Google Home can now be trained to identify the different voices of people you live with. Today Google announced that its smart speaker can support up to six different accounts on the same device. With this you’ll finally have the Home tailored to your voice and be able to sleep at night knowing no one is going to mess up your Spotify recommendation because they wanted to listen to something you wouldn’t. Training the thing to tell people apart sounds rather easy, and Google is using neural networks to identify who’s who, which if I do say so myself is pretty freaking cool! Now how do you train it, read the follow from Google’s Blog post and find out.
We ask you to say the phrases “Ok Google” and “Hey Google” two times each. Those phrases are then analyzed by a neural network, which can detect certain characteristics of a person’s voice. 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 we can understand if it’s you speaking or not. This comparison takes place only on your device, in a matter of milliseconds.
Neural networks crazy right? Yeah I’d say so. Multi-user support is rolling out in the United States today and will expand to the UK over the coming weeks. Just make sure you’ve got the latest version of the Google Home app, as that’s required to set it up. Remember this is for different voices, so personal and work it can’t tell the difference…yet. Give Google some time and we might have something down the road.