Classyfier

What is it?

The Classyfier is a table that detects the beverages people consume around it and chooses music that fits the situation accordingly. A built-in microphone catches characteristic sounds and then compares these sounds to a catalogue of pre-trained examples. The Classyfier identifies it as belonging to one of three classes; hot beverages, wine or beer. Each class has its own playlist that one can navigate through by knocking on the table.

We have been in particular fascinated by the possibility of interacting with everyday objects and triggering contextual aware devices with the sound of those objects. We soon decided on the beverage table because its a very graphic example, which allowed for us to explore different kinds of interactions with the beverages and the table.

Prototyping

To explore our initial concept further we build a table and experimented with different kinds of interactions using the openFrameworks collection for machine learning by Gene Kogan, as well as Processing and Wekinator to classify sounds and trigger a playlist.

At the exhibition
Training the different classes