Residual Recurrent CRNN for End-to-End Optical Music Recognition on Monophonic Scores

Abstract

Optical Music Recognition is a field that attempts to extract digital information from images of either the printed music scores or the handwritten music scores. One of the challenges of the Optical Music Recognition task is to transcript the symbols of the camera-captured images into digital music notations. Previous end-to-end model, based on deep leanring, was developed as a Convolutional Recurrent Neural Network. However, it does not explore sufficient contextual information from full scales and there is still a large room for improvement. In this paper, we propose an innovative endto-end framework that combines a block of Residual Recurrent Convolutional Neural Network with a recurrent Encoder-Decoder network to map a sequence of monophonic music symbols corresponding to the notations present in the image. The Residual Recurrent Convolutional block can improve the ability of the model to enrich the context information while the number of parameter will not be increasing. The experiment results were benchmarked against a publicly available dataset called CAMERA-PRIMUS. We evaluate the performances of our model on both the images with ideal conditions and that with non-ideal conditions. The experiments show that our approach surpass the state-of-the-art end-to-end method using Convolutional Recurrent Neural Network.

A Sequence-to-Sequence Framework Based on Transformer With Masked Language Model for Optical Music Recognition

“…Baró et al [20] explored the application of LSTM which helps in keeping the context dependence of symbols in OMR. In [21], a recurrent residual convolutional neural network was developed, and its experiments proved that this model has significant improvement than the up-to-date CRNN model.…”