# Transcoda: End-to-End Zero-Shot Optical Music Recognition via Data-Centric Synthetic Training

arXiv: https://arxiv.org/abs/2605.10835 · HTML: https://mlsanity.com/paper/2605.10835/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 30 references that are in the map.
- First posted on arXiv 11 May 2026.

## Builds on (most cited first, 15 of 15)

- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [SimMIM: A Simple Framework for Masked Image Modeling](https://mlsanity.com/paper/2111.09886/) (2021)
- [XGrammar: Flexible and Efficient Structured Generation Engine for Large Language Models](https://mlsanity.com/paper/2411.15100/) (2024)
- [DAN: a Segmentation-free Document Attention Network for Handwritten Document Recognition](https://mlsanity.com/paper/2203.12273/) (2022)
- [Full Page Handwriting Recognition via Image to Sequence Extraction](https://mlsanity.com/paper/2103.06450/) (2021)
- [Sheet Music Transformer: End-To-End Optical Music Recognition Beyond Monophonic Transcription](https://mlsanity.com/paper/2402.07596/) (2024)
- [PDMX: A Large-Scale Public Domain MusicXML Dataset for Symbolic Music Processing](https://mlsanity.com/paper/2409.10831/) (2024)
- [Augraphy: A Data Augmentation Library for Document Images](https://mlsanity.com/paper/2208.14558/) (2022)
- [End-to-End Full-Page Optical Music Recognition for Pianoform Sheet Music](https://mlsanity.com/paper/2405.12105/) (2024)
- [Generating Symbolic Music from Natural Language Prompts using an LLM-Enhanced Dataset](https://mlsanity.com/paper/2410.02084/) (2024)
- [An Empirical Evaluation of End-to-End Polyphonic Optical Music Recognition](https://mlsanity.com/paper/2108.01769/) (2021)
- [Sheet Music Benchmark: Standardized Optical Music Recognition Evaluation](https://mlsanity.com/paper/2506.10488/) (2025)
- [TrOMR:Transformer-Based Polyphonic Optical Music Recognition](https://mlsanity.com/paper/2308.09370/) (2023)
- [Toward a More Complete OMR Solution](https://mlsanity.com/paper/2409.00316/) (2024)
- [LEGATO: Large-scale End-to-end Generalizable Approach to Typeset OMR](https://mlsanity.com/paper/2506.19065/) (2025)

## Built on by (most cited first, 1 of 1)

- [A Dataset and Benchmark for Optical Music Recognition of String Quartet Scores](https://mlsanity.com/paper/2608.10978/) (2026)

## Abstract (arXiv)

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++).