Download Antiderivative Antialiasing for Recurrent Neural Networks Neural networks have become invaluable for general audio processing tasks, such as virtual analog modeling of nonlinear audio equipment.
For sequence modeling tasks in particular, recurrent neural networks (RNNs) have gained widespread adoption in recent years. Their general applicability and effectiveness
stems partly from their inherent nonlinearity, which makes them
prone to aliasing. Recent work has explored mitigating aliasing
by oversampling the network—an approach whose effectiveness is
directly linked with the incurred computational costs. This work
explores an alternative route by extending the antiderivative antialiasing technique to explicit, computable RNNs. Detailed applications to the Gated Recurrent Unit and Long Short-Term Memory cell are shown as case studies. The proposed technique is evaluated
on multiple pre-trained guitar amplifier models, assessing its impact on the amount of aliasing and model tonality. The method is
shown to reduce the models’ tendency to alias considerably across
all considered sample rates while only affecting their tonality moderately, without requiring high oversampling factors. The results
of this study can be used to improve sound quality in neural audio
processing tasks that employ a suitable class of RNNs. Additional
materials are provided in the accompanying webpage.
Download An Equivalent Circuit Interpretation of Antiderivative Antialiasing The recently proposed antiderivative antialiasing (ADAA) technique for stateful systems involves two key features: 1) replacing a nonlinearity in a physical model or virtual analog simulation
with an antialiased nonlinear system involving antiderivatives of
the nonlinearity and time delays and 2) introducing a digital filter
in cascade with each original delay in the system. Both of these
features introduce the same delay, which is compensated by adjusting the sampling period. The result is a simulation with reduced
aliasing distortion. In this paper, we study ADAA using equivalent
circuits, answering the question: “Which electrical circuit, discretized using the bilinear transform, yields the ADAA system?”
This gives us a new way of looking at the stability of ADAA and
how introducing extra filtering distorts a system’s response. We
focus on the Wave Digital Filter (WDF) version of this technique.
Download Network Variable Preserving Step-size Control in Wave Digital Filters In this paper a new technique is introduced that allows for the variable step-size simulation of wave digital filters. The technique is based on the preservation of the underlying network variables which prevents fluctuation in the stored energy in reactive network elements when the step-size is changed. This method allows for the step-size variation of wave digital filters discretized with any passive discretization technique and works with both linear and nonlinear reference circuits. The usefulness of the technique with regards to audio circuit simulation is demonstrated via the case study of a relaxation oscillator where it is shown how the variable step-size technique can be used to mitigate frequency error that would otherwise occur with a fixed step-size simulation. Additionally, an example of how aliasing suppression techniques can be combined with physical modeling is given with an example of the polyBLEP antialiasing technique being applied to the output voltage signal of the relaxation oscillator.