Differentiable All-pole Filters for Time-varying Audio Systems

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yu, Chin-Yun, Mitcheltree, Christopher, Carson, Alistair, Bilbao, Stefan, Reiss, Joshua D., Fazekas, György
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912076396494848
author Yu, Chin-Yun
Mitcheltree, Christopher
Carson, Alistair
Bilbao, Stefan
Reiss, Joshua D.
Fazekas, György
author_facet Yu, Chin-Yun
Mitcheltree, Christopher
Carson, Alistair
Bilbao, Stefan
Reiss, Joshua D.
Fazekas, György
contents Infinite impulse response filters are an essential building block of many time-varying audio systems, such as audio effects and synthesisers. However, their recursive structure impedes end-to-end training of these systems using automatic differentiation. Although non-recursive filter approximations like frequency sampling and frame-based processing have been proposed and widely used in previous works, they cannot accurately reflect the gradient of the original system. We alleviate this difficulty by re-expressing a time-varying all-pole filter to backpropagate the gradients through itself, so the filter implementation is not bound to the technical limitations of automatic differentiation frameworks. This implementation can be employed within audio systems containing filters with poles for efficient gradient evaluation. We demonstrate its training efficiency and expressive capabilities for modelling real-world dynamic audio systems on a phaser, time-varying subtractive synthesiser, and compressor. We make our code and audio samples available and provide the trained audio effect and synth models in a VST plugin at https://diffapf.github.io/web/.
format Preprint
id arxiv_https___arxiv_org_abs_2404_07970
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Differentiable All-pole Filters for Time-varying Audio Systems
Yu, Chin-Yun
Mitcheltree, Christopher
Carson, Alistair
Bilbao, Stefan
Reiss, Joshua D.
Fazekas, György
Audio and Speech Processing
Machine Learning
Sound
Infinite impulse response filters are an essential building block of many time-varying audio systems, such as audio effects and synthesisers. However, their recursive structure impedes end-to-end training of these systems using automatic differentiation. Although non-recursive filter approximations like frequency sampling and frame-based processing have been proposed and widely used in previous works, they cannot accurately reflect the gradient of the original system. We alleviate this difficulty by re-expressing a time-varying all-pole filter to backpropagate the gradients through itself, so the filter implementation is not bound to the technical limitations of automatic differentiation frameworks. This implementation can be employed within audio systems containing filters with poles for efficient gradient evaluation. We demonstrate its training efficiency and expressive capabilities for modelling real-world dynamic audio systems on a phaser, time-varying subtractive synthesiser, and compressor. We make our code and audio samples available and provide the trained audio effect and synth models in a VST plugin at https://diffapf.github.io/web/.
title Differentiable All-pole Filters for Time-varying Audio Systems
topic Audio and Speech Processing
Machine Learning
Sound
url https://arxiv.org/abs/2404.07970