Smashcima: Full-Page Handwritten Music Document Synthesizer

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3A10511628" target="_blank" >RIV/00216208:11320/25:10511628 - isvavai.cz</a>

Výsledek na webu

<a href="https://dl.acm.org/doi/10.1145/3748336.3748380" target="_blank" >https://dl.acm.org/doi/10.1145/3748336.3748380</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1145/3748336.3748380" target="_blank" >10.1145/3748336.3748380</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Smashcima: Full-Page Handwritten Music Document Synthesizer

Popis výsledku v původním jazyce

Despite massive progress made in Optical Music Recognition (OMR) with deep learning, data scarcity remains an issue, especially for manuscripts. Synthetic data has been shown to alleviate this issue, but no tool for rendering a handwritten page from structured encoding such as MusicXML exists. This paper introduces Smashcima, a framework for the creation of synthetic handwritten full-page music images. It accepts MusicXML files and produces images with full information on their glyphs, segmentation masks, keypoints, notation graph, and semantics. It is compatible with the MuNG format and so can also be used to produce synthetic training data object detection and graph models. It can synthesize images of all levels of complexity of music notation, including pianoform music. Smashcima thus greatly increases the value of dataset acquisition, as it can expand a small manually annotated dataset to the scale of arbitrary available MusicXML data, thereby alleviating manuscript data scarcity for OMR.

Název v anglickém jazyce

Smashcima: Full-Page Handwritten Music Document Synthesizer

Popis výsledku anglicky

Despite massive progress made in Optical Music Recognition (OMR) with deep learning, data scarcity remains an issue, especially for manuscripts. Synthetic data has been shown to alleviate this issue, but no tool for rendering a handwritten page from structured encoding such as MusicXML exists. This paper introduces Smashcima, a framework for the creation of synthetic handwritten full-page music images. It accepts MusicXML files and produces images with full information on their glyphs, segmentation masks, keypoints, notation graph, and semantics. It is compatible with the MuNG format and so can also be used to produce synthetic training data object detection and graph models. It can synthesize images of all levels of complexity of music notation, including pianoform music. Smashcima thus greatly increases the value of dataset acquisition, as it can expand a small manually annotated dataset to the scale of arbitrary available MusicXML data, thereby alleviating manuscript data scarcity for OMR.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of the 12th International Conference on Digital Libraries for Musicology

ISBN

979-8-4007-2083-3

ISSN

—

e-ISSN

—

Počet stran výsledku

5

Strana od-do

119-123

Název nakladatele

Association for Computing Machinery

Místo vydání

New York, NY, USA

Místo konání akce

Seoul, Korea

Datum konání akce

26. 9. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001612605000017