Tracking Conductor of an Orchestra Using Artificial Neural Networks

Live performance using a combination of musicians and electronics has so far been problematic art. Getting the two components to create a coherent sound is a major problem. Automatic conductor following is one way to do this. In this case, the conductor can control the electronics as one controls the musicians. Conductor following requires multiple information technology tools. Pattern recognition techniques are used to recognize the gestures (movements) conductor makes. The identiied gestures need to be matched with general knowledge of the conducting technique and the knowledge of the piece being conducted. Finally the conductor follower must create musical, expressive output. Little research has been done on this eld. Most systems only track the tempo of the piece. Few can track dynamics or ner nuances like staccato. Our main research goal is interpreting the tempo of the conductor and reacting musically in real-time. A multi-layer perceptron network is used to estimate the phase of the conductor motion. This enables very accurate tracking with fast reaction. An oscillator is used to track slow tempo changes when accurate tracking is not necessary. Applications of this technology include conductor training, live performance and music synthesis control.