Inspecting and Interacting with Meaningful Music Representations using VAE

04/18/2019
by   Ruihan Yang, et al.
0

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. Based on the interpretable representations, an intuitive graphical user interface is designed for users to better direct the music creation process by manipulating the pitch contours and rhythmic complexity.

READ FULL TEXT

page 4

page 5

research
06/09/2019

Deep Music Analogy Via Latent Representation Disentanglement

Analogy is a key solution to automated music generation, featured by its...
research
06/21/2019

Classical Music Prediction and Composition by means of Variational Autoencoders

This paper proposes a new model for music prediction based on Variationa...
research
08/17/2020

PIANOTREE VAE: Structured Representation Learning for Polyphonic Music

The dominant approach for music representation learning involves the dee...
research
08/11/2022

Symbolic Music Loop Generation with Neural Discrete Representations

Since most of music has repetitive structures from motifs to phrases, re...
research
07/19/2023

Polyffusion: A Diffusion Model for Polyphonic Score Generation with Internal and External Controls

We propose Polyffusion, a diffusion model that generates polyphonic musi...
research
04/15/2019

Are Nearby Neighbors Relatives?: Diagnosing Deep Music Embedding Spaces

Deep neural networks have frequently been used to directly learn represe...
research
08/17/2020

Learning Interpretable Representation for Controllable Polyphonic Music Generation

While deep generative models have become the leading methods for algorit...

Please sign up or login with your details

Forgot password? Click here to reset