From the site:
Blob Opera is a machine learning experiment by David Li in collaboration with Google Arts and Culture.
This experiment pays tribute to and explores the original musical instrument: the voice. Play four opera voices in real time. No singing skills required!
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.
How it works:
Drag the blobs up and down to change pitch. Or forwards and backwards for different vowel sounds. Another machine learning model lets the blobs respond to and harmonise your input in real time.
Click the Christmas Tree for a holiday surprise based on the top searched Christmas Carols of the year.
With special thanks to:
Tenor Christian Joel, bass Frederick Tong, mezzo-soprano Joanna Gamble and soprano Olivia Doutney. Additional singing from Ingunn Gyda Hrafnkelsdottir and John Holland-Avery.
Blob Opera is an experiment using the latest web audio technology and may not perform optimally on older devices. If you're on a mobile device, why not try a desktop one!
A little example created by me: https://g.co/arts/auePwVjiLntSjvdX9
Have fun! Cheers !