Published on November 15, 2016 by Google

Check out g.co/aiexperiments to learn more.

Bird sounds vary widely. This experiment uses machine learning to organize thousands of bird sounds. The computer wasn’t given tags or the birds’ names – only the audio. Using a technique called t-SNE, the computer created this map, where similar sounds are placed closer together. g.co/aiexperiments

Built by Kyle McDonald, Manny Tan, Yotam Mann, and friends at Google Creative Lab. Thanks to Cornell Lab of Ornithology for their support. The sounds are available in the Macaulay Library’s Essential Set for North America. t-SNE animation featured in video by Gene Kogan.

More resources:
github.com/lvdmaaten/bhtsne
www.birds.cornell.edu
macaulaylibrary.org
ml4a.github.io

Leave a Reply

6 Comments on "A.I. Experiments: Bird Sounds"

Notify of
avatar

Bartosz Olszewski
Guest
Bartosz Olszewski
7 days 20 hours ago

I like cheese

Mr. R.A.
Guest
Mr. R.A.
8 days 13 hours ago

Great project!

pim 2558
Guest
pim 2558
11 days 17 hours ago

หนังเอก

607
Guest
607
13 days 7 hours ago

Cool!

mathew cheriyan
Guest
mathew cheriyan
17 days 14 hours ago

this should be made for all animals. that would be cool!

Tiger Tang (Tix)
Guest
Tiger Tang (Tix)
18 days 23 hours ago

Incredible and somehow inspiring. 🙂

wpDiscuz