Guitar-TECHS: An Electric Guitar Dataset Covering Techniques, Musical Excerpts, Chords, and Scales

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. GuitarTECHS 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 GuitarTECHS 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.

Recording Setup

Guitars were equipped with a Fishman Triple Play Connect multi-track MIDI pickup, allowing for the independent and automated capture of MIDI notes from each string. The audio output from each guitar was routed through a signal splitter, allowing us to send the signal to an audio interface for direct digital collection and an amplifier that was recorded using a microphone connected to the same audio interface. Additionally, audio was captured from two perspectives: a player perspective (or egocentric) using a head-mounted stereo microphone, and a listener (or exo-centric) perspective also using a stereo microphone but positioned 5 feet directly in front of the performer.