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

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.

The Psychological Education Strategy of Music Generation and Creation by Generative Confrontation Network under Deep Learning

“…Lopez Duarte [ 8 ] addressed excessive repetition caused by low interactivity of musical sequences during gameplay by using random or sequential containers with overlapping rules and adaptive mixing parameters. Li and Sung [ 9 ] proposed a conditional GAN method using an initial model. This method can automatically generate complete variable-length music.…”

An Improved Time Series Network Model Based on Multitrack Music Generation

“…The melody composition method could enhance the original GAN based on individual [10]. The INCO-GAN [11] is designed to mainly address two problems: 1) cannot judge when to end the generation by itself; 2) no apparent time relationship between the notes or bars. The automatic music generation is two phases: training and generation.…”

A review of Generative Adversarial Networks (GANs) and its applications in a wide variety of disciplines -- From Medical to Remote Sensing

“…Their proposed Creative-GAN model, uses the Genre Ambiguity Loss to tackle the problem of originality. Li et al [99] presented an inception model-based conditional generative adversarial network approach (INCO-GAN), which allows for the automatic synthesis of complete variable-length music. Their proposed model comprises of four distinct components: a conditional vector Generator (CVG), an inception model-based conditional GAN (INCO-GAN), a time distribution layer and an inception model [154].…”

“…MidiNet [180], MuseGAN [34], Binary Neurons based WGAN-GP [35], GANSYNTH [37], Creative-GAN [158], INCO-GAN [99], Transformer-GANs [121] Table 14. Applications in Music…”