Real-time Gesture Mapping in Pd Environment using Neural Networks

In this paper, we describe an adaptive approach to gesture mapping for musical applications. Neural Network abstractions and interfaces are implemented in the Pure Data environment which trains a network automatically and performs a mapping in real-time using trained network parameters. In this paper, we will focus with neural network representations and implementations in a real-time musical environment. This adaptive mapping is evaluated in different static and dynamic situations by a network of sensors sampled at a rate of 200Hz in real-time. Finally, some remarks are given on the network design and future works.