Classical Music Prediction and Composition by means of Variational Autoencoders
This work addresses music generation for classical compositions, but it is incremental as it applies VAEs in a novel way to a specific domain.
The paper tackles the problem of music prediction and composition by using Variational Autoencoders to represent music in a latent space and predict future values, achieving accurate results with a small dataset on unseen data.
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.