Blob Opera, a delightful machine learning and music experiment

David Li created the Blob Opera, a wonderful creative experiment at the intersection of machine learning, music, and digital art. From the project description at Google Arts & Culture, hosts of the project:

This experiment pays tribute to and explores the original musical instrument: the voice. 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 many hours of singing. In the experiment you don't hear their voices, but rather the machine learning model's understanding of what opera singing sounds like, based on what it learned from the opera singers.

The resulting experiment allows you to play Blob Opera, altering pitch & vowel sounds to create your own composition. The blobs respond and harmonise to your input in real time.