Google Arts & Culture has come up with something very fun. I foresee the rest of this Friday dedicated to crafting my masterpiece, but here’s a snippet I created in a minute.
It’s a creation by David Li: “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. 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.”
Girl at the Opera 