Evaluation of Real-Time Aliasing Reduction Methods in Neural Networks for Nonlinear Audio Effects Modelling - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles Journal of the Audio Engineering Society Year : 2023

Evaluation of Real-Time Aliasing Reduction Methods in Neural Networks for Nonlinear Audio Effects Modelling

Abstract

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.
No file

Dates and versions

hal-04235385 , version 1 (10-10-2023)

Licence

Attribution

Identifiers

Cite

Tara Vanhatalo, Pierrick Legrand, Myriam Desainte-Catherine, Pierre Hanna, Guillaume Pille. Evaluation of Real-Time Aliasing Reduction Methods in Neural Networks for Nonlinear Audio Effects Modelling. Journal of the Audio Engineering Society, 2023, ⟨10.17743/jaes.2022.0122⟩. ⟨hal-04235385⟩
136 View
0 Download

Altmetric

Share

Gmail Facebook X LinkedIn More