🐸 Exciting news! The AnuraSet is out! https://rdcu.be/dqpkC We've just released a new dataset for benchmarking Neotropical anuran calls identification in passive acoustic monitoring. 🎉#PAM #AIforConservation
Comments
Log in with your Bluesky account to leave a comment
📁 The AnuraSet was compiled through a country-wide collaborative PAM program across Brazil 🇧🇷 and comprises 27 hours of expert annotations 👩🏽💻 for 42 different anuran species🐸, providing a rich resource for research and development in the field of acoustic monitoring and ML 🤖💻
🔍 What's in the dataset? AnuraSet includes annotations, deep learning models, and baseline experiments to kickstart your research. The dataset is available under open licenses, promoting reproducible and accessible science 🫱🏼🫲🏾 https://soundclim.github.io/anuraweb/ #OpenScience
🧩 Working on call identification? AnuraSet can be used to benchmark and compare different identification methods. Since tropical acoustic environments are highly complex AnuraSet has the capacity to accelerate the development of robust machine listening models #tech4wildlife
☝🏽But that's not all, in this paper we also highlight the challenges in the field and encourage a culture of collaboration, experimentation, and exploration in machine learning for applied ecology and biodiversity monitoring 🐸🤖 #AIforGood
📥 You can access AnuraSet here: https://soundclim.github.io/anuraweb/ We encourage researchers, ecologists, engineers, and enthusiasts to explore, use, and contribute to this valuable resource. #AIforConservation #ConservationTech
🙏 Special thanks to SoundClim Contributors GEOBON and Microsoft, under the GEO-Microsoft Planetary Computer Programme, Instituto humboldt for their support in creating this dataset. #CienciaCriolla
Comments