Analysis of Social Interaction in Music Performance with Score-Independent Audio Features

Research on analysis of expressive music performance is recently moving its focus from a single player to small music ensembles, extending the analysis to the social interaction among the members of the ensemble. A step in this direction is the definition and the validation of a set of scoreindependent audio features that enable to characterize the social interaction in the ensemble, based on the analysis of the music performance. This paper focuses on the analysis of four different performances of a same music piece performed by a string quartet. The performances differ with respect to factors affecting the social interaction within the ensemble. The analysis aims at evaluating whether and to what extent a set of consolidated score-independent audio features, already employed for analysis of expressive music content and particularly suitable for string instruments, enable to distinguish among such different performances.