PopMNet: Generating structured pop music melodies using neural networks

Recently, many deep learning models have been proposed to generate symbolic melodies. However, generating pop music melodies with well organized structures remains to be challenging. In this paper, we present a melody structure-based model called PopMNet to generate structured pop music melodies. The melody structure is defined by pairwise relations, specifically, repetition and sequence, between all bars in a melody. PopMNet consists of a Convolutional Neural Network (CNN)-based Structure Generation Net (SGN) and a Recurrent Neural Network (RNN)-based Melody Generation Net (MGN). The former generates melody structures and the latter generates melodies conditioned on the structures and chord progressions. The proposed model is compared with four existing models AttentionRNN, LookbackRNN, MidiNet and Music Transformer. The results indicate that the melodies generated by our model contain much clearer structures compared to those generated by other models, as confirmed by human behavior experiments.