This device detects different household sounds via tinyML


For people with hearing loss or other hearing problems, maintaining situational awareness can be vital to staying safe and independent. It was this problem that inspired the team of Lucia Camacho Tiemblo, Spiros Kotsikos and Maria Alifieri to create a small device that can alert users to certain household sounds on their phone.

The team decided to incorporate built-in machine learning in order to recognize ambient sounds, so they opted for an Arduino Nano 33 BLE Sense. After recording many samples of various events, such as conversation, door knocking, TV, doorbell, and silence, they fed them into a tinyML model with the help of Edge Impulse’s studio. The resulting model successfully differentiated events about 90% of the time.

Beyond simply outputting recognized audio to a serial monitor, the team’s firmware also allows results to be sent via Bluetooth® Low Energy where a connected smartphone can read the data and display it. The mobile application contains three simple buttons to access a list of sounds, some settings and a submenu to manage the connection with the Arduino.

You can read more about this accessibility project here on


Comments are closed.