AUTOMATIC CLASSIFICATION OF ENVIRONMENTAL NOISE SOURCES BY STATISTICAL-METHODS

This paper shows how the tools of statistical pattern recognition can be used to create an ''intelligent'' noise monitoring system able to d istinguish between the acoustic signals of different types of environm ental noise sources, e.g., airplanes, cars, or trucks. The basics of s tatistical pattern recognition theory are reviewed in a tutorial fashi on and illustrated on simple acoustical noise recognition examples. Gu idelines for the design, training, and utilization of a pattern classi fication system are provided, The pitfalls of an intuitive, heuristic approach to these tasks are highlighted. Experimental results obtained by an automatic noise recognition system based on a statistical patte rn recognition framework are presented. Finally, possible improvements of this system which are currently being investigated further are dis cussed. (C) 1998 Institute of Noise Control Engineering.