Dragging the blobs right and left changes the vowels’ sound, the extreme right side represents character ‘o’ and the extreme left represents character ‘a’.Dragging the blobs down decreases the pitch.Dragging the blobs up increases the pitch.The actual voices of the singers are not heard as the machine learning model was made to learn in a way so that it creates a general interactive experience of opera singing artificially. Christian Joel, Tenor, bass Frederick Tong, mezzo‑soprano Joanna Gamble, and soprano Olivia Doutney recorded 16 hours of singing”, which was used as the training dataset for the model. The harmonization is achieved using a “machine learning model trained on the voices of four opera singers for creating an engaging experiment for everyone, regardless of musical skills. The most significant feature is the coordination of the blob voices when they sing together. Four multicolored blobs with different voice features can be controlled and manipulated by the user to create a full-fledged opera-based festive song. In collaboration with Google Arts and Culture, artist David Li has created this interactive machine learning experiment. No more listening to monotonous opera songs when you can create one for yourself using Google’s Blob Opera.
0 kommentar(er)
