Cross-domain Sound Recognition for Efficient Underwater Data Analysis

arXiv:2309.03451v2 Announce Type: replace-cross
Abstract: This paper presents a novel deep learning approach for analyzing massive underwater acoustic data by leveraging a model trained on a broad spectrum of non-underwater (aerial) sounds. Recognizing the challenge in labeling vast amounts of underwater data, we propose a two-fold methodology to accelerate this labor-intensive procedure.
The first part of our approach involves PCA and UMAP visualization of the underwater data using the feature vectors of an aerial sound recognition model. This enables us …

abstract aerial analysis arxiv challenge cs.lg cs.sd data data analysis deep learning domain eess.as labeling labor massive methodology novel paper recognition sound spectrum type underwater vast