Query-based Deep Improvisation
This work addresses music generation for composers or AI artists, but it is incremental as it builds on existing VAE methods with a query-based approach.
The paper tackles the problem of generating structured music by querying a VAE trained on a specific style with input from a different style, resulting in new music that blends query aspects with the network's style, using a noisy channel for control.
In this paper we explore techniques for generating new music using a Variational Autoencoder (VAE) neural network that was trained on a corpus of specific style. Instead of randomly sampling the latent states of the network to produce free improvisation, we generate new music by querying the network with musical input in a style different from the training corpus. This allows us to produce new musical output with longer-term structure that blends aspects of the query to the style of the network. In order to control the level of this blending we add a noisy channel between the VAE encoder and decoder using bit-allocation algorithm from communication rate-distortion theory. Our experiments provide new insight into relations between the representational and structural information of latent states and the query signal, suggesting their possible use for composition purposes.