A pattern recognition approach to tone detection

A pattern recognition approach is proposed for tone detection. Three basic tone features are extracted from the signal in the form of power, mean frequency, and spectral concentration. These three features are calculated for each signal sample taken during the decision interval and are represented by points in a three dimensional space.The actual tone detection function is then performed by partitioning the feature space in two decision volumes corresponding to the two alternatives (tone present and absent respectively) and by identifying the presence of associated clusters. A reject option is available when the decision volumes are not complementary, and allows the system to be insensitive to very noisy samples (e.g. impulsive noise).A non-linear classification method is presented which provides adaptive and robust detection in presence of non gaussian noise. Moreover global performance may be optimized on-line for unknown or time varying environments.Hardware and Software simulation results are presented and show good performance in presence of impulsive and interference noise.