Anti-aliasing of neural distortion effects via model fine tuning

TL;DR

This paper introduces a fine-tuning method for neural guitar distortion models that significantly reduces aliasing artifacts caused by high-frequency inputs, improving perceptual quality without extensive oversampling.

Contribution

A novel teacher-student fine-tuning approach that suppresses aliasing in neural distortion models using aliasing-free training data, applicable to LSTM and TCN architectures.

Findings

Aliasing was reduced more than twofold oversampling in most cases.

Harmonic distortion components are affected, with model-dependent effects.

LSTM models achieved the best balance between anti-aliasing and similarity to analog devices.

Abstract

Neural networks have become ubiquitous with guitar distortion effects modelling in recent years. Despite their ability to yield perceptually convincing models, they are susceptible to frequency aliasing when driven by high frequency and high gain inputs. Nonlinear activation functions create both the desired harmonic distortion and unwanted aliasing distortion as the bandwidth of the signal is expanded beyond the Nyquist frequency. Here, we present a method for reducing aliasing in neural models via a teacher-student fine tuning approach, where the teacher is a pre-trained model with its weights frozen, and the student is a copy of this with learnable parameters. The student is fine-tuned against an aliasing-free dataset generated by passing sinusoids through the original model and removing non-harmonic components from the output spectra. Our results show that this method significantly suppresses aliasing for both long-short-term-memory networks (LSTM) and temporal convolutional networks (TCN). In the majority of our case studies, the reduction in aliasing was greater than that achieved by two times oversampling. One side-effect of the proposed method is that harmonic distortion components are also affected. This adverse effect was found to be model-dependent, with the LSTM models giving the best balance between anti-aliasing and preserving the perceived similarity to an analog reference device.