用于石斑鱼声音高效分类的迁移学习。

Transfer learning for efficient classification of grouper sound.

作者信息

Ibrahim Ali K, Zhuang Hanqi, Chérubin Laurent M, Schärer-Umpierre Michelle T, Nemeth Richard S, Erdol Nurgun, Ali Ali Muhamed

机构信息

Harbor Branch Oceanographic Institute, Florida Atlantic University, 5600 US1 North, Fort Pierce, Florida 34946, USA.

Department of Computer and Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, Florida 33431, USA.

出版信息

J Acoust Soc Am. 2020 Sep;148(3):EL260. doi: 10.1121/10.0001943.

DOI:10.1121/10.0001943

PMID:33003883

Abstract

A transfer learning approach is proposed to classify grouper species by their courtship-associated sounds produced during spawning aggregations. Vessel sounds are also included in order to potentially identify human interaction with spawning fish. Grouper sounds recorded during spawning aggregations were first converted to time-frequency representations. Two types of time frequency representations were used in this study: spectrograms and scalograms. These were converted to images, and then fed to pretrained deep neural network models: VGG16, VGG19, Google Net, and MobileNet. The experimental results revealed that transfer learning significantly outperformed the manually identified features approach for grouper sound classification. In addition, both time-frequency representations produced almost identical results in terms of classification accuracy.

摘要

提出了一种迁移学习方法，通过石斑鱼在产卵聚集期间发出的求偶相关声音对石斑鱼种类进行分类。还纳入了船只声音，以便有可能识别人类与产卵鱼类的互动。在产卵聚集期间记录的石斑鱼声音首先被转换为时频表示。本研究使用了两种时频表示：频谱图和小波尺度图。这些被转换为图像，然后输入到预训练的深度神经网络模型：VGG16、VGG19、谷歌网络和MobileNet。实验结果表明，迁移学习在石斑鱼声音分类方面明显优于手动识别特征方法。此外，就分类准确率而言，两种时频表示产生的结果几乎相同。