Raspberry Pi Audio Machine Learning with Edge Impulse

In this tutorial you learn how to do use our I2S microphones together with a Raspberry Pi and Edge Impulse to easily create and deploy powerful audio Machine Learning applications.

Requirements

The first step is to go through this guide and make sure that I2S is running on your Raspberry Pi and the I2S microphone is connected.

Getting Started with Edge Impulse

Create an Edge Impulse account

Go to this page and create an Edge Impulse account.

Explore Edge Impulse and create a project

Edge Impulse is very well documented. Read through the documentation to understand how to create a new project.

Add your Raspberry Pi as Edge Impulse device

The Raspberry Pi with our I2S microphone can be added as an input device for your Edge Impulse project. Please follow this guide to understand how this can be done.

• Run the edge-impulse-linux command with the --disable-camera option:

edge-impulse-linux --disable-camera

• Use the arrow up/down keys to select snd_rpi_i2s_car - snd_rpi_i2s_card as microphone.

Get started

Navigate to one of the Edge Impulse examples for Raspberry Pi, e.g.

• Responding to your voice
• Recognize sounds from audio