Neural network based classifier and biofeedback device for improving clarinet tone-quality

Abstract

This paper describes an automated tool for classifying tone quality (a quality related to timbre). This tool provides real-time visual feedback to players of clarinet to help improve tone production technique. A neural network architecture is employed to build a graphical biofeedback device that allows the user to immediately `see' what changes in technique lead to better tone-quality. The tone is also classified and probability estimates are shown in a bar graph, giving quantitative feedback to the user.