“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. By dragging one of the blobs higher or lower on your screen you can adjust the pitch of that blob, and any lower voices will harmonise to that pitch. 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. Blob Opera is a Google sound experiment involving 4 'blobs' (bass, tenor, mezzo-soprano and soprano) who harmonise with each other at the click of a mouse. “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. You can direct your own Blob Opera on Google’s Arts and Culture site here. 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.
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!Ĭrafted 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.
0 kommentar(er)
