1 of 7

GAPS: A Large and Diverse Classical Guitar Dataset and Benchmark Transcription Model

Xavier Riley, Zixun Guo, Drew Edwards and Simon Dixon

Centre for Digital Music

Queen Mary University of London

j.x.riley@qmul.ac.uk

ISMIR 2024

This work was supported by the UKRI and EPSRC under grant EP/S022694/1

2 of 7

Motivation

Piano transcription works really well (98% on MAESTRO, 90% on MAPS)

Why? Because there are good datasets for piano.

What happens if we build an equivalent dataset for guitar?

ISMIR 2024

Credit: GiantMIDI-Piano Kong et al. 2020

3 of 7

4 of 7

GAPS

300 Pieces (14 hours) of solo classical guitar with:

  • MusicXML scores w/ tab
  • Aligned MIDI w/ beats
  • Video and Audio
  • Extensive Metadata

All manually checked and verified

Dataset

(Guitar-Aligned Performance Scores)

ISMIR 2024

5 of 7

GAPS

Training Data Pipeline

ISMIR 2024

6 of 7

GAPS

Results

ISMIR 2024

Method

F-measure (no offset)

MT3 (2022)

90.0%

Lu et al. (2023)

91.1.%

Ours

91.2%

GuitarSet – test split

Method

F-measure (no offset)

MT3 (2022)

32.0%

Zang et al. (2023)

70.2%

Maman and Bermano (2022)

82.9%

Ours

88.1%

GuitarSet – entire dataset (zero shot)

7 of 7

GAPS

Thank you!

ISMIR 2024