Saved in:
Bibliographic Details
Main Author: Atkinson, Steven
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.07470
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911258517700608
author Atkinson, Steven
author_facet Atkinson, Steven
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_07470
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Slimmable NAM: Neural Amp Models with adjustable runtime computational cost
Atkinson, Steven
Machine Learning
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.
title Slimmable NAM: Neural Amp Models with adjustable runtime computational cost
topic Machine Learning
url https://arxiv.org/abs/2511.07470