SynthTab: Leveraging Synthesized Data for Guitar Tablature Transcription

TL;DR

This paper introduces SynthTab, a large-scale synthesized guitar tablature dataset created using guitar plugins, which enhances GTT model training and generalization across diverse datasets.

Contribution

The paper presents a novel synthesis pipeline for generating large, diverse GTT audio datasets from symbolic tablature, improving model training and reducing overfitting.

Findings

Pre-training on SynthTab improves GTT performance.

SynthTab mitigates overfitting in cross-dataset experiments.

SynthTab covers multiple guitars and styles for robust training.

Abstract

Guitar tablature is a form of music notation widely used among guitarists. It captures not only the musical content of a piece, but also its implementation and ornamentation on the instrument. Guitar Tablature Transcription (GTT) is an important task with broad applications in music education, composition, and entertainment. Existing GTT datasets are quite limited in size and scope, rendering models trained on them prone to overfitting and incapable of generalizing to out-of-domain data. In order to address this issue, we present a methodology for synthesizing large-scale GTT audio using commercial acoustic and electric guitar plugins. We procure SynthTab, a dataset derived from DadaGP, which is a vast and diverse collection of richly annotated symbolic tablature. The proposed synthesis pipeline produces audio which faithfully adheres to the original fingerings and a subset of techniques specified in the tablature, and covers multiple guitars and styles for each track. Experiments show that pre-training a baseline GTT model on SynthTab can improve transcription performance when fine-tuning and testing on an individual dataset. More importantly, cross-dataset experiments show that pre-training significantly mitigates issues with overfitting.