Slimmable NAM: Neural Amp Models with adjustable runtime computational cost
Steven Atkinson
2025 Poster
in
Workshop: Artificial Intelligence for Music: Where Creativity Meets Computation
in
Workshop: Artificial Intelligence for Music: Where Creativity Meets Computation
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.
Chat is not available.
Successful Page Load