# Classical Music Prediction and Composition by means of Variational Autoencoders

## TL;DR

This paper introduces a novel Variational Autoencoder-based model for classical music prediction and composition, capable of representing music in latent space and generating new compositions from limited training data.

## Contribution

The work presents a new approach using VAEs for music prediction and composition, demonstrating effective representation and prediction with small datasets.

## Key findings

- Accurate music representation in latent space
- Effective prediction of future musical values
- Ability to generate new compositions from limited data

## Abstract

This paper proposes a new model for music prediction based on Variational Autoencoders (VAEs). In this work, VAEs are used in a novel way in order to address two different problems: music representation into the latent space, and using this representation to make predictions of the future values of the musical piece. This approach was trained with different songs of a classical composer. As a result, the system can represent the music in the latent space, and make accurate predictions. Therefore, the system can be used to compose new music either from an existing piece or from a random starting point. An additional feature of this system is that a small dataset was used for training. However, results show that the system is able to return accurate representations and predictions in unseen data.