Marine mammal vocal recognition method based on one-dimensional convolutional neural network

The invention discloses a marine mammal sounding recognition method based on a one-dimensional convolutional neural network, which comprises the following steps: firstly, preprocessing a sounding sample of a marine mammal, secondly, designing the one-dimensional convolutional neural network which can be used for marine mammal sounding recognition, and directly recognizing a sound signal. The interference of the step of converting the sound signal into the image on the recognition result is avoided, and compared with the original two-dimensional convolutional neural network, the one-dimensional convolutional neural network designed by the invention has higher recognition efficiency and better recognition performance. 本发明公开了一种基于一维卷积神经网络的海洋哺乳动物发声识别方法，首先对海洋哺乳动物的发声样本进行了预处理，其次设计了可用于海洋哺乳动物发声识别的一维卷积神经网络，直接对声信号进行识别，避免了将声信号转化为图像的步骤对识别结果带来的干扰，相较于原有的二维卷积神经网络，本发明设计的一维卷积神经网络拥有更高的识别效率和更良好的识别性能。