GAPS: A Large and Diverse Classical Guitar Dataset and Benchmark Transcription Model
Published in ISMIR, 2024
Recommended citation: Riley, Xavier, Zixun Guo, Drew Edwards, and Simon Dixon (2024). "GAPS: A Large and Diverse Classical Guitar Dataset and Bench- mark Transcription Model" Proceedings of the 25th International Society for Music Information Retrieval Conference https://www.eecs.qmul.ac.uk/~simond/pub/2024/RileyEtAl-ISMIR-2024.pdf
We introduce GAPS (Guitar-Aligned Performance Scores), a new dataset of classical guitar performances, and a benchmark guitar transcription model that achieves state-of-the-art performance on GuitarSet in both supervised and zero-shot settings. GAPS is the largest dataset of real guitar audio, containing 14 hours of freely available audio-score aligned pairs, recorded in diverse conditions by over 200 performers, together with high-resolution note-level MIDI alignments and performance videos.These enable us to train a state-of-the-art model for automatic transcription of solo guitar recordings which can generalise well to real world audio that is unseen during training.