A variational autoencoder for music generation controlled by tonal tension
This work addresses the need for controllable music generation systems for musicians and composers, though it is incremental as it builds on existing VAE methods with added tension control.
The researchers tackled the problem of uncontrollable music generation by neural networks by developing a variational autoencoder that incorporates tonal tension measures, enabling control over the direction and level of tonal tension in generated music while preserving rhythmic similarity to a seed fragment.
Many of the music generation systems based on neural networks are fully autonomous and do not offer control over the generation process. In this research, we present a controllable music generation system in terms of tonal tension. We incorporate two tonal tension measures based on the Spiral Array Tension theory into a variational autoencoder model. This allows us to control the direction of the tonal tension throughout the generated piece, as well as the overall level of tonal tension. Given a seed musical fragment, stemming from either the user input or from directly sampling from the latent space, the model can generate variations of this original seed fragment with altered tonal tension. This altered music still resembles the seed music rhythmically, but the pitch of the notes are changed to match the desired tonal tension as conditioned by the user.