discussion / Acoustics  / 28 June 2017

Sound Event Recognition - through collaboration

here's our 90-second video explaining the SERVAL sensor, which saw the light thanks to our collaboration with Karol Piczak.

The 7th of July we'll organize a hackathon with the data science students of the Jheronimous Academy for Data Science (JADS). It's their challenge to outperform our elephant rumbles classifier.

Our first real case is HWC related to elephants, enabled through our collabation with Angela Stoeger, Matthias Zeppenzauer, Peter Wrege, and Blaise Droz. 

Now sit back and enjoy ;-)

https://youtu.be/69AvxTBWIRE

ps anyone interested in helping us to develop the sensor further, for example by training it for wolves, bears, bird species, etc., or simply through funding - you are most welcome!

 




Hi @Jan+Kees . I just came across your post after joining recently. Great stuff! Is there more documentation on how you developed your sound recognition algos? I'm working on something that can detect chainsaws and noticed that is one of the sounds your device detects.

Thanks for any further details!

Matthew

@jankees we have no results to show yet. We are still in the planning phase. I looked on your site but couldn't find any references to code repos. Did I miss them?

 

@jankees,  

Hi I am working on a system to reduce Human Elephant Conflict and am interested in acoustics of Elephants and the identification of elephants through their acoustic signature to assist with this project, did you get anywhere with the serval sensor for detecting Elephants? 

We are a non profit called the Forgotten Parks Foundation and currently managing the Upemba and Kundelungu National Parks in the DR.Congo and have an immediate requirement to reduce HEC so we would like to assist with the development of such a system.