Improving Unsupervised Clean-to-Rendered Guitar Tone Transformation Using GANs and Integrated Unaligned Clean Data

TL;DR

This paper enhances unsupervised guitar tone transformation using GANs by integrating advanced discriminators and leveraging more unpaired data, resulting in improved modeling of various guitar amplifier tones.

Contribution

It introduces a GAN framework with multi-scale and multi-period discriminators and explores the use of additional unpaired data for better tone modeling.

Findings

Improved modeling of low-gain and high-gain guitar amplifiers.

Advanced discriminators enhance the quality of tone transformation.

Using unpaired data benefits the GAN training process.

Abstract

Recent years have seen increasing interest in applying deep learning methods to the modeling of guitar amplifiers or effect pedals. Existing methods are mainly based on the supervised approach, requiring temporally-aligned data pairs of unprocessed and rendered audio. However, this approach does not scale well, due to the complicated process involved in creating the data pairs. A very recent work done by Wright et al. has explored the potential of leveraging unpaired data for training, using a generative adversarial network (GAN)-based framework. This paper extends their work by using more advanced discriminators in the GAN, and using more unpaired data for training. Specifically, drawing inspiration from recent advancements in neural vocoders, we employ in our GAN-based model for guitar amplifier modeling two sets of discriminators, one based on multi-scale discriminator (MSD) and the other multi-period discriminator (MPD). Moreover, we experiment with adding unprocessed audio signals that do not have the corresponding rendered audio of a target tone to the training data, to see how much the GAN model benefits from the unpaired data. Our experiments show that the proposed two extensions contribute to the modeling of both low-gain and high-gain guitar amplifiers.