Abstract
As a result of our research, the Waseda Flutist Robot has been able of nearly imitating the human flute playing and able of transferring skills to flutist beginners to improve their sound quality. In this paper, the concept of a general transfer skill system (GTSS) towards the implementation of an automated musical teaching tool is presented. The implementation of the perceptual systems of the GTSS is described. A set of experiments were done to verify the effectiveness of each system. As a result, the robot is able of interacting with students more naturally by recognizing melodies and tracking human faces. Furthermore, the robot was also able of evaluating quantitatively the students' performances to detect their improvements (learning curve).
