Hands-On Music Generation with Magenta

Hands-On Music Generation with Magenta

Section 1: Introduction to Artwork Generation
Section 2: Music Generation with Machine Learning
Section 3: Training, Learning, and Generating a Specific Style
Section 4: Making Your Models Interact with Other Applications

Latent Space Interpolation with MusicVAE

In this chapter, we'll learn about the importance of continuous latent space of Variational Autoencoders (VAEs) and its importance in music generation compared to standard Autoencoders (AEs). We'll use the MusicVAE model, a hierarchical recurrent VAE, from Magenta to sample sequences and then interpolate between them, effectively morphing smoothly from one to another. We'll then see how to add groove, or humanization, to an existing sequence using the GrooVAE model. We'll finish by looking at the TensorFlow code used to build the VAE model.

The following topics will be covered in this chapter:

  • Continuous latent space in VAEs
  • Score transformation with MusicVAE and GrooVAE
  • Understanding TensorFlow code
Unlock full access

Continue reading with a subscription

Packt gives you instant online access to a library of over 7,500 practical eBooks and videos, constantly updated with the latest in tech

End of Section 1

Your notes and bookmarks