%0 Book Section
%T Optical Music Recognition by Long Short-Term Memory Networks
%A Arnau Baro
%A Pau Riba
%A Jorge Calvo-Zaragoza
%A Alicia Fornes
%E A. Fornes, B. Lamiroy
%B Graphics Recognition. Current Trends and Evolutions
%D 2018
%V 11009
%I Springer
%@ 978-3-030-02283-9
%F Arnau Baro2018
%O DAG; 600.097; 601.302; 601.330; 600.121
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=3227), last updated on Thu, 29 Oct 2020 13:39:11 +0100
%X Optical Music Recognition refers to the task of transcribing the image of a music score into a machine-readable format. Many music scores are written in a single staff, and therefore, they could be treated as a sequence. Therefore, this work explores the use of Long Short-Term Memory (LSTM) Recurrent Neural Networks for reading the music score sequentially, where the LSTM helps in keeping the context. For training, we have used a synthetic dataset of more than 40000 images, labeled at primitive level. The experimental results are promising, showing the benefits of our approach.
%K Optical Music Recognition
%K Recurrent Neural Network
%K Long ShortTerm Memory
%U http://refbase.cvc.uab.es/files/BRC2018.pdf
%U http://dx.doi.org/10.1007/978-3-030-02284-6_7
%P 81-95