对非平稳信号进行分段、截取，再对处理过后的短时信号做短时傅里叶变换，分析其频谱特性，并找到各个时间节点的频率特性，以便分析不同事件段内的声音特征，达到区分不同声音的目的。(The nonstationary signals are segmented, and then the interception, the short-time signal after processing the short-time Fourier transform, the analysis of the spe