A symbol-level melody completion based on a convolutional neural network with generative adversarial learning

Kosuke Nakamura, Takashi Nose, Yuya Chiba, Akinori Ito

Research output: Contribution to journalArticlepeer-review

Abstract

In this paper, we deal with melody completion, a technique which smoothly completes partially-masked melodies. Melody completion can be used to help people compose or arrange pieces of music in several ways, such as editing existing melodies or connecting two other melodies. In recent years, various methods have been proposed for realizing high-quality completion via neural networks. Therefore, in this research, we examine a method of melody completion based on an image completion network. We represent melodies as images and train a completion network to complete those images. The completion network consists of convolution layers and is trained in the framework of generative adversarial networks. We also consider chord progression from musical pieces as conditions. From the experimental result, it was confirmed that the network could generate original melody as a completion result and the quality of the generated melody was not significantly worse than the result of a simple example-based melody completion method.

Original languageEnglish
Pages (from-to)248-257
Number of pages10
JournalJournal of information processing
Volume28
DOIs
Publication statusPublished - 2020

Keywords

  • Automatic music composition
  • Convolutional neural networks
  • Generative adversarial networks
  • Melody completion

ASJC Scopus subject areas

  • Computer Science(all)

Fingerprint Dive into the research topics of 'A symbol-level melody completion based on a convolutional neural network with generative adversarial learning'. Together they form a unique fingerprint.

Cite this