Inspecting and Interacting with Meaningful Music Representations using VAE

Understand

Variational Autoencoders(VAEs) have already achieved great results on image generation and recently made promising progress on music generation.

• However, the generation process is still quite difficult to control in the sense that the learned latent representations lack meaningful music semantics.
• It would be much more useful if people can modify certain music features, such as rhythm and pitch contour, via latent representations to test different composition ideas.
• In this paper, we propose a new method to inspect the pitch and rhythm interpretations of the latent representations and we name it disentanglement by augmentation.