Symbolic Music Loop Generation with VQ-VAE
This work addresses music generation for composers or AI applications, but it is incremental as it builds on existing VQ-VAE methods with specific modifications for loops.
The paper tackles generating 8-bar symbolic music loops by using VQ-VAE with discrete representations and repetitive latent features, achieving results that better capture musical properties compared to other models.
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.