If you were around in 2013, you may recall that we told you about Cornell’s Archive of 150,000 Bird Calls and Animal Sounds, with Recordings Going Back to 1929. It’s a splendid place for ornithologists and bird lovers to spend time. And, it turns out, the same also applies to computer programmers.
Late last year, Google launched an experiment where, drawing on Cornell’s sound archive, they used machine learning (artificial intelligence that lets computers learn and do tasks on their own) to organize thousands of bird sounds into a map where similar sounds are placed closer together. And it resulted in this impressive interactive visualization. Check it out. Or head into Cornell’s archive and do your own old-fashioned explorations.
Note: You can find free courses on machine learning and artificial intelligence in the Relateds below.
If you would like to sign up for Open Culture’s free email newsletter, please find it here. Or follow our posts on Threads, Facebook, BlueSky or Mastodon.
If you would like to support the mission of Open Culture, consider making a donation to our site. It’s hard to rely 100% on ads, and your contributions will help us continue providing the best free cultural and educational materials to learners everywhere. You can contribute through PayPal, Patreon, and Venmo (@openculture). Thanks!
Related Content:
Neural Networks for Machine Learning: A Free Online Course
A Free Course on Machine Learning & Data Science from Caltech
Hello guys,
Such a nice experiment you have made! I’m an ornithologist myself, and I know from practical field experience, that it’s very unusual to hear only 1 bird species singing/calling at the same time (when e.g walking in the forest). Can the AI decipher if another bird is singing in the background of the record, and still identify the targeted species?