Music Generation Powered by Artificial Intelligence

dc.contributor.author	Shyshkin, Oleh
dc.date.accessioned	2019-02-19T16:04:10Z
dc.date.available	2019-02-19T16:04:10Z
dc.date.issued	2019
dc.identifier.citation	Shyshkin, Oleh. Semantic segmentation for visual indoor localization : Master Thesis : manuscript / Oleh Shyshkin ; Supervisor Juan Pablo Maldonado Lopez, Dr. ; Ukrainian Catholic University, Department of Computer Sciences. – Lviv : [s.n.], 2019. – 26 p. : ill.	uk
dc.identifier.uri	http://er.ucu.edu.ua/handle/1/1337
dc.language.iso	en	uk
dc.subject	Music Generation	uk
dc.subject	TCN based models	uk
dc.subject	PerformanceRNN	uk
dc.title	Music Generation Powered by Artificial Intelligence	uk
dc.type	Preprint	uk
dc.status	Публікується вперше	uk
dc.description.abstracten	Music is an essential part of human life in our days. Despite a long history of the phenomena people still explore it and expand the new horizons. For the last ten years quality of computer-generated music significantly improved. State of the art machine learning models like PerformanceRNN can perform music close to a human level. However, it is hard to deal with a generation of long-term music for the systems. In work, we apply a TCN model to a generation music task and evaluate the quality of the music. We show that the models have a significantly better performance than a baseline model for a long-term music generation task. However, it has own weak points in musicality and time generation. We also discuss possible options to resolve the issues.	uk