Multiple user support is one of Google Home’s key differentiators from competing speaker assistant devices. After launching in the US earlier this year, it is now expanding internationally, starting with the UK.
Multi-user detection allows several users to share a Google Home and get personalized Assistant results. Touted at I/O 2017, Google leverages neural networks to recognize voice samples and detect certain attributes of a user’s speech:
From that point on, any time you say “Ok Google” or “Hey Google” to your Google Home, the neural network will compare the sound of your voice to its previous analysis so it can understand if it’s you speaking or not. This comparison takes place only on your device, in a matter of milliseconds.
Set-up is simple and starts by linking another Google account — up to six — to Google Home. Afterwards, users will be asked to speak the phrases “Ok Google” and “Hey Google” two times each.
In the Google Home app, users can then link music and other streaming accounts, as well as set preferences for Google Assistant and other features, like commute times and the daily briefing.
At I/O, Google announced a plethora of new upcoming features for Home, including proactive notifications, Bluetooth streaming, and hands-free calling. These features should be arriving in the coming year.