Analyzing the ocean acoustic environment is a tricky task. Background noise and variable channel transmission environment make it complicated to implement accurate ship-radiated noise recognition. Existing recognition systems are weak in addressing the variable underwater environment, thus leading to disappointing performance in practical application. In order to keep the recognition system robust in various underwater environments, this work proposes an adaptive generalized recognition system - AGNet (Adaptive Generalized Network). By converting fixed wavelet parameters into fine-grained learnable parameters, AGNet learns the characteristics of underwater sound at different frequencies. Its flexible and fine-grained design is conducive to capturing more background acoustic information (e.g., background noise, underwater transmission channel). To utilize the implicit information in wavelet spectrograms, AGNet adopts the convolutional neural network with parallel convolution attention modules as the classifier. Experiments reveal that our AGNet outperforms all baseline methods on several underwater acoustic datasets, and AGNet could benefit more from transfer learning. Moreover, AGNet shows robust performance against various interference factors.

翻译：分析海洋声学环境是一项具有挑战性的任务。背景噪声和变化的信道传输环境使得实现精确的舰船辐射噪声识别变得复杂。现有识别系统在处理多变的海洋环境方面存在不足，导致实际应用中性能不佳。为了在各种水下环境中保持识别系统的鲁棒性，本文提出了一种自适应广义识别系统——AGNet（自适应广义网络）。通过将固定小波参数转换为细粒度可学习参数，AGNet能够学习不同频率下水声信号的特征。其灵活且细粒度的设计有助于捕获更多背景声学信息（如背景噪声、水下传输信道）。为充分利用小波谱图中的隐含信息，AGNet采用并行卷积注意力模块的卷积神经网络作为分类器。实验表明，AGNet在多个水声数据集上优于所有基线方法，且能更有效地从迁移学习中获益。此外，AGNet在多种干扰因素下展现出稳定的性能。