objective metric based on chirp-train signals is developed to quantify modulation accuracy. Experiments modeling a vintage hardware phaser demonstrate the method's ability to capture time-varying dynamics in a fully black-box context.
title Time-Varying Audio Effect Modeling by End-to-End Adversarial Training
topic Sound
Machine Learning
url https://arxiv.org/abs/2512.15313