Blob Opera is a machine learning experiment by David Li in collaboration with Google Arts and Culture.
Opera singers use their voices as expressive and beautiful musical instruments. This experiment pays tribute to those voices, as musical instruments anyone can learn how to play. Play four opera voices in real time. No singing skills required!
They collaborated with four opera singers to teach a machine learning model how to sing. Tenor, Christian Joel, bass Frederick Tong, mezzo‑soprano Joanna Gamble and soprano Olivia Doutney recorded 16 hours of singing to train an algorithm called a Convolutional Neural Network. 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.
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 with your input in real time.
Blob Opera – on tour
We’ve seen the blobs do their thing in The Blobpera House, now you can take them on tour. Take the blobs to cities around the world, and find inspiration in the music and landmarks of London, New York, Mexico City, Seoul, Cape Town, and Paris. Hear the blobs sing a curated selection of traditional, classic songs in the public domain from each location.
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!
Journey through the world of performing arts and watch the world’s greatest performers come to life in 360° on