Passive acoustic monitoring is a method that is commonly used to collect long-term data on soniferous animal presence and abundance. However, these large datasets require substantial effort for manual analysis; therefore, automatic methods are a more effective way to conduct these analyses and extract points of interest. In this study, an energy detector and subsequent pre-trained neural network were used to detect and classify six fish call types from a long-term dataset collected in the northern Gulf of Mexico. The development of this two-step methodology and its performance are the focus of this paper. The energy detector by itself had a high recall rate (>84%), but very low precision; however, a subsequent neural network was used to classify detected signals and remove noise from the detections. Image augmentation and iterative training were used to optimize classification and compensate for the low number of training images for two call types. The classifier had a relatively high average overall accuracy (>87%), but classifier average recall and precision varied greatly for each fish call type (recall: 39–91%; precision: 26–94%). This coupled methodology expedites call extraction and classification and can be applied to other datasets that have multiple, highly variable calls.

The larval and post-larval forms of many marine organisms, such as oysters, crabs, lobster, coral, and fish, utilize ambient acoustic cues to orient, settle, or metamorphose. In this study, the effect of anthropogenic and ambient sounds on the orientation behavior of four larval estuarine fishes was examined in a controlled, laboratory experiment. Pre-settlement size red drum Sciaenops ocellatus, southern flounder Paralichthys lethostigma, spotted seatrout Cynoscion nebulosus, and Florida blenny Chasmodes saburrae larvae were exposed to four sound treatments—control, estuarine soundscape, seismic airguns, and large-ship passage—in a linear acoustic chamber. Initial significant (p < 0.05) avoidance of airguns was observed in three of the four species (all but the Florida blenny), but habituation to this sound occurred as the experiment progressed. All species avoided ship passage sounds; however, the avoidance behavior was not significant. Interestingly, none of the species studied were significantly attracted to the acoustic cues alone of the estuarine soundscape; in fact, three of the four species spent less time near the speaker when it was broadcast. These results suggest that larval fish can potentially habituate to anthropogenic noise relatively quickly (<10 min). Understanding how sounds affect larval behavior is necessary because successful recruitment ultimately affects a population's success.

Long-term passive acoustic monitoring datasets can require substantial effort for manual analysis; therefore, automatic methods are a more effective way to conduct these analyses and extract calls of interest. In this study, acoustic recordings from the northern Gulf of Mexico, about 60 km north of the 2010 Deepwater Horizon oil spill location, collected between July 2010 and May