Deep Regularized RNNs for Virtual Analog Modeling
For researchers in audio DSP, this work provides a practical solution to a known artifact problem in recurrent neural network-based virtual analog modeling.
This paper addresses noise artifacts in black-box virtual analog modeling with time-varying control inputs. By introducing deep control-conditioned LSTMs and a gammatone filterband loss, the proposed method achieves comparable modeling accuracy to unregularized baselines while eliminating noise artifacts.
Virtual analog (VA) modeling methods seek to emulate analog audio hardware using digital signal processing (DSP). Modeling approaches fall into three broad categories: white-box methods, which use detailed device knowledge for accurate simulation; gray-box methods that use generic DSP blocks to model the system; and black-box methods, which rely solely on opaque models learned from input-output data. A category of architectures used widely in black-box modeling are recurrent neural networks (RNNs). To model device controls, the control values can be provided as conditioning input to the network. However, when the conditioning is time-varied, the models are susceptible to producing noise artifacts. Regularization of the RNN dynamics significantly reduces these artifacts, though at a loss in modeling accuracy. This paper closes the dynamics regularization quality gap by introducing deep control-conditioned LSTMs and a gammatone filterband (GFB) loss. Experiments indicate that the proposed method achieves comparable modeling performance as unregularized baselines while avoiding the noise artifacts caused by time-varying control inputs.