Aircraft type recognition of non speech segment in short-wave speech communication

This paper investigates aircraft type recognition of non speech segment in short-wave speech communication. According to physical characteristics of non speech segment acoustic signal in the aircraft cockpit in short-wave speech communication, wavelet packet energy entropy can be used as the features, as well as selecting appropriate skewness and kurtosis, support vector machine(SVM) is used as classifier. The experiment results show that the algorithm combined with wavelet packet energy entropy, skewness and kurtosis can identify the eight kinds of aircrafts at a high accuracy.