Neural networks have seen increased popularity in recent years for nonlinear audio effects modelling. Such a task requires sampling and creates high frequency harmonics that can quickly surpass the Nyquist rate, creating aliasing in the baseband. In this work, we study the impact of processing audio with neural networks and the potential aliasing these highly nonlinear algorithms can incur or aggravate. Namely, we evaluate the performance of a number of anti-aliasing methods for use in real-time. Notably, one method of anti-aliasing capable of real-time performance was identified: forced sparsity through network pruning.

Authors: Vanhatalo, Tara; Legrand, Pierrick; Desainte-Catherine, Myriam; Hanna, Pierre; Pille, Guillaume
Affiliations: Inria Bordeaux Sud-Ouest, Institute of Mathematics of Bordeaux, UMR 5251 CNRS, University of Bordeaux, F-33405 Talence, France; University of Bordeaux, CNRS, Bordeaux INP, LaBRI, UMR 5800, F-33400 Talence, France; Orosys, F-34980 Saint-Gély-du-Fesc, France; Inria Bordeaux Sud-Ouest, Institute of Mathematics of Bordeaux, UMR 5251 CNRS, University of Bordeaux, F-33405 Talence, France; University of Bordeaux, CNRS, Bordeaux INP, LaBRI, UMR 5800, F-33400 Talence, France; Orosys, F-34980 Saint-Gély-du-Fesc, France; University of Bordeaux, CNRS, Bordeaux INP, LaBRI, UMR 5800, F-33400 Talence, France; Orosys, F-34980 Saint-Gély-du-Fesc, France; Orosys, F-34980 Saint-Gély-du-Fesc, France(See document for exact affiliation information.)
JAES Volume 72 Issue 3 pp. 114-122; March 2024
Publication Date: March 5, 2024 Import into BibTeX
Permalink: https://www.aes.org/e-lib/browse.cfm?elib=22384

Click to purchase paper as a non-member or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member and would like to subscribe to the E-Library then Join the AES!

This paper costs $33 for non-members and is free for AES members and E-Library subscribers.

Learn more about the AES E-Library

E-Library Location: (CD JAES72)   /jaes72/3/pg114.pdf

DOI: https://doi.org/10.17743/jaes.2022.0122

Start a discussion about this paper!