The Bach Google Doodle is an AI musician which has learned the patterns in over 300 pieces of music from Johann Sebastian Bach, a famous 18th century German composer. The AI musician will take the notes you give it and suggest harmonies in Bach’s style. It takes a melody and creates backing melodies for different instruments that sound pleasing.
Visit the Bach Google Doodle online, put some notes together, press ‘Harmonize’ and see what you think of the result. If you don’t like its first suggestion you can press Harmonize to try again.
How to use it
Once on the page click the large play symbol (a white triangle) to open the doodle, and then again to run the intro demo (which you can skip on later visits).
Use your mouse to place notes at different positions on the five horizontal lines. If you hover over a note an X will appear so you can delete it and place it somewhere else. If you press and hold a note an option will appear to let you sharpen it (raise it by a semitone) or flatten it (lower it by a semitone). You can press the play icon to hear what your composition sounds like. Then press HARMONIZE to activate the AI. It will look at your piece of music and suggest the backing track (harmonies). You can then click a smiley or cross face if you like it or didn’t like it.
Hover your mouse cursor over all the other bits of the page too – there are lots of fun things to play with including some Easter eggs.
About the doodle
🎹 Celebrating Johann Sebastian Bach was Google’s first-ever AI-powered doodle and “is an interactive experience encouraging players to compose a two measure melody of their choice. With the press of a button, the Doodle then uses machine learning to harmonize the custom melody into Bach’s signature music style (or a Bach 80’s rock style hybrid if you happen to find a very special easter egg in the Doodle…”
▶️ You can also watch Google’s short video ‘Behind the Doodle’ on YouTube.
– by Jo Brodie and Paul Curzon, Queen Mary University of London
Subscribe to be notified whenever we publish a new post to the CS4FN blog.
cs4fn 