Live data from Hacker News

Thousands of bird sounds visualized using Google machine learning

aiexperiments.withgoogle.com

21–30 of 44 posts

Re: Thousands of bird sounds visualized using Google machine learning

#23
As a birder, this looks like a failed experiment to me. Or I don't understand what their goal was. The groupings make little sense in terms of what these species sound like. I'm guessing that's an artifact of the way they sampled the sounds, losing macro properties. Kind of like grouping the words 'paramour', 'enmity' and 'hamster' together bc they all contain /m/ sound.

Re: Thousands of bird sounds visualized using Google machine learning

#24
post #21
post #19

It doesn't work in Firefox. How rude.

Worked in Firefox for me. However, it was a bit slow to load.

I got:

> Oops, sorry for the tech trouble. For the best experience, view in Chrome browser.

But then, I block some stuff: ads, WebGL, WebRTC, and tracking.

Re: Thousands of bird sounds visualized using Google machine learning

#26
post #15

Unfortunately they only hint at the envisioned application in the video and don't provide any further links, but the idea is amazing: Use sounds to monitor bio-diversity. Imagine we'd not need cameras and lots of luck to "catch" proof of an animals existence but a grid of interconnected omnidirectional microphones. We'd get real time tracking of individual animals in 3D and could have smartphones literally point the…

Somewhat related, but there was a very good talk at MLConf 2017 about using sound to catch illegal logging in the Amazon. Similar premise: collect the sound, analyze the patterns, and classify.

Re: Thousands of bird sounds visualized using Google machine learning

#27
post #15

Unfortunately they only hint at the envisioned application in the video and don't provide any further links, but the idea is amazing: Use sounds to monitor bio-diversity. Imagine we'd not need cameras and lots of luck to "catch" proof of an animals existence but a grid of interconnected omnidirectional microphones. We'd get real time tracking of individual animals in 3D and could have smartphones literally point the…

Somewhat related, but there was a very good talk at MLConf 2017 about using sound to catch illegal logging in the Amazon. Similar premise: collect the sound, analyze the patterns, and classify.

Thanks for the pointer, found the video: https://www.youtube.com/watch?v=VlQyudLKJno
Post reply on HN