Practical End-to-End Optical Music Recognition for Pianoform Music

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F24%3A10492884" target="_blank" >RIV/00216208:11320/24:10492884 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/chapter/10.1007/978-3-031-70552-6_4" target="_blank" >https://link.springer.com/chapter/10.1007/978-3-031-70552-6_4</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-031-70552-6_4" target="_blank" >10.1007/978-3-031-70552-6_4</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Practical End-to-End Optical Music Recognition for Pianoform Music

Popis výsledku v původním jazyce

The majority of recent progress in Optical Music Recognition (OMR) has been achieved with Deep Learning methods, especially models following the end-to-end paradigm, reading input images and producing a linear sequence of tokens. Unfortunately, many music scores, especially piano music, cannot be easily converted to a linear sequence. This has led OMR researchers to use custom linearized encodings, instead of broadly accepted structured formats for music notation. Their diversity makes it difficult to compare the performance of OMR systems directly. To bring recent OMR model progress closer to useful results: (a) We define a sequential format called Linearized MusicXML, allowing to train an end-to-end model directly and maintaining close cohesion and compatibility with the industry-standard MusicXML format. (b) We create a dev and test set for benchmarking typeset OMR with MusicXML ground truth based on the OpenScore Lieder corpus. They contain 1,438 and 1,493 pianoform systems, each with an image fro

Název v anglickém jazyce

Practical End-to-End Optical Music Recognition for Pianoform Music

Popis výsledku anglicky

The majority of recent progress in Optical Music Recognition (OMR) has been achieved with Deep Learning methods, especially models following the end-to-end paradigm, reading input images and producing a linear sequence of tokens. Unfortunately, many music scores, especially piano music, cannot be easily converted to a linear sequence. This has led OMR researchers to use custom linearized encodings, instead of broadly accepted structured formats for music notation. Their diversity makes it difficult to compare the performance of OMR systems directly. To bring recent OMR model progress closer to useful results: (a) We define a sequential format called Linearized MusicXML, allowing to train an end-to-end model directly and maintaining close cohesion and compatibility with the industry-standard MusicXML format. (b) We create a dev and test set for benchmarking typeset OMR with MusicXML ground truth based on the OpenScore Lieder corpus. They contain 1,438 and 1,493 pianoform systems, each with an image fro

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

<a href="/cs/project/DH23P03OVV008" target="_blank" >DH23P03OVV008: OmniOMR – rozpoznávání hudebního záznamu pomocí strojového učení pro digitální knihovny</a><br>

Návaznosti

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

Rok uplatnění

2024

Kód důvěrnosti údajů

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

Název statě ve sborníku

Document Analysis and Recognition -- ICDAR 2024

ISBN

978-3-031-70551-9

ISSN

—

e-ISSN

—

Počet stran výsledku

19

Strana od-do

55-73

Název nakladatele

Springer International Publishing

Místo vydání

Cham, Switzerland

Místo konání akce

Athîna, Greece

Datum konání akce

30. 8. 2024

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—