English

Music Transcription by Deep Learning with Data and "Artificial Semantic" Augmentation

Sound 2017-12-12 v1 Machine Learning Audio and Speech Processing

Abstract

In this progress paper the previous results of the single note recognition by deep learning are presented. The several ways for data augmentation and "artificial semantic" augmentation are proposed to enhance efficiency of deep learning approaches for monophonic and polyphonic note recognition by increase of dimensions of training data, their lossless and lossy transformations.

Keywords

Cite

@article{arxiv.1712.03228,
  title  = {Music Transcription by Deep Learning with Data and "Artificial Semantic" Augmentation},
  author = {Vladyslav Sarnatskyi and Vadym Ovcharenko and Mariia Tkachenko and Sergii Stirenko and Yuri Gordienko and Anis Rojbi},
  journal= {arXiv preprint arXiv:1712.03228},
  year   = {2017}
}

Comments

4 pages, 3 figures

R2 v1 2026-06-22T23:12:41.680Z