KIT | KIT-Bibliothek | Impressum | Datenschutz

Exploring Procedural Data Generation for Automatic Acoustic Guitar Fingerpicking Transcription

Murgul, Sebastian ORCID iD icon 1; Heizmann, Michael 1
1 Institut für Industrielle Informationstechnik (IIIT), Karlsruher Institut für Technologie (KIT)

Abstract:

Automatic transcription of acoustic guitar fingerpicking performances remains a challenging task due to the scarcity of labeled training data and legal constraints connected with musical recordings. This work investigates a procedural data generation pipeline as an alternative to real audio recordings for training transcription models. Our approach synthesizes training data through four stages: knowledge-based fingerpicking tablature composition, MIDI performance rendering, physical modeling using an extended Karplus-Strong algorithm, and audio augmentation including reverb and distortion. We train and evaluate a CRNN-based note-tracking model on both real and synthetic datasets, demonstrating that procedural data can be used to achieve reasonable note-tracking results. Finetuning with a small amount of real data further enhances transcription accuracy, improving over models trained exclusively on real recordings. These results highlight the potential of procedurally generated audio for data-scarce music information retrieval tasks.


Postprint §
DOI: 10.5445/IR/1000184107
Veröffentlicht am 13.09.2025
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Industrielle Informationstechnik (IIIT)
Publikationstyp Proceedingsbeitrag
Publikationsdatum 11.09.2025
Sprache Englisch
Identifikator KITopen-ID: 1000184107
Erschienen in Proceedings of the 6th Conference on AI Music Creativity (AIMC 2025), Brussels, Belgium, September 10th-12th
Veranstaltung 6th Conference on AI Music Creativity (AIMC 2025), Brüssel, Belgien, 10.09.2025 – 12.09.2025
KIT – Die Universität in der Helmholtz-Gemeinschaft
KITopen Landing Page