In non-cooperation communication, speech suppression is an important link of aircraft type recognition based on shortwave speech communication. Ensemble mean and ensemble variance for analyzing physical characteristics of aircraft cockpit background sound has been proposed in this paper. Some important peak feature is revealed from the ensemble mean and ensemble variance, which has important guiding significance to further researches on speech suppression of aircraft type recognition based on shortwave speech communication. The two algorithms of speech suppression are proposed which are empirical mode decomposition and wavelet transform(EMD_WT) and the algorithm of ensemble empirical mode decomposition and wavelet packet (EEMD_WP). In the process of speech suppression, EMD_WT produced extra noise pollution, and EEMD_WP kept the aircraft cockpit background sound and weakened the effect of the speech largely. The contrast test proves that EEMD_WP has better performance by in time domain and in frequency domain. In non-cooperation communication, speech suppression is an important link of aircraft type recognition based on shortwave speech communication. Ensemble mean and ensemble variance for analyzing physical characteristics of aircraft cockpit background sound has been proposed in this paper. Some important peak feature is revealed from the ensemble mean and ensemble variance, which has important guiding significance to further researches on speech suppression of aircraft type recognition based on shortwave speech communication. The two algorithms of speech suppression are proposed which are empirical mode decomposition and wavelet transform (EMD_WT) and the algorithm of ensemble empirical mode decomposition and wavelet packet (EEMD_WP). In the process of speech suppression, EMD_WT produced extra noise pollution, and EEMD_WP kept the aircraft cockpit background sound and weakened the effect of the speech largely. The contrast test proves that EEMD_WP has better performance by in time domain and in frequency domain.