Handwritten Historical Music Recognition by Sequence-to-Sequence with Attention Mechanism

Arnau Baró*, Alícia Fornes, Carles Badal

*Corresponding author for this work

Research output: Other contribution

1 Citation (Web of Science)


Despite decades of research in Optical Music Recognition (OMR), the recognition of old handwritten music scores remains a challenge because of the variabilities in the handwriting styles, paper degradation, lack of standard notation, etc. Therefore, the research in OMR systems adapted to the particularities of old manuscripts is crucial to accelerate the conversion of music scores existing in archives into digital libraries, fostering the dissemination and preservation of our music heritage. In this paper we explore the adaptation of sequence-to-sequence models with attention mechanism (used in translation and handwritten text recognition) and the generation of specific synthetic data for recognizing old music scores. The experimental validation demonstrates that our approach is promising, especially when compared with long short-term memory neural networks.

Original languageEnglish
TypeConference proceedings
Number of pages6
ISBN (Electronic)978-1-7281-9966-5
Publication statusPublished - 2020

Publication series

NameInternational Conference on Handwriting Recognition
ISSN (Print)2167-6445


Dive into the research topics of 'Handwritten Historical Music Recognition by Sequence-to-Sequence with Attention Mechanism'. Together they form a unique fingerprint.

Cite this