Modeling Music as Synchronized Time Series: Application to Music Score Collections

Capture d’écran 2026-07-15 à 17.25.14

Music is a temporal organization of sounds, and we can therefore assume that any repre- sentation of music content has a structure that reflects some conceptual and organisational principles. This structure is hardly explicitly accessible in many encodings, such as for instance audio files. However, it appears much more clearly in the notation of music.
We thus propose to use the music notation language as a framework to model the content of digital music objects, whatever their specific encoding. We describe an algebra that leverages this structured music representation to extract, restructure, and combine large collection of such objects. The data model leverages the hidden structure of digital music encodings to permit sophisticated manipulations of their content.
We apply the model to music scores collections, taking advantage of the precise represen- tation of music structure that can be found in digital notation. We describe a system, based on an extension of XQuery with our algebra, that provides search, restructuration, extrac- tion, and analytic services on top of large collections of XML-encoded digital scores. Beyond its application to music objects, our work shows how one can build on a structured content embedded in a complex XML encoding to develop robust collection management tools with minimal implementation effort.

Raphaël Fournier-S'niehotta, Philippe Rigaux, Nicolas Travers:
Modeling Music as Synchronized Time Series: Application to Music Score Collections. Inf. Syst. 73: 35-49 (2018) https://doi.org/10.1016/j.is.2017.12.003

Laisser un commentaire