Ural Federal University named after the first President of Russia B.N. Yeltsin, Yekaterinburg, Russia
Volume 2020 (7),
Article ID 36174520,
AI, Data Mining and Data-Driven Solutions in Different Fields: 36AI 2020
Abstract
This article provides a brief summary on graph and network-based models of melody. It describes how to use these models for arrangement generation and how to compare results obtained with different generation methods. The comparison may be based on characteristics of a graph representing an original piece and graphs of generated arrangements.
Two main goals of this article are: to provide a formal description of existing models and generation methods in terms of stochastic processes and to introduce the new methods of comparing musical tracks using their graph representation.