The monitoring of migratory fish is essential to evaluate the state of the fish population in freshwater and follow its evolution. During spawning in rivers, some species of alosa produce a characteristic splash sound, called “bull”, that enables to perceive their presence.
The French Association Migrateurs Rhône Méditerranée provide an important effort to aurally count these bulls throughout the night from different sites on the river banks of the Rhone basin.
In order to reduce the human costs and expand the scope of study, I propose a deep learning approach for audio event detection from recordings made from the river banks.
See the published paper here: Fish migration monitoring from audio detection with CNNs.
This paper was presented at AudioMostly21 using this video made by the projet team.