Symbolic Music Loop Generation with VQ-VAE

11/15/2021
by   Sangjun Han, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

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
08/17/2020

PIANOTREE VAE: Structured Representation Learning for Polyphonic Music

The dominant approach for music representation learning involves the dee...
research
06/17/2016

Learning Interpretable Musical Compositional Rules and Traces

Throughout music history, theorists have identified and documented inter...
research
12/21/2022

Polytopic Analysis of Music

Structural segmentation of music refers to the task of finding a symboli...
research
10/21/2019

On large-scale genre classification in symbolically encoded music by automatic identification of repeating patterns

The importance of repetitions in music is well-known. In this paper, we ...
research
03/17/2002

NetNeg: A Connectionist-Agent Integrated System for Representing Musical Knowledge

The system presented here shows the feasibility of modeling the knowledg...
research
05/16/2023

Discrete Diffusion Probabilistic Models for Symbolic Music Generation

Denoising Diffusion Probabilistic Models (DDPMs) have made great strides...

Please sign up or login with your details

Forgot password? Click here to reset