• Corpus ID: 236912863

An Empirical Evaluation of End-to-End Polyphonic Optical Music Recognition

@inproceedings{Edirisooriya2021AnEE,
  title={An Empirical Evaluation of End-to-End Polyphonic Optical Music Recognition},
  author={Sachinda Edirisooriya and Hao-Wen Dong and Julian McAuley and Taylor Berg-Kirkpatrick},
  booktitle={ISMIR},
  year={2021}
}
Previous work has shown that neural architectures are able to perform optical music recognition (OMR) on monophonic and homophonic music with high accuracy. However, piano and orchestral scores frequently exhibit polyphonic passages, which add a second dimension to the task. Monophonic and homophonic music can be described as homorhythmic, or having a single musical rhythm. Polyphonic music, on the other hand, can be seen as having multiple rhythmic sequences, or voices, concurrently. We first… 

Figures and Tables from this paper

Note Detection in Music Teaching Based on Intelligent Bidirectional Recurrent Neural Network

TLDR
Experiments show the network model can significantly improve detection accuracy and can efficiently detect notes in music teaching and has better feature extraction and generalization capabilities.

Note Detection in Music Teaching Based on Intelligent Bidirectional Recurrent Neural Network

  • Ya Yue
  • Computer Science
    Security and Communication Networks
  • 2022
TLDR
Experiments show the network model can significantly improve detection accuracy and can efficiently detect notes in music teaching and has better feature extraction and generalization capabilities.

Improving Deep-Learning-based Optical Music Recognition for Camera-based Inputs

  • W. NgX. Nguyen
  • Computer Science
    2022 IEEE 4th International Conference on Artificial Intelligence Circuits and Systems (AICAS)
  • 2022
TLDR
This study investigates the use of well-known preprocessed techniques and a state-of-the-art deep learning OMR method and concludes that developing OMR algorithms to read camera-based input music scores is plausible and should be further explored.

References

SHOWING 1-10 OF 25 REFERENCES

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

TLDR
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.

End-to-End Optical Music Recognition Using Neural Networks

TLDR
Results obtained depict classification error rates around 2 % at symbol level, thus proving the potential of the proposed end-to-end architecture for OMR.

Camera-PrIMuS: Neural End-to-End Optical Music Recognition on Realistic Monophonic Scores

TLDR
This work evaluates the performance of an end-to-end approach that uses a deep convolutional recurrent neural network (CRNN) over non-ideal image conditions of music scores and confirms that the CRNN is able to successfully solve the task under these conditions, thereby representing a groundbreaking piece of research towards useful OMR systems.

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

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

Optical Music Recognition with Convolutional Sequence-to-Sequence Models

TLDR
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.

Understanding Optical Music Recognition

TLDR
This work provides a robust definition of OMR and its relationship to related fields, analyzes how OMR inverts the music encoding process to recover the musical notation and the musical semantics from documents, and proposes a taxonomy of O MR, with most notably a novel taxonomic of applications.

A Baseline for General Music Object Detection with Deep Learning

TLDR
A baseline for general detection of musical symbols with deep learning is presented and the first time that competing music object detection systems from the machine learning paradigm are directly compared to each other.

Towards Full-Pipeline Handwritten OMR with Musical Symbol Detection by U-Nets

TLDR
This work shows that a U-Net architecture for semantic segmentation combined with a trivial detector already establishes a high baseline for this task, and proposes tricks that further improve detection performance: training against convex hulls of symbol masks, and multichannel output models that enable feature sharing for semantically related symbols.

Handwritten Music Object Detection: Open Issues and Baseline Results

TLDR
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%.

Towards a Universal Music Symbol Classifier

TLDR
This paper presents the approach towards unifying multiple datasets into the largest currently available body of over 90000 musical symbols that belong to 79 classes, containing both handwritten and printed music symbols.