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

Authors :: Sarnatskyi, Vladyslav
Ovcharenko, Vadym
Tkachenko, Mariia
Stirenko, Sergii
Gordienko, Yuri
Rojbi, Anis
Source :: International Journal of Systems Applications Engineering and Development, 11, 212-215 (2017)
Publication Year :: 2017
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.<br />Comment: 4 pages, 3 figures

Subjects :: Computer Science - Sound
Computer Science - Learning
Electrical Engineering and Systems Science - Audio and Speech Processing

Database :: arXiv
Journal :: International Journal of Systems Applications Engineering and Development, 11, 212-215 (2017)
Publication Type :: Report
Accession number :: edsarx.1712.03228
Document Type :: Working Paper

Tools