KLANN: Linearising long-term dynamics in nonlinear audio effects using Koopman networks
- Ville Huhtala,
- Lauri Juvela,
- Sebastian J. Schlecht
Abstract
In recent years, neural network-based black-box modeling of nonlinear audio effects has improved considerably. Present convolutional and recurrent models can model audio effects with long-term dynamics, but the models require many parameters, thus increasing the processing time. In this paper, we propose KLANN, a Koopman-Linearised Audio Neural Network structure that lifts a one-dimensional signal (mono audio) into a high-dimensional approximately linear state-space representation with nonlinear mapping, and then uses differentiable biquad filters to predict linearly within the lifted state-space. Results show that the proposed models match the high performance of the state-of-the-art neural models while having a more compact architecture, reducing the number of parameters by tenfold, and having interpretable components.13 Dec 2023Submitted to TechRxiv 18 Dec 2023Published in TechRxiv