Musical state representation for imitating human players by a robotic acoustic musical device

The objective in our work is to develop a robotic acoustic musical device ROMI that jointly plays two instruments that belong to two different classes, improvises while assisting others in an orchestral performance and also learns to imitate human players in a duet This intelligence in imitation also provides player identification and performance training. In this paper we introduce the robotic device ROMI together with its control architecture and focus on our musical state representation and automatic parameter estimation for imitation of duo players by ROMI.