cs.CV · 2606.31454 Copy arXiv ID · Jun 30, 2026 Save Towards a foundational model for recognising diastematic Gregorian notation Authors: Daniel Kurek , Jan Hajič
Organizations: Institute of Formal and Applied Linguistics, Charles University, Prague, Czechia
Abstract Optical recognition of Gregorian notation has recently been attempted with end-to-end methods, with four datasets introduced. However, each of these datasets is in a different encoding. We design a common encoding based on the S-GABC proposal, convert all four datasets to this common encoding, and train a shared end-to-end foundational model for diastematic Gregorian notation that establishes a new state of the art across all four datasets.
Explore similar work May 11, 2026 · Daniel Dratschuk, Paul Swoboda Deepseek-Ocr Synthetic Training Data
Jul 7, 2026 · Guang Yang, Brian Siyuan Zheng, Victoria Ebert +1 Sheet Music Human Annotations
Jun 8, 2026 · Jiří Mayer, Martina Dvořáková, Vojtěch Dvořák +6 Sheet Music Piano
May 11, 2026 · cs.CV J/K move · Enter open · S save
Daniel Dratschuk, Paul Swoboda
Heinrich Heine University Düsseldorf, Germany
Optical Music Recognition (OMR), the task of transcribing sheet music into a structured textual representation, is currently bottlenecked by a lack of large-scale, annotated datasets of real scans. This forces models to rely on either few-shot transfer or synthetic training pipelines that remain overly simplistic. A secondary challenge is encoding non-uniqueness: in the popular Humdrum **kern format for transcribing music, multiple different text encodings can render into the same visual sheet music. This one-to-many mapping creates a harder learning task and introduces high uncertainty during decoding. We propose Transcoda, an OMR system built on (i) an advanced synthetic data generation pipeline, (ii) a normalization of the **kern encoding to enforce a unique normal form and (iii) grammar-based decoding to ensure the syntactic correctness of the output. This approach allows us to train a compact 59M-parameter model in just 6 hours on a single GPU that outperforms billion-parameter baselines. Transcoda achieves the best score among state of the art baselines on a newly curated benchmark of synthetically rendered scores at 18.46% OMR-NED (compared to 43.91% for the next-best system, Legato) and reduces the error rate on historical Polish scans to 63.97% OMR-NED (down from 80.16% for SMT++).