Raspberry Pi 3 Based Neural Network Music box

• Tweet
• Pin It

Raspberry Pi enthusiast Aleksey Tikhonov has published details of his new Raspberry Pi project to create a Neural Network RaspberryPi Music box.

All the experience gained in Aleksey’s past projects, a Raspberry pi 3 and Leadsound’s speaker have led to this new project.

After making the Pianola network project, I came to the idea of the RaspberryPi music box for the infinite neural network music generation.

Basically, I used the same VAE-like neural network approach as in our Neyro-Skryabin performance, but I had to squeeze it into a raspPi3 box and tune the model to make the near real-time NN-generation of an endless stream of midi music.

As a hardware, I took a RaspberryPi 3 Starter Kit and some Leadsound’s speaker like this. As a software, I had to setup Tensorflow for ARMv7l and used mido+pygame to play the music aloud.

Further information of the Neural Network RaspberryPi Music box can be found in the video below.

Related Posts

• 

  Autofocus Glasses/Phoropter Using Variable Focus Liquid Lens
  Autofocus Glasses/Phoropter Using Variable Focus Liquid Lens
• Home Automation & Lights controlling System
  Home Automation & Lights controlling System
• 

  “Listen to temperatures” with TinyML
  “Listen to temperatures” with TinyML
• 

  An inexpensive FM receiver for the Raspberry Pi
  An inexpensive FM receiver for the Raspberry Pi