This note presents a system that learns expressive and idiosyncratic gesture variations for gesture-based interaction. The system is used as an interaction technique in a music conducting scenario where gesture variations drive music articulation. A simple model based on Gaussian Mixture Modeling is used to allow the user to configure the system by providing variation examples. The system performance and the influence of user musical expertise is evaluated in a user study, which shows that the model is able to learn idiosyncratic variations that allow users to control articulation, with better performance for users with musical expertise.

Body movement has received increasing attention in music technology research during the last years. Some new musical interfaces make use of gestures to control music in a meaningful and intuitive way. A typical approach is to use the orchestra conducting paradigm, in which the computer that generates the music would be a \textit{virtual orchestra} conducted by the user. However, although conductors' gestures are complex and their meaning can vary depending on the musical context, this context-dependency is still to explore. We propose a method to study context-dependency of body and facial gestures of conductors in orchestral classical music based on temporal clustering of gestures into actions, followed by an analysis of the evolution of audio features after action occurrences. For this, multi-modal data (audio, video, motion capture) will be recorded in real live concerts and rehearsals situations using unobtrusive techniques.