Guitar-TECHS: An Electric Guitar Dataset Covering Techniques, Musical Excerpts, Chords and Scales Using a Diverse Array of Hardware

TL;DR

Guitar-TECHS is a diverse, multi-modal guitar dataset designed to improve machine listening models by providing extensive recordings of techniques, musical content, and various recording setups, validated through empirical transcription experiments.

Contribution

This paper introduces Guitar-TECHS, a comprehensive, multi-perspective guitar dataset with diverse recordings and synchronized labels, addressing limitations of small datasets in guitar music research.

Findings

Effective training of guitar transcription models using Guitar-TECHS

Enhanced robustness of models across different recording conditions

Demonstrated dataset's utility through empirical transcription results

Abstract

Guitar-related machine listening research involves tasks like timbre transfer, performance generation, and automatic transcription. However, small datasets often limit model robustness due to insufficient acoustic diversity and musical content. To address these issues, we introduce Guitar-TECHS, a comprehensive dataset featuring a variety of guitar techniques, musical excerpts, chords, and scales. These elements are performed by diverse musicians across various recording settings. Guitar-TECHS incorporates recordings from two stereo microphones: an egocentric microphone positioned on the performer's head and an exocentric microphone placed in front of the performer. It also includes direct input recordings and microphoned amplifier outputs, offering a wide spectrum of audio inputs and recording qualities. All signals and MIDI labels are properly synchronized. Its multi-perspective and multi-modal content makes Guitar-TECHS a valuable resource for advancing data-driven guitar research, and to develop robust guitar listening algorithms. We provide empirical data to demonstrate the dataset's effectiveness in training robust models for Guitar Tablature Transcription.