LEGATO: Large-scale End-to-end Generalizable Approach to Typeset OMR
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912622004142080 |
|---|---|
| author | Yang, Guang Ebert, Victoria Tamer, Nazif Zheng, Brian Siyuan Pozzobon, Luiza Smith, Noah A. |
| author_facet | Yang, Guang Ebert, Victoria Tamer, Nazif Zheng, Brian Siyuan Pozzobon, Luiza Smith, Noah A. |
| contents | We propose Legato, a new end-to-end model for optical music recognition (OMR), a task of converting music score images to machine-readable documents. Legato is the first large-scale pretrained OMR model capable of recognizing full-page or multi-page typeset music scores and the first to generate documents in ABC notation, a concise, human-readable format for symbolic music. Bringing together a pretrained vision encoder with an ABC decoder trained on a dataset of more than 214K images, our model exhibits the strong ability to generalize across various typeset scores. We conduct comprehensive experiments on a range of datasets and metrics and demonstrate that Legato outperforms the previous state of the art. On our most realistic dataset, we see a 68\% and 47.6\% absolute error reduction on the standard metrics TEDn and OMR-NED, respectively. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_19065 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LEGATO: Large-scale End-to-end Generalizable Approach to Typeset OMR Yang, Guang Ebert, Victoria Tamer, Nazif Zheng, Brian Siyuan Pozzobon, Luiza Smith, Noah A. Computer Vision and Pattern Recognition Digital Libraries We propose Legato, a new end-to-end model for optical music recognition (OMR), a task of converting music score images to machine-readable documents. Legato is the first large-scale pretrained OMR model capable of recognizing full-page or multi-page typeset music scores and the first to generate documents in ABC notation, a concise, human-readable format for symbolic music. Bringing together a pretrained vision encoder with an ABC decoder trained on a dataset of more than 214K images, our model exhibits the strong ability to generalize across various typeset scores. We conduct comprehensive experiments on a range of datasets and metrics and demonstrate that Legato outperforms the previous state of the art. On our most realistic dataset, we see a 68\% and 47.6\% absolute error reduction on the standard metrics TEDn and OMR-NED, respectively. |
| title | LEGATO: Large-scale End-to-end Generalizable Approach to Typeset OMR |
| topic | Computer Vision and Pattern Recognition Digital Libraries |
| url | https://arxiv.org/abs/2506.19065 |