Obstacles with Synthesizing Training Data for OMR

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F22%3A10457043" target="_blank" >RIV/00216208:11320/22:10457043 - isvavai.cz</a>

Výsledek na webu

<a href="https://arxiv.org/abs/2211.13285" target="_blank" >https://arxiv.org/abs/2211.13285</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Obstacles with Synthesizing Training Data for OMR

Popis výsledku v původním jazyce

Training with synthetic data has been successfully used in many domains of deep learning where authentic training data is scarce. Optical Music Recognition (OMR), especially recognition of handwritten music, greatly benefits from training on synthetic data too. In this paper, we explore the challenges of synthesizing images of sheets of music for training deep learning OMR models and compare such synthesis to the process of digital music engraving. We also contrast that with the architecture of our synthesizer prototype, which was used to achieve state-ofthe-art results by training on the synthetic images only.

Název v anglickém jazyce

Obstacles with Synthesizing Training Data for OMR

Popis výsledku anglicky

Training with synthetic data has been successfully used in many domains of deep learning where authentic training data is scarce. Optical Music Recognition (OMR), especially recognition of handwritten music, greatly benefits from training on synthetic data too. In this paper, we explore the challenges of synthesizing images of sheets of music for training deep learning OMR models and compare such synthesis to the process of digital music engraving. We also contrast that with the architecture of our synthesizer prototype, which was used to achieve state-ofthe-art results by training on the synthetic images only.

Druh

O - Ostatní výsledky

CEP obor

—

OECD FORD obor

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

Projekt

<a href="/cs/project/GX19-26934X" target="_blank" >GX19-26934X: Neuronové reprezentace v multimodálním a mnohojazyčném modelování</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2022

Kód důvěrnosti údajů

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