Score Analyzer: Extracting performance information for instrumental e-learning

Today, most musical scores can be downloaded on the Web, often for free. However, beginners can have difficulties in finding a score appropriate to their level, and should often rely on themselves to start out on the chosen piece. In this instrumental e-Learning context, we propose a Score Analyzer service in order to automatically extract difficult parts within a MusicXML piece and suggest advice thanks to a Musical Sign Base (MSB). To do so, we first study how teachers introduce a piece to their students and propose a corresponding descriptive logic. We then identify seven criteria to characterize technical instrumental difficulties and propose methods to extract them from a MusicXML score. These criteria are implemented in a Score Analyzer prototype. Its first results are confronted to pianists' estimations. Finally we discuss the integration of this work to @-MUSE, a collaborative score annotation platform based on multimedia contents indexation.