The cocktail party algorithm is one of the most widely used algorithms for source separation of sound. The algorithm aims to find an automated solution for a problem that everyone experiences regularly, namely how to make oneself heard in a noisy environment. The cocktail party algorithm picks up the sound from different microphones, and then applies smart filters once the system has determined which sounds originate from the same source.
This problem also becomes topical when developing sensors based on passive sonar, for instance for autonomous aquatic drones who have to develop awareness of ships and other possible obstacles on a busy shipping lane. It is possible to deploy multiple hydrophones to localize sound sources under water, but the system will be hindered considerably by the sound that the drone itself makes, such as the sound produced by the propellers.
This paper describes a possible solution to the underwater sound filtering problem, using Blind Source Separation. The problem regards splitting sound from a boat engine and the water waves to prove the possibility to extract one sound fragment from the other on the open sea. The illustrations shown further in the report are tests performed in MATLAB to prove the theory.