Google Magenta’s Lo-Fi Player to produce your virtual music room
A latest Google Magenta project designed by an intern gives you mix lo-fi, hip-hop music tracks to build a custom music room in your browser, with no musical ability needed.
Magenta is planned to use Google’s machine learning systems for the creation of art and music, and the Lo-Fi Player is a fun sample of what it can do.
When you begin Lo-Fi Player, you’re taken to a pixellated virtual “room” where you click various objects a clock, a cat, or a piano, for instance in the room to improve the different tracks, like the bass line and the melody.
“The view outside the window relates to the background sound in the track, and you can adjust both the visual and the music by clicking on the window,” Lo-Fi Player creator Vibert Thio addressed in a blog post.
Lo-Fi Player also has an interactive YouTube stream, a “shared space” where people can be in the same music room collectively. But alternatively of clicking on elements in the room, players type commands into the live chat window to replace the tracks.
Magenta is powered by Google’s open-source TensorFlow system, part of a continuing research project “exploring the role of machine learning as a tool in the artistic process.” Other Magenta projects have entered the Piano Genie, an AI program that lets anyone “play” the piano think Guitar Hero and NSynth. This machine-learning algorithm uses a neural network to learn and create new sounds.
The Lo-Fi Player is customizable; its source code can be found on GitHub, and Thio states the team also built a tutorial called “Play, Magenta!” where users can edit sounds and canvas live in their browsers.
Thio also emphasizes that Lo-Fi Player isn’t meant to replace human producers or to be lo-fi hip hop streams. “Think of it more like a prototype for an interactive music piece or an interactive introduction to the genre to improve people acknowledge the art even more,” he says.