# Query-based Deep Improvisation

## TL;DR

This paper presents a novel method for generating music by querying a trained VAE with different style inputs, enabling controlled blending of styles and longer-term musical structure.

## Contribution

It introduces a query-based approach to music generation using VAEs, incorporating a noisy channel for style blending control, and offers insights into latent space representations.

## Key findings

- Query-based music generation produces diverse outputs.
- Noisy channel controls style blending effectively.
- Latent space relates to structural and representational information.

## Abstract

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.