Awesome! 🥊

Congrats, awesome work!

Sweet approach! I’ve been exploring something similar, but in a forest context where I want to connect vocal patterns with biodiversity indices. Really curious to see how your audio-visual angle unfolds, especially for grounding calls in behaviour. Great work!!

Super cool! What kind of analytics and insights are you looking for in the audio signatures?

Another stranger here, but as a fellow PhD student I still wanna send some internet fist bumps 👊

Thanks for sharing! Great battery of people.

When you have a hammer everything looks like a nail!

Super cool. Im trying out using a transformer pretrained on the Audioset dataset for feature extraction in a species detection classifier. Should definitely try the birdnet embeddings as well!