Due to the poor visibility of the deep-sea environment, acoustic signals are often collected and analyzed to explore the behavior of marine species. With the progress of underwater signal-acquisition technology, the amount of acoustic data obtained from the ocean has exceeded the limit that human can process manually, so designing efficient marine-mammal classification algorithms has become a research hotspot. In this paper, we design a classification model based on a multi-channel parallel structure, which can process multi-dimensional acoustic features extracted from audio samples, and fuse the prediction results of different channels through a trainable full connection layer. It uses transfer learning to obtain faster convergence speed, and introduces data augmentation to improve the classification accuracy. The k-fold cross-validation method was used to segment the data set to comprehensively evaluate the prediction accuracy and robustness of the model. The evaluation results showed that the model can achieve a mean accuracy of 95.21% while maintaining a standard deviation of 0.65%. There was excellent consistency in performance over multiple tests.
Keywords: convolutional neural network; data augmentation; feature extraction; marine mammal classification; transfer learning.