# An Empirical Evaluation of End-to-End Polyphonic Optical Music Recognition

arXiv: https://arxiv.org/abs/2108.01769 · HTML: https://mlsanity.com/paper/2108.01769/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 25 references that are in the map.
- First posted on arXiv 3 Aug 2021.

## Builds on (most cited first, 4 of 4)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Understanding Optical Music Recognition](https://mlsanity.com/paper/1908.03608/) (2019)
- [Optical Music Recognition with Convolutional Sequence-to-Sequence Models](https://mlsanity.com/paper/1707.04877/) (2017)
- [Deep Watershed Detector for Music Object Recognition](https://mlsanity.com/paper/1805.10548/) (2018)

## Built on by (most cited first, 8 of 8)

- [Sheet Music Transformer: End-To-End Optical Music Recognition Beyond Monophonic Transcription](https://mlsanity.com/paper/2402.07596/) (2024)
- [A Unified Representation Framework for the Evaluation of Optical Music Recognition Systems](https://mlsanity.com/paper/2312.12908/) (2023)
- [TrOMR:Transformer-Based Polyphonic Optical Music Recognition](https://mlsanity.com/paper/2308.09370/) (2023)
- [Transcoda: End-to-End Zero-Shot Optical Music Recognition via Data-Centric Synthetic Training](https://mlsanity.com/paper/2605.10835/) (2026)
- [Comparision Of Adversarial And Non-Adversarial LSTM Music Generative Models](https://mlsanity.com/paper/2211.00731/) (2022)
- [Proceedings of the 5th International Workshop on Reading Music Systems](https://mlsanity.com/paper/2311.04091/) (2023)
- [A High-Accuracy Optical Music Recognition Method Based on Bottleneck Residual Convolutions](https://mlsanity.com/paper/2604.16446/) (2026)
- [A Dataset and Benchmark for Optical Music Recognition of String Quartet Scores](https://mlsanity.com/paper/2608.10978/) (2026)

## Abstract (arXiv)

Previous work has shown that neural architectures are able to perform optical music recognition (OMR) on monophonic and homophonic music with high accuracy. However, piano and orchestral scores frequently exhibit polyphonic passages, which add a second dimension to the task. Monophonic and homophonic music can be described as homorhythmic, or having a single musical rhythm. Polyphonic music, on the other hand, can be seen as having multiple rhythmic sequences, or voices, concurrently. We first introduce a workflow for creating large-scale polyphonic datasets suitable for end-to-end recognition from sheet music publicly available on the MuseScore forum. We then propose two novel formulations for end-to-end polyphonic OMR -- one treating the problem as a type of multi-task binary classification, and the other treating it as multi-sequence detection. Building upon the encoder-decoder architecture and an image encoder proposed in past work on end-to-end OMR, we propose two novel decoder models -- FlagDecoder and RNNDecoder -- that correspond to the two formulations. Finally, we compare the empirical performance of these end-to-end approaches to polyphonic OMR and observe a new state-of-the-art performance with our multi-sequence detection decoder, RNNDecoder.