INCO-GAN: Variable-Length Music Generation Method Based on Inception Model-Based Conditional GAN

Shuyu Li,Yunsick Sung

doi:10.3390/math9040387

Abstract

Deep learning has made significant progress in the field of automatic music generation. At present, the research on music generation via deep learning can be divided into two categories: predictive models and generative models. However, both categories have the same problems that need to be resolved. First, the length of the music must be determined artificially prior to generation. Second, although the convolutional neural network (CNN) is unexpectedly superior to the recurrent neural network (RNN), CNN still has several disadvantages. This paper proposes a conditional generative adversarial network approach using an inception model (INCO-GAN), which enables the generation of complete variable-length music automatically. By adding a time distribution layer that considers sequential data, CNN considers the time relationship in a manner similar to RNN. In addition, the inception model obtains richer features, which improves the quality of the generated music. In experiments conducted, the music generated by the proposed method and that by human composers were compared. High cosine similarity of up to 0.987 was achieved between the frequency vectors, indicating that the music generated by the proposed method is very similar to that created by a human composer.

Highlights

Music composition is a creative task for humans that requires some familiarity with music theory
The process and result of the conditional vectors generation method based on conditional vector generator (CVG) and the music generation method based on INCO-generative adversarial networks (GAN)
The accuracy and loss value obtained during the training process were utilized to determine whether the CVG and INCO-GAN were trained well

Summary

Introduction

Music composition is a creative task for humans that requires some familiarity with music theory. To enable machines to compose music like human composers, many studies utilize deep learning techniques. There are two major problems that need to be overcome for effective automatic music generation via machine learning [1]. The temporal relationship of notes or bars in music must be considered. A single note or bar has no meaning, as in the case of a sentence containing only a single word. The task of automatic music generation is to learn how to arrange the selected notes. One must consider the connection between multiple tracks in music. When music is being played by different players or instruments, it is divided into different tracks. When multiple tracks are played together, the interrelationship between their respective notes becomes very complicated

Objectives

Methods

Results

Discussion

Conclusion