From Optical Music Recognition to Handwritten Music Recognition: A baseline

@article{Bar2019FromOM,
  title={From Optical Music Recognition to Handwritten Music Recognition: A baseline},
  author={Arnau Bar{\'o} and Pau Riba and Jorge Calvo-Zaragoza and Alicia Forn{\'e}s},
  journal={Pattern Recognit. Lett.},
  year={2019},
  volume={123},
  pages={1-8}
}

Figures and Tables from this paper

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

This paper explores 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 and demonstrates that the approach is promising, especially when compared with long short-term memory neural networks.

Approaching End-to-End Optical Music Recognition for Homophonic Scores

The results prove that the serialized ways of encoding the music content are appropriate for Deep Learning-based OMR and they deserve further study.

Exploiting the Two-Dimensional Nature of Agnostic Music Notation for Neural Optical Music Recognition

This work considers two Convolutional Recurrent Neural Network schemes trained to simultaneously extract the shape and height information and to propose different policies for eventually merging them at the actual neural level to solve the OMR task at a staff-line level.

State-of-the-Art Model for Music Object Recognition with Deep Learning

This paper proposes an end-to-end detection model based on a deep convolutional neural network and feature fusion that is able to directly process the entire image and then output the symbol categories and the pitch and duration of notes.

Optical Music Recognition: State of the Art and Major Challenges

This paper reviews relevant works in OMR, including fundamental methods and significant outcomes, and highlights different stages of the OMR pipeline, which often lack standard input and output representation and standardised evaluation.

Handwritten Music Recognition Improvement through Language Model Re-interpretation for Mensural Notation

This paper tries to make a complete recognition system directly from the scores, using techniques that enhance information obtained from symbols, and explores other language model interpretations and test the proposal on a publicly available dataset.

On the Integration of Language Models into Sequence to Sequence Architectures for Handwritten Music Recognition

After studying various Language Model integration techniques, the experimental evaluation on historical handwritten music scores shows a significant improvement over the state of the art, showing that this is a promising research direction for dealing with such difficult manuscripts.

Music Score Recognition and Composition Application Based on Deep Learning

  • Mingheng Liang
  • Computer Science
    Mathematical Problems in Engineering
  • 2022
A deep learning-based music score recognition model is proposed that employs a deep network, accepts the entire score image as input, and outputs the note's time value and pitch directly.

Generative Adversarial Network for Musical Notation Recognition during Music Teaching

  • Na Li
  • Computer Science
  • 2022
This work improves the generative adversarial network to enhance the recognition accuracy and e€ciency of music short scores and has the best recognition accuracy in the monophonic spectrum and the miscellaneous spectrum which is better than the machine learning method.

References

SHOWING 1-10 OF 32 REFERENCES

CVC-MUSCIMA: a ground truth of handwritten music score images for writer identification and staff removal

This paper presents the CVC-MUSCIMA database and ground truth of handwritten music score images, especially designed for writer identification and staff removal tasks and provides some baseline results for easing the comparison between different approaches.

Towards Self-Learning Optical Music Recognition

A new approach to solve OMR is proposed by investigating how humans read music scores and by imitating that behavior with machine learning, which can be performed at high rates of confidence which is comparable to the performance of humans on the same task.

Handwritten Music Object Detection: Open Issues and Baseline Results

This work proposes an end-to-end trainable object detector for music symbols that is capable of detecting almost the full vocabulary of modern music notation in handwritten music scores and shows that a machine learning approach can be used to accurately detect music objects with a mean average precision of over 80%.

Optical Music Recognition by Long Short-Term Memory Networks

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.

Towards the Recognition of Compound Music Notes in Handwritten Music Scores

This work proposes a method based on perceptual grouping for the recognition of compound music notes and has been tested using several handwritten music scores of the CVC-MUSCIMA database and compared with a commercial Optical Music Recognition software.

The MUSCIMA++ Dataset for Handwritten Optical Music Recognition

  • Jan HajicPavel Pecina
  • Computer Science
    2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR)
  • 2017
Ground truth in MUSCIMA++ is a notation graph, which analysis shows to be a necessary and sufficient representation of music notation, and is designed and collected, a new dataset for OMR.

Optical Music Recognition with Convolutional Sequence-to-Sequence Models

A deep learning architecture called a Convolutional Sequence-to-Sequence model is presented to both move towards an end- to-end trainable OMR pipeline, and apply a learning process that trains on full sentences of sheet music instead of individually labeled symbols.

Deep Watershed Detector for Music Object Recognition

This paper introduces a novel object detection method, based on synthetic energy maps and the watershed transform, called Deep Watershed Detector (DWD), specifically tailored to deal with high resolution images that contain a large number of very small objects and is therefore able to process full pages of written music.

Handwritten Music Recognition for Mensural Notation: Formulation, Data and Baseline Results

A labeled corpus containing 576 staves is presented, along with a baseline recognition system based on a combination of hidden Markov models and N-gram language models, for mensural notation, one of the most widespread varieties of Western classical music.

End-to-End Neural Optical Music Recognition of Monophonic Scores

This work studies the use of neural networks that work in an end-to-end manner by using a neural model that combines the capabilities of convolutional neural Networks, which work on the input image, and recurrent neural networks, which deal with the sequential nature of the problem.