


Additional singing from Ingunn Gyda Hrafnkelsdottir and John Holland-Avery.īlob Opera is an experiment using the latest web audio technology and may not perform optimally on older devices. Tenor Christian Joel, bass Frederick Tong, mezzo-soprano Joanna Gamble and soprano Olivia Doutney. Another machine learning model lets the blobs respond to and harmonise your input in real time.

Or forwards and backwards for different vowel sounds. 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.ĭrag the blobs up and down to change pitch. Combine sounds and perform on the opera stage in different cities. By moving them from side to side, you make them sing. Here it is proposed to manage unusual creatures - Blobs. Tenor, Christian Joel, bass Frederick Tong, mezzo-soprano Joanna Gamble and soprano Olivia Doutney recorded 16 hours of singing. In this game, you can feel like a real opera singer, like Christian Joel or Olivia Doutney, who had a hand in creating this creation. We developed a machine learning model trained on the voices of four opera singers in order to create an interactive experiment anyone can enjoy, regardless of musical skills. This experiment pays tribute to and explores the original musical instrument: the voice. How to conduct Blob Opera True, it takes practice, practice, practice to end up in Carnegie Hall, but you only need to be on a device connected to the internet to conduct Blob Opera. Blob Opera is a machine learning experiment by David Li in collaboration with Google Arts and Culture.
