PLAY-ALONG MAPPING OF MUSICAL CONTROLLERS

We describe our tool for interactively creating musical controller mappings using a "play-along" paradigm, in which a user pretends to play along with a musical score in real-time using an arbitrary input control modality. As the user "performs," a supervised machine learning system builds a training dataset from the user's gestures and the synthesis engine's current parameters. After one or more training stages, the algorithm learns a mapping from user inputs to synthesis parameters. Control is transferred to the user, who can then control the synthesis in real-time.