Connectionist system for music interpretation

This paper uses an adaptive technique, the artificial neural network (ANN) for musical interpretation, solving the problems showed by traditional approaches. Human rhythmic perception is studied through several experiments, the suitability of ANN for solving these kind of problems is analyzed compared to other approaches, and a real time connectionist model is presented together with its integration with the musician. This model uses relative inputs and temporal windows for information representation, and it can be used in collaboration with human musicians or independently