Applying speech technology to the ship-type classification problem

Ship classification is the task of automatically classifying a ship into one of several predefined categories using features that are derived from a collected underwater sonar signal. In this paper, we follow a cross-disciplinary approach, where tools and methodologies from speech processing are used to tackle this problem. The corpus that we use was collected by the Scripps Institution of Oceanography, UCSD, with a single-hydrophone setup, over the course of nine years. Of that corpus, we use data from 1861 ships for our research. We present our methodology for feature extraction, ship detection, and the classification of ships into a number of ship types. To demonstrate the effectiveness of our approach, we compare our results with an implementation based on the method in [1]. We also report on a series of controlled experiments that measure the effect of different parameter settings in the feature generation and classification stages.