Proceedings of the ACM/IEEE international conference on Human-robot interaction
Swipe: a sawtooth waveform inspired pitch estimator for speech and music
Swipe: a sawtooth waveform inspired pitch estimator for speech and music
IEA/AIE'10 Proceedings of the 23rd international conference on Industrial engineering and other applications of applied intelligent systems - Volume Part I
Hi-index | 0.00 |
We propose a Thereminist robot system that plays the Theremin based on a Theremin's pitch model. The Theremin, which is a 1920s electronic musical instrument, is played by moving a player's hand position in the air without touching it. It is difficult to play the Theremin because the relationship between the hand position and Theremin's pitch (pitch characteristics) is non-linear and varies according to the electromagnetic field (hereafter called environment). These characteristics cause two problems: (1) Adapting to the environment change is required and (2) a naïve design tends to depend on robot's particular hardware. We implement the coarse-to-fine control system on the Thereminist robot using newly proposed two pitch models: parametric and nonparametric ones. The Thereminist robot works as below: first, the robot calibrates the pitch model by parameter fitting with the Levenberg-Marquardt method. Second, the robot moves its hand in a coarse manner by feedforward control based on the pitch model. Finally, the robot adjusts its position by feedback control (Proportional-Integral control). In these steps, the robot can play a required pitch quickly, because the robot moves its hand using the pitch model without listening to the Theremin's sound Thus, the time to play the exact pitch is shorter than when only feedback control is used. Three experiments were conducted to evaluate the robustness against the number of samples, environment change, and types of robots. The results revealed that our pitch model describes using only 12 samples of pitches for estimation of the parameters, and adapts if the environment changes. In addition, our system works on two different robots: HRP-2 and ASIMO.