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

Vanhatalo T, Legrand P, Desainte-Catherine M, Hanna P, Pille G. Evaluation of Real-Time Aliasing Reduction Methods in Neural Networks for Nonlinear Audio Effects Modelling. J Audio Eng Soc. 2024;72(3):114-122. doi:10.17743/jaes.2022.0122

@article{Vanhatalo2024_22384,
  author = {Vanhatalo, Tara and Legrand, Pierrick and Desainte-Catherine, Myriam and Hanna, Pierre and Pille, Guillaume},
  title = {{Evaluation of Real-Time Aliasing Reduction Methods in Neural Networks for Nonlinear Audio Effects Modelling}},
  journal = {Journal of the Audio Engineering Society},
  volume = {72},
  number = {3},
  pages = {114--122},
  year = {2024},
  month = mar,
  publisher = {Audio Engineering Society},
  doi = {10.17743/jaes.2022.0122},
  url = {https://doi.org/10.17743/jaes.2022.0122}
}

TY  - JOUR
TI  - Evaluation of Real-Time Aliasing Reduction Methods in Neural Networks for Nonlinear Audio Effects Modelling
AU  - Vanhatalo, Tara
AU  - Legrand, Pierrick
AU  - Desainte-Catherine, Myriam
AU  - Hanna, Pierre
AU  - Pille, Guillaume
T2  - Journal of the Audio Engineering Society
J2  - J. Audio Eng. Soc.
VL  - 72
IS  - 3
SP  - 114
EP  - 122
PY  - 2024
DA  - 2024/03/06
DO  - 10.17743/jaes.2022.0122
UR  - https://doi.org/10.17743/jaes.2022.0122
PB  - Audio Engineering Society
LA  - en
AB  - 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.
ER  -