Skip to main content Skip to main navigation

Publication

Enhancing Biodiversity Monitoring: An Interactive Tool for Efficient Identification of Species in Large Bioacoustics Datasets

Hannes Kath; Ilira Troshani; Bengt Lüers; Thiago Gouvea; Daniel Sonntag
In: ICMI Companion '24: Companion Proceedings of the 26th International Conference on Multimodal Interaction. ACM International Conference on Multimodal Interaction (ICMI-2024), 26th International Conference on Multimodal Interaction, November 4-8, Costa Rica, Pages 91-93, ICMI, Association for Computing Machinery, 2024.

Abstract

Biodiversity loss is a major challenge for humanity, which has increased the rate of species extinction by a factor of 100-1000 compared to pre-industrial times. XPRIZE Rainforest is a competition focused on developing a pipeline for real-time biodiversity measurement: teams have 24 hours to collect data and another 48 hours to produce a list of species present in the data. Passive acoustic monitoring (PAM) is a scalable technology for data acquisition in wildlife monitoring. However, analyzing large PAM datasets poses a significant challenge. This paper presents a tool used by the Brazilian team during the XPRIZE Rainforest finals. Using a combination of audio separation, weakly supervised learning, transfer learning, active learning, multiple-instance learning, and novel class detection, samples are carefully selected and presented to the user for annotation.