Google Home Smart Speaker Adds Multi-User Support Via Personalized Voice Recognition
Google has enhanced Google Home by allowing up to six people to attach their accounts to the device. Most importantly, Google Home will automatically distinguish your voice from that of your other family members (or roommates), so that when you say “OK Google”, only results pertaining to your account preferences are played back.
So how does Google identify your voice and match it to your account? It all comes down to the company’s powerful neural networks which analyze how you say the phrases “OK Google” or “Hey Google”. This “training” process takes place when you link your account to Google Home.
“Those phrases are then analyzed by a neural network, which can detect certain characteristics of a person's voice,” writes Google Assistant Product Manager Yury Pinsky. “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.”
Amazon is widely regarded as being the most full-featured and capable of all the AI smart speakers on the market with its Echo family, but multi-user support on the Google Home gives the search giant a key advantage over its rivals.
Google says that multi-user support is arriving today for U.S. users, and will be enabled in the United Kingdom “in the coming months”.