The neural network wrote music that reflects the sound of various Russian cities

Platforma, a developer of big data-based business solutions, and Tele2, a mobile operator, presented the music of Russian cities created by a neural network. The first five compositions reflect the sound of Moscow, St. Petersburg, Nizhny Novgorod, Arkhangelsk and Kazan.

Artificial intelligence generated melodies based on a photo of the city, a three-dimensional landscape map and various geodata. So, from the horizon line, the neural network made a waveform so that it was responsible for the timbre, and the density of the concentration of residents in the areas was converted into a sequencer that helped put the notes in their places.

After that, the music was adapted for listening by popular artists from these cities. Among them: Symphony Orchestra of St. Petersburg, beatmaker CVPELLV from Moscow, indie artist Radif Kashapov from Kazan, rapper Ira PSP from Nizhny Novgorod and musician Mikhail Carlos (Devilboy x Carlos) from Arkhangelsk.

Tracks are available on Yandex Music →