Comparative Study of State-based Neural Networks for Virtual Analog Audio Effects Modeling

TL;DR

This study compares different neural network architectures for virtual analog audio effects modeling, focusing on their ability to emulate various effects with dynamic parameters and low latency, highlighting strengths and limitations of each approach.

Contribution

It introduces a comprehensive comparison of State-Space, Linear Recurrent Units, and LSTM networks for audio effects modeling, incorporating parameter influence via Feature-wise Linear Modulation.

Findings

LSTM networks excel at emulating distortions and equalizers.

Encoder-decoder LSTM and State-Space models are effective for saturation and compression.

No model effectively emulates low-pass filters; Linear Recurrent Units show inconsistent performance.

Abstract

Artificial neural networks are a promising technique for virtual analog modeling, having shown particular success in emulating distortion circuits. Despite their potential, enhancements are needed to enable effect parameters to influence the network's response and to achieve a low-latency output. While hybrid solutions, which incorporate both analytical and black-box techniques, offer certain advantages, black-box approaches, such as neural networks, can be preferable in contexts where rapid deployment, simplicity, or adaptability are required, and where understanding the internal mechanisms of the system is less critical. In this article, we explore the application of recent machine learning advancements for virtual analog modeling. We compare State-Space models and Linear Recurrent Units against the more common LSTM networks, with a variety of audio effects. We evaluate the performance and limitations of these models using multiple metrics, providing insights for future research and development. Our metrics aim to assess the models' ability to accurately replicate the signal's energy and frequency contents, with a particular focus on transients. The Feature-wise Linear Modulation method is employed to incorporate effect parameters that influence the network's response, enabling dynamic adaptability based on specified conditions. Experimental results suggest that LSTM networks offer an advantage in emulating distortions and equalizers, although performance differences are sometimes subtle yet statistically significant. On the other hand, encoder-decoder configurations of Long Short-Term Memory networks and State-Space models excel in modeling saturation and compression, effectively managing the dynamic aspects inherent in these effects. However, no models effectively emulate the low-pass filter, and Linear Recurrent Units show inconsistent performance across various audio effects.