Symbolic Music Loop Generation with VQ-VAE

Abstract

Music is a repetition of patterns and rhythms. It can be composed by repeating a certain number of bars in a structured way. In this paper, the objective is to generate a loop of 8 bars that can be used as a building block of music. Even considering musical diversity, we assume that music patterns familiar to humans can be defined in a finite set. With explicit rules to extract loops from music, we found that discrete representations are sufficient to model symbolic music sequences. Among VAE family, musical properties from VQ-VAE are better observed rather than other models. Further, to emphasize musical structure, we have manipulated discrete latent features to be repetitive so that the properties are more strengthened. Quantitative and qualitative experiments are extensively conducted to verify our assumptions.

References in corpus (12)

• Auto-Encoding Variational Bayes
• Decoupled Weight Decay Regularization
• Neural Discrete Representation Learning
• Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
• A Hierarchical Latent Vector Model for Learning Long-Term Structure in Music
• MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompaniment
• Jukebox: A Generative Model for Music
• A Comprehensive Survey on Deep Music Generation: Multi-level Representations, Algorithms, Evaluations, and Future Directions
• Learning to Groove with Inverse Sequence Transformations
• Learning a Latent Space of Multitrack Measures
• Deep Learning for Multi-label Classification
• Vector Quantized Contrastive Predictive Coding for Template-based Music Generation