BirdSet: A Multi-Task Benchmark for Classification in Computational Avian Bioacoustics

1 code implementation • 15 Mar 2024 • Lukas Rauch, Raphael Schwinger, Moritz Wirth, René Heinrich, Jonas Lange, Stefan Kahl, Bernhard Sick, Sven Tomforde, Christoph Scholz

Data fragmentation and opacity across studies complicate a comprehensive evaluation of model performance.

BIRB: A Generalization Benchmark for Information Retrieval in Bioacoustics

1 code implementation • 12 Dec 2023 • Jenny Hamer, Eleni Triantafillou, Bart van Merriënboer, Stefan Kahl, Holger Klinck, Tom Denton, Vincent Dumoulin

The ability for a machine learning model to cope with differences in training and deployment conditions--e. g. in the presence of distribution shift or the generalization to new classes altogether--is crucial for real-world use cases.

Information Retrieval Representation Learning +1

Global birdsong embeddings enable superior transfer learning for bioacoustic classification

1 code implementation • 12 Jul 2023 • Burooj Ghani, Tom Denton, Stefan Kahl, Holger Klinck

With the advent of deep learning models, classification of important signals from these datasets has markedly improved.

Audio Classification Decision Making +1

Parsing Birdsong with Deep Audio Embeddings

no code implementations • 20 Aug 2021 • Irina Tolkova, Brian Chu, Marcel Hedman, Stefan Kahl, Holger Klinck

Monitoring of bird populations has played a vital role in conservation efforts and in understanding biodiversity loss.

Recognizing Birds from Sound - The 2018 BirdCLEF Baseline System

3 code implementations • 19 Apr 2018 • Stefan Kahl, Thomas Wilhelm-Stein, Holger Klinck, Danny Kowerko, Maximilian Eibl

Reliable identification of bird species in recorded audio files would be a transformative tool for researchers, conservation biologists, and birders.

BIG-bench Machine Learning Bird Audio Detection