Skip to main content Skip to main navigation

Publikation

Flexible and Interpretable Soundscape Analysis for Biodiversity Assessment and Ecosystem Health for Domain Experts

Rida Saghir
In: IUI '25: Proceedings of the 30th International Conference on Intelligent User Interfaces. International Conference on Intelligent User Interfaces (IUI-2025), March 24-27, Cagliari, Italy, Pages 218-221, ISBN 9781450375139, Association for Computing Machinery, New York, NY, United States, 3/2025.

Zusammenfassung

Biodiversity loss is a major threat to global sustainability and achieving conservation goals requires informed governance, which depends on robust biodiversity monitoring. Passive Acoustic Monitoring (PAM) enables scalable, continuous data collection, but the vast amount of unlabelled audio data necessitates efficient analysis techniques. While traditional methods focus on species identification, soundscape analysis provides a broader view of ecosystem health by capturing acoustic diversity, temporal patterns, and human impact. To address these challenges, researchers have explored various feature extraction methods, including acoustic indices, predefined acoustical features (PAFs), and AI-based techniques like self-supervised and transfer learning. However, their effectiveness varies by task at hand, requiring careful selection, comparison and technical domain knowledge. This research focuses on development of a tool for soundscape analysis that allows users to flexibly switch between methods and compare outputs in ecologically meaningful ways. By integrating computational techniques with domain relevant information, this research aims to improve biodiversity monitoring and ecosystem assessment.

Weitere Links