I'll be giving a talk on "Music generation with structural constraints: an operations research approach" at ORBEL30, the national conference of the SOGESCI-BVWB, the Belgian Operational Research (OR) Society, Member of EURO, the association of European OR Societies, and Belgian representative of IFORS (International Federation of OR Societies). The conference is hosted by the Catholic University of Leuven (UCL) at Louvain-la-Neuve on January 27th and 28th.

The conference is intended as a meeting place for researchers, users and potential users of Operational Research, Statistics, Computer Science and related fields. It will provide managers, practitioners and researchers with a unique opportunity to exchange information on quantitative techniques for decision making.

The main focus of the talk is about how the problem of automatically composing music can be formulated as an optimization problem and the different ways in which structural constrains can be incorporated in this approach. The full structured abstract of the talk can be found in the proceedings.

Music generation with structural constraints: an operations research approach.

Dorien Herremans, PhD (MSCA Fellow) Queen Mary University of London

Date/time: January 27th and 28th.
Venue: Catholic University of Leuven (UCL)

Abstract:
Music generation systems have attracted research attention since the advent of computing. They have become increasingly important, bolstered by rising global expenditure on digital music, which was over 64 billion USD in 2014 alone [McKinsey(2010)]. Most music generation systems are based on statistical models and rules. A drawback of these early systems is their inability to synthesize music that possess global structure. When music does not have a clear direction or long-term coherence, it fails to hold the listener’s attention and can be hard to follow. The computing power available to us today provides us with new opportunities to generate good sounding music with structure. This talk will review state systems for generating music with structure, and describe an optimisation-based approach to music generation. The problem of structure has recently been tackled using deep learning, with mixed results. Guaranteed success has been achieved using optimisation algorithms that constrain the structure of the generated music. This approach is currently being examined in the authors’ EU project MorpheuS. link to full structured abstract