Interactive Music Generation with Positional Constraints using Anticipation-RNNs

TL;DR

This paper presents Anticipation-RNN, a novel neural network architecture that enables interactive music generation by enforcing user-defined positional constraints, making RNNs more suitable for creative applications.

Contribution

Introduction of Anticipation-RNN, allowing RNNs to incorporate positional constraints during sequence generation for interactive music composition.

Findings

Efficient sampling comparable to traditional RNNs.

Successful generation of constrained melodies in Bach style.

Enables real-time, interactive music creation.

Abstract

Recurrent Neural Networks (RNNS) are now widely used on sequence generation tasks due to their ability to learn long-range dependencies and to generate sequences of arbitrary length. However, their left-to-right generation procedure only allows a limited control from a potential user which makes them unsuitable for interactive and creative usages such as interactive music generation. This paper introduces a novel architecture called Anticipation-RNN which possesses the assets of the RNN-based generative models while allowing to enforce user-defined positional constraints. We demonstrate its efficiency on the task of generating melodies satisfying positional constraints in the style of the soprano parts of the J.S. Bach chorale harmonizations. Sampling using the Anticipation-RNN is of the same order of complexity than sampling from the traditional RNN model. This fast and interactive generation of musical sequences opens ways to devise real-time systems that could be used for creative purposes.