Leveraging Real Electric Guitar Tones and Effects to Improve Robustness in Guitar Tablature Transcription Modeling

TL;DR

This paper demonstrates that incorporating synthetic training data created from recordings of real guitar tones with various effects enhances the robustness of guitar tablature transcription models, especially when tested on diverse professional performances.

Contribution

It introduces a novel approach of using real guitar tones with effects for synthetic data generation to improve GTT robustness, filling a gap left by purely simulated data.

Findings

Improved GTT robustness with real-tone based synthetic data

Evaluation on a new diverse dataset of professional guitar performances

Synthetic data with effects outperforms purely simulated data

Abstract

Guitar tablature transcription (GTT) aims at automatically generating symbolic representations from real solo guitar performances. Due to its applications in education and musicology, GTT has gained traction in recent years. However, GTT robustness has been limited due to the small size of available datasets. Researchers have recently used synthetic data that simulates guitar performances using pre-recorded or computer-generated tones and can be automatically generated at large scales. The present study complements these efforts by demonstrating that GTT robustness can be improved by including synthetic training data created using recordings of real guitar tones played with different audio effects. We evaluate our approach on a new evaluation dataset with professional solo guitar performances that we composed and collected, featuring a wide array of tones, chords, and scales.