Deep Learning for Black-Box Modeling of Audio Effects

Martínez Ramírez, Benetos, Reiss
2020 Applied Sciences  
Virtual analog modeling of audio effects consists of emulating the sound of an audioprocessor reference device. This digital simulation is normally done by designing mathematicalmodels of these systems. It is often difficult because it seeks to accurately model all componentswithin the effect unit, which usually contains various nonlinearities and time-varying components.Most existing methods for audio effects modeling are either simplified or optimized to a very specificcircuit or type of
more » ... effect and cannot be efficiently translated to other types of audio effects.Recently, deep neural networks have been explored as black-box modeling strategies to solve thistask, i.e., by using only input–output measurements. We analyse different state-of-the-art deeplearning models based on convolutional and recurrent neural networks, feedforward WaveNetarchitectures and we also introduce a new model based on the combination of the aforementionedmodels. Through objective perceptual-based metrics and subjective listening tests we explore theperformance of these models when modeling various analog audio effects. Thus, we show virtualanalog models of nonlinear effects, such as a tube preamplifier; nonlinear effects with memory, suchas a transistor-based limiter and nonlinear time-varying effects, such as the rotating horn and rotatingwoofer of a Leslie speaker cabinet.
doi:10.3390/app10020638 fatcat:myrxwvst3za57kdu73dyc4exqu