Demo of Zero-Shot Guitar Amplifier Modelling: Enhancing Modeling with Hyper Neural Networks

TL;DR

This paper introduces a hypernetwork-based neural model for zero-shot guitar amplifier tone modeling, enabling versatile and real-time audio synthesis without specific training data for each amplifier.

Contribution

It proposes a novel hypernetwork-conditioned GCN approach that extends tone modeling capabilities to unseen amplifier tones in real-time applications.

Findings

Achieves broader tone coverage than traditional models

Demonstrates real-time performance with a plugin interface

Outperforms existing methods in tone versatility

Abstract

Electric guitar tone modeling typically focuses on the non-linear transformation from clean to amplifier-rendered audio. Traditional methods rely on one-to-one mappings, incorporating device parameters into neural models to replicate specific amplifiers. However, these methods are limited by the need for specific training data. In this paper, we adapt a model based on the previous work, which leverages a tone embedding encoder and a feature wise linear modulation (FiLM) condition method. In this work, we altered conditioning method using a hypernetwork-based gated convolutional network (GCN) to generate audio that blends clean input with the tone characteristics of reference audio. By extending the training data to cover a wider variety of amplifier tones, our model is able to capture a broader range of tones. Additionally, we developed a real-time plugin to demonstrate the system's practical application, allowing users to experience its performance interactively. Our results indicate that the proposed system achieves superior tone modeling versatility compared to traditional methods.