Toward Computer-Assisted Understanding of Dynamics in Symphonic Music

Many people enjoy classical symphonic music. Its diverse instrumentation makes for a rich listening experience. This diversity adds to conductors' expressive freedom to shape the sound according to their imagination. As a result, the same piece can sound quite different from one conductor to another. Differences in interpretation might be noticeable to listeners, but they are sometimes hard to pinpoint, presumably because of the acoustic complexity of the sound. This article describes a computational model that interprets dynamics-expressive loudness variations in performances-in terms of the musical score, highlighting differences between performances of the same piece. The authors demonstrate through experiments that the model has predictive power and give examples of conductor idiosyncrasies found by using the model as an explanatory tool. Although the present model is still in active development, it could pave the road for a consumer-oriented companion to interactive classical music understanding. This article is part of a special issue on multimedia technologies for enriched music.