Multiple acoustic source localization using deep data association

Deep learning-based DOA estimation using CRNN for underwater acoustic arrays

“…In recent years, the availability of big data has enabled machine learning and deep learning to be employed in research domains such as image processing, speech processing, and acoustic signal processing (Wang et al, 2019;Bai et al, 2019;Bai et al, 2021;Chen et al, 2022;Bai et al, 2022). Various methodologies based on deep learning have been highly effective in solving classification, localization, association, and functional approximation tasks (Ayub et al, 2021;Desai and Mehendale, 2022;Ayub et al, 2022). Deep learning has recently been applied to the estimation of various parameters from acoustic signals in an underwater environment using sonar array systems (Niu et al, 2017;Ferguson et al, 2017;Houeǵnigan et al, 2017;Wang and Peng, 2018;Bianco et al, 2019;Shen et al, 2020;Ozanich et al, 2020).These studies show that deep learning performs exceptionally well in comparison to traditional methods.…”