Automatic Music Completion Based on Joint Optimization of Harmony Progression and Voicing

Abstract

This paper proposes automatic music completion-the automatic generation of music pieces from any incomplete fragments of music-as a new class of music composition assistance tasks. This is a generalization of conventional music information problems such as automatic melody generation and harmonization. The goal is to turn musical ideas of a user into music pieces, allowing users to quickly explore new ideas and enabling inexperienced users to create their own music. This principle is applicable to a wide variety of music, and as a first step, we present a system that automatically fills in missing parts of a four-part chorale, as well as the underlying harmony progression. The user can input any combination of melody fragments, and freely constrain the harmony. Our system searches for harmonies and melodies that adhere to music-theoretical principles, which requires extensive knowledge and practice for human composers. Accounting for the mutual influence of melodic and harmonic development in music composition, the system is based on a joint model of harmony and voicing. The system was evaluated by analyzing generated music with respect to music theory, in addition to a subjective evaluation experiment. The readers are invited to experiment with our system at http://160.16.202.131/music completion.

A Parameterized Harmony Model for Automatic Music Completion

“…We have previously used Dijkstra's algorithm to explore the search space [28], which, however, is infeasible for the presented model. We have improved the computation speed by implementing a beam search algorithm [31], but this still has the drawback that sometimes certain harmonies become too dominant. For example, in a section with few constraints, almost all voicing candidates remaining in the beam can belong to a single harmony.…”