PLDA in i-vector based underwater acoustic signals classification

• Published in: Ships and offshore structures Vol. 19; no. 3; pp. 366 - 374
• Main Authors: Song, Yongqiang, Liu, Feng, Shen, Tongsheng
• Format: Journal Article
• Language: English
• Published: Cambridge Taylor & Francis 03.03.2024; Taylor & Francis Ltd
• Subjects: Artificial neural networks; Coefficients; Deep learning; Discriminant analysis; long short-term memory; Machine learning; Marine resources; probabilistic discriminant analysis methods; Probabilistic models; Recognition; Signal classification; Underwater; underwater acoustic signal processing; Underwater acoustics
• ISSN: 1744-5302; 1754-212X
• DOI: 10.1080/17445302.2023.2169066

Intelligent recognition of underwater acoustic targets is crucial for exploiting marine resources. In this paper, we propose a deep learning method for underwater acoustic signal recognition consisting of three steps: Firstly, we extract the underwater acoustic signal's identification vector (i-vector) using a Gaussian mixture model. Secondly, we construct a probabilistic linear discriminant analysis (PLDA) model that divides the i-vector into two segments, Finally, we used a multi-long short-term memory neural network (MLSTMNN) to learn the features, outputting the underwater acoustic signal labels through the softmax layer. Experiments using the ShipsEar dataset can obtain a recognition rate of 84.8%; compared to the traditional Mel frequency Cepstral Coefficients (MFCC) and convolutional neural networks, the recognition rate greatly improved.