On the Joint Minimization of Regularization Loss Functions in Deep Variational Bayesian Methods for Attribute-Controlled Symbolic Music Generation

This repository contains the code for the paper On the Joint Minimization of Regularization Loss Functions in Deep Variational Bayesian Methods for Attribute-Controlled Symbolic Music Generation, submitted to EUSIPCO 2025 and currently under review.

The project makes use of the Resolv libraries to generate the dataset and train the models.

The dataset is currently available on Zenodo.