BirdVox, a collaboration between the Cornell Lab of Ornithology and NYU’s Music and Audio Research Laboratory,  aims to investigate machine listening techniques for the automatic detection and classification of free-flying bird species from their vocalizations. The ultimate goal is to deploy a network of acoustic sensing devices for real-time monitoring of seasonal bird migratory patterns, particularly the determination of the precise timing of passage for each species.

Current bird migration monitoring tools rely on information from weather surveillance radar, which provides deep insight into the density, direction, and speed of bird movements but little to no insight into the species actually migrating, and from crowdsourced human observations, made almost exclusively during daytime hours and of limited use for studying nocturnal migratory flights other than by proxy. Automatic bioacoustic analysis is a complementary solution that is both scalable and able to produce species-specific information that is otherwise impossible to obtain. Such techniques have wide-ranging implications in the field of ecology, e.g., for understanding biodiversity and changes in its spatial and temporal distribution, and for monitoring migrating species in areas where potential hazards exist, such as collisions with buildings, planes, communications towers, and wind turbines.