Parametric Neural Amp Modeling with Active Learning

ABSTRACT We introduce PANAMA, an active learning framework to train parametric guitar amp models end-to-end using a combination of an LSTM model and a WaveNet-like architecture. With PANAMA, one can create a virtual amp by recording samples that are determined through an ensemble-based active learning strategy to minimize the amount of datapoints needed (i.e., amp knob settings). Our strategy uses gradient-based optimization to maximize the disagreement among ensemble models, in order to identify the most informative dat-apoints. MUSHRA listening tests reveal that, with 75 data-points, our models are able to match the perceptual quality of NAM, the leading open-source non-parametric amp modeler. Index T erms-- neural amp modeling, active learning 1. INTRODUCTION In recent years, data-driven guitar amp modeling has become increasingly popular.