Evaluating Neural Networks Architectures for Spring Reverb Modelling

TL;DR

This paper compares five neural network architectures to evaluate their effectiveness in digitally modeling the nonlinear characteristics of spring reverb, a key spatial audio effect, across different datasets and sampling rates.

Contribution

It introduces a comparative analysis of neural network models for spring reverb emulation, focusing on parametric control and advancing black-box modelling techniques.

Findings

Recurrent and convolutional models show varying effectiveness in reverb replication.

Higher sampling rates improve model accuracy.

Neural networks can effectively emulate nonlinear spring reverb characteristics.

Abstract

Reverberation is a key element in spatial audio perception, historically achieved with the use of analogue devices, such as plate and spring reverb, and in the last decades with digital signal processing techniques that have allowed different approaches for Virtual Analogue Modelling (VAM). The electromechanical functioning of the spring reverb makes it a nonlinear system that is difficult to fully emulate in the digital domain with white-box modelling techniques. In this study, we compare five different neural network architectures, including convolutional and recurrent models, to assess their effectiveness in replicating the characteristics of this audio effect. The evaluation is conducted on two datasets at sampling rates of 16 kHz and 48 kHz. This paper specifically focuses on neural audio architectures that offer parametric control, aiming to advance the boundaries of current black-box modelling techniques in the domain of spring reverberation.