Parametric Neural Amp Modeling with Active Learning

TL;DR

This paper presents PANAMA, an active learning framework that efficiently trains parametric guitar amp models using minimal data, leveraging gradient-based optimization to select the most informative samples.

Contribution

It introduces a novel active learning approach for training parametric amp models with minimal data using a WaveNet-like architecture.

Findings

Active learning reduces the number of samples needed for training.

Gradient-based algorithms effectively identify optimal data points.

The framework enables virtual amp creation with limited recordings.

Abstract

We introduce PANAMA, an active learning framework for the training of end-to-end parametric guitar amp models using a WaveNet-like architecture. With \model, one can create a virtual amp by recording samples that are determined by an active learning strategy to use a minimum amount of datapoints (i.e., amp knob settings). We show that gradient-based optimization algorithms can be used to determine the optimal datapoints to sample, and that the approach helps under a constrained number of samples.