Representing Musical Genre: A State of the Art

TLDR

Musical genre is a widely used descriptor and crucial metadata for large music databases, yet it is intrinsically ill‑defined, with attempts to define it often resulting in circular, ungrounded projections, raising questions about whether it is an intrinsic attribute of titles or an extrinsic description of the whole piece. The article reviews approaches to representing musical genre and proposes a classification into manual, prescriptive, and emergent categories. The authors evaluate the pros and cons of each approach and illustrate their analysis with results from the Cuidado IST project. The study demonstrates that the Cuidado IST project provides empirical evidence on the strengths and weaknesses of manual, prescriptive, and emergent genre representation approaches.

Abstract

Abstract Musical genre is probably the most popular music descriptor. In the context of large musical databases and Electronic Music Distribution, genre is therefore a crucial metadata for the description of music content. However, genre is intrinsically ill-defined and attempts at defining genre precisely have a strong tendency to end up in circular, ungrounded projections of fantasies. Is genre an intrinsic attribute of music titles, as, say, tempo? Or is genre a extrinsic description of the whole piece? In this article, we discuss the various approaches in representing musical genre, and propose to classify these approaches in three main categories: manual, prescriptive and emergent approaches. We discuss the pros and cons of each approach, and illustrate our study with results of the Cuidado IST project.