Abstract
Piano reduction is a sheet music that is arranged for piano performance while retaining as much information as possible on a song composed of multiple parts, such as an orchestra. There have been several studies on automatic generation of piano reductions. However, they have had difficulties in dealing with a wide range of genres because they are generated according to predefined rules. Therefore, in this study, we propose a method for automatic generation of piano reduction with enhanced versatility using deep learning. In this system, a CNN-based supervised learning model is used to generate a piano-playable score from a song consisting of multiple parts. We also proposed an algorithm to discriminate the playability of a sheet on the piano and tried to improve the accuracy of the piano reduction. As a result of the evaluation of the generated piano reduction, it was found that the playability was improved.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.