The entropy series and neurons firing series of the image obtained by feeding the spectrogram into PCNN were used as the characteristics of emotion speech for emotion recognition.

• 该方法将语音转化为语谱图后输入到PCNN，得到输出图像的神经元点火序列及其熵序列作为语音情感的特征，利用其特征实现语音情感识别。