Ethoacoustic By Bayesian Non Parametric And Stochastic Neighbor Embedding To Forecast Anthropic Pressure On Dolphins

Marine mammals are found in every sea worldwide and are at the highest level of the marine food chain. They communicate among themselves through sounds. It is complicated to study and to characterize these populations because they spend most of their time below the surface. Nevertheless, it is possible to analyze, characterize and classify different cetacean species through the use of bioacoustics. Our study focuses on the Pantropical spotted dolphin (Stenella attenuata), in particular on the influence of nautical tourism, i.e. whale-watching boats, in the Caribbean Sea on dolphin communications. The objective of this study was to observe the correlation between dolphin behaviours and whistles. The most appropriate methods had to be implemented in order to analyze ethoacoustic data. To achieve this, we compared a manual method with an automatic whistle detector. Then, we used different methods of projection (ACP and t-SNE) to reduce the dimension of acoustic data. We concluded by clustering the sounds versus the behavioural classes. The results showed that our automatic method was effective as different clusters were identified : pantropical spotted dolphin do not communicate in the same manner when they are surrounded by whale-watching boats, or during socialization. Therefore, acoustic survey is an efficient non-intrusive way to characterize the form of communication and to evaluate impacts of noise on cetaceans. Our method is effective and provides opportunities for acoustic surveys of anthropophonic pollution.