Aircraft Type Recognition Based on Shortwave Speech Communication with Auditory Perception

This paper studies aircraft type recognition based on shortwave speech communication. Frequency bands are selected based on wavelet packet decomposition (WPD), considering Bark scale with auditory masking properties, which combines with physical properties of the target acoustic signal simultaneously. Support vector machine (SVM) is used as classifier. The simulation results of aircraft type recognition have shown that WPD based on Bark scale combining with physical properties (BWPD) can extract the robust feature of aircraft cabin background sound and identify the five kinds of aircrafts with high recognition rate. BWPD-SVM has achieved more excellent performance and higher recognition rate than MFCC-SVM and WPD-HOC-SVM.