Scripps Institution of Oceanography, University of California San Diego, La Jolla, California 92037, USA.
Naval Undersea Warfare Center Newport, Newport, Rhode Island 02841, USA.
J Acoust Soc Am. 2021 Apr;149(4):2587. doi: 10.1121/10.0004221.
Deep clustering was applied to unlabeled, automatically detected signals in a coral reef soundscape to distinguish fish pulse calls from segments of whale song. Deep embedded clustering (DEC) learned latent features and formed classification clusters using fixed-length power spectrograms of the signals. Handpicked spectral and temporal features were also extracted and clustered with Gaussian mixture models (GMM) and conventional clustering. DEC, GMM, and conventional clustering were tested on simulated datasets of fish pulse calls (fish) and whale song units (whale) with randomized bandwidth, duration, and SNR. Both GMM and DEC achieved high accuracy and identified clusters with fish, whale, and overlapping fish and whale signals. Conventional clustering methods had low accuracy in scenarios with unequal-sized clusters or overlapping signals. Fish and whale signals recorded near Hawaii in February-March 2020 were clustered with DEC, GMM, and conventional clustering. DEC features demonstrated the highest accuracy of 77.5% on a small, manually labeled dataset for classifying signals into fish and whale clusters.
深度聚类被应用于无标签的、自动检测到的珊瑚礁音景信号中，以区分鱼类脉冲声和鲸鱼歌声的片段。深度嵌入聚类（DEC）使用信号的固定长度功率谱图学习潜在特征并形成分类聚类。还提取了手工挑选的光谱和时间特征，并使用高斯混合模型（GMM）和传统聚类进行聚类。DEC、GMM 和传统聚类在具有随机带宽、持续时间和 SNR 的鱼类脉冲声（fish）和鲸鱼歌声单元（whale）模拟数据集上进行了测试。GMM 和 DEC 都实现了很高的准确性，并识别出了包含鱼类、鲸鱼以及鱼类和鲸鱼重叠信号的聚类。在具有不等大小聚类或重叠信号的情况下，传统聚类方法的准确性较低。2020 年 2 月至 3 月在夏威夷附近记录的鱼类和鲸鱼信号使用 DEC、GMM 和传统聚类进行了聚类。在一个用于将信号分类为鱼类和鲸鱼聚类的小型、手动标记数据集上，DEC 特征的准确率最高，达到了 77.5%。
