Sample Rate Independent Recurrent Neural Networks for Audio Effects Processing

TL;DR

This paper explores methods to modify recurrent neural networks for audio effects to operate reliably across different sample rates, introducing novel techniques for sample rate independence and demonstrating their effectiveness.

Contribution

It proposes new methods for making RNN-based audio models sample rate independent, including delay-based and interpolation techniques, with comprehensive evaluation.

Findings

Delay-based approach achieves high fidelity sample rate conversion

Cubic Lagrange interpolation significantly improves non-integer sample rate adjustment

First in-depth study on sample rate independence in RNN audio models

Abstract

In recent years, machine learning approaches to modelling guitar amplifiers and effects pedals have been widely investigated and have become standard practice in some consumer products. In particular, recurrent neural networks (RNNs) are a popular choice for modelling non-linear devices such as vacuum tube amplifiers and distortion circuitry. One limitation of such models is that they are trained on audio at a specific sample rate and therefore give unreliable results when operating at another rate. Here, we investigate several methods of modifying RNN structures to make them approximately sample rate independent, with a focus on oversampling. In the case of integer oversampling, we demonstrate that a previously proposed delay-based approach provides high fidelity sample rate conversion whilst additionally reducing aliasing. For non-integer sample rate adjustment, we propose two novel methods and show that one of these, based on cubic Lagrange interpolation of a delay-line, provides a significant improvement over existing methods. To our knowledge, this work provides the first in-depth study into this problem.