Jingle blobs, jingle blobs, jingle all the way! Need an extra dose of holiday cheer? Look no further than the Blob Opera, Google’s latest, festive machine learning experiment!
Crafted by artist David Li in conjunction with Google’s Arts and Culture team, the Blob Opera features four colorful Blob singers in the roles of soprano, mezzo-soprano, tenor and bass. As users drag Blobs around the screen, the singers harmonize, changing notes and vowel sounds as snow falls gently around them, teaching both basic music theory and opera in the process.
You can direct your own Blob Opera on Google’s Arts and Culture site here.
“We developed a machine learning model trained on the voices of four opera singers in order to create an engaging experiment for everyone, regardless of musical skills. Tenor, Christian Joel, bass Frederick Tong, mezzo‑soprano Joanna Gamble and soprano Olivia Doutney recorded 16 hours of singing,” reads a message from Google on the Blob Opera site.
“In the experiment you don’t hear their voices, but the machine learning model’s understanding of what opera singing sounds like, based on what it learnt from them.”
Using the machine learning algorithms, users can even approximate their own wordless operas on screen, record their work and share it with friends
And that’s not all: with the click of a couple buttons on the bottom right-hand corner of the screen, the Blobs don Santa hats, ready to sing operatic renditions of classic Christmas carols like “Silent Night,” “O Come All Ye Faithful,” “Once in Royal David’s City” and “Hark! The Herald Angels Sing.”