Neural Translation of Musical Style

TL;DR

This paper presents a neural model capable of performing sheet music with expressive variations, producing performances indistinguishable from human musicians, effectively passing a musical Turing test.

Contribution

It introduces a neural approach to perform sheet music with human-like expressiveness, capturing performance nuances typically added by musicians.

Findings

Generated performances are indistinguishable from human performances.

The model successfully captures expressive elements like dynamics and tempo.

Passes a musical Turing test.

Abstract

Music is an expressive form of communication often used to convey emotion in scenarios where "words are not enough". Part of this information lies in the musical composition where well-defined language exists. However, a significant amount of information is added during a performance as the musician interprets the composition. The performer injects expressiveness into the written score through variations of different musical properties such as dynamics and tempo. In this paper, we describe a model that can learn to perform sheet music. Our research concludes that the generated performances are indistinguishable from a human performance, thereby passing a test in the spirit of a "musical Turing test".