Recent Advances of Computational Intelligence Techniques for Composing Music
Yu-Wei Wen, Chuan-Kang Ting
Abstract
Music exerts a ubiquitous influence on human cultures and daily lives. Composing music is deemed rather complicated because it involves various factors (e.g., instruments, melodies, percussions, and chords) needed to be well coordinated for creating harmony, tension, and emotions. Computational intelligence (CI) has shown its effectiveness in solving complex problems, such as optimization, data modeling, and reasoning. In light of the advantages of CI, a considerable amount of research has been proposed to incorporate CI techniques into music composition applications. The literature shows that evolutionary computation and neural network are very popular in this research area. The present survey reviews the recent studies on music composition using CI techniques, to reflect the methodological advances in the past decade. Particularly, this survey stresses two trends: 1) an increasing interest in deep learning for music composition and 2) the deepened engagement of synergizing domain knowledge, music data, and human interaction. In addition, we provide a taxonomy to classify these studies and discuss the research challenges and future directions.