Wavelet technology can be used to extract the characteristics of the signal in each frequency band. The multi-scale spatial energy distribution feature extraction method based on wavelet transform is to analyze the frequency band of the signal, and then use the calculated energy of each frequency band as the feature vector:
signal The dyadic wavelet decomposition of f(t) can be expressed as:
f(t)=A^j + ΣD^j
其中A^j 表示近似信号为信号的低频部分，D^j为细节信号，为高频部分
The total energy of the signal is:
E= EA^j + ΣED^j
选择第j层的近似信号和各层的细节信号的能量作为特征构成特征向量
F=[EAj，ED1,ED2,....,EDj]
The wavelet transform can be used to extract the features of the acoustic signal, and extract the vector data that can represent the acoustic signal, that is, the transformation from the acoustic signal to the feature vector data is completed.
In python, Scipy provides some signal processing functions, but they are not comprehensive. A better signal processing library is PyWavelets (pywt)