Slimmable NAM: Neural Amp Models with adjustable runtime computational cost

Steven Atkinson

Keywords: Supervised learning, real-time audio, digital signal processing, adaptive computation

TL;DR: Neural Amp Models whose CPU usage can be reduced without re-training.

Abstract: This work demonstrates "slimmable Neural Amp Models", whose size and computational cost can be changed without additional training and with negligible computational overhead, enabling musicians to easily trade off between the accuracy and compute of the models they are using. The method's performance is quantified against commonly-used baselines, and a real-time demonstration of the model in an audio effect plug-in is developed.

Track: Demo Track

Confirmation: Demo Track: I confirm that I have followed the formatting guideline and included all author names and affiliations.

(Optional) Short Video Recording Link: https://youtu.be/93WAQsFu694

Submission Number: 6