Alexa Can Recognize Multiple Voices

Amazon’s Alexa now offers voice recognition that can tell the difference between family members’ voices.

Users can set up voice recognition using the Echo, Echo Dot or Echo Show. Family members are then asked to read aloud 10 phrases, and Alexa will use that data to create a voice profile, which will work across other Echo devices and most third-party Alexa-enabled devices.

“Once you set up the feature, Alexa will learn your voice (versus your spouse/partner/roommate’s voice) and be able to deliver a more personalized experience,” a company spokesperson told The Verge. “Today the feature is available for calling/messaging, flash briefing, shopping and the Amazon Music Unlimited Family Plan, and it’ll be rolling out to additional Alexa features in the future.”

The company noted that the voice recognition will get smarter the more it’s used, and also revealed that touch-to-talk devices, such as Fire TV remote and the Amazon Tap, do not support voice profiles.

In April, Google announced that Google Home had gained the ability to recognize individual voices, supporting up to six different accounts on the same smart speaker. Google Home is able to tailor its answers for each person and can use voice activation to determine from which account to pull data. According to The Verge, Google can make voice comparisons in a matter of milliseconds.

“We ask you to say the phrases ‘Ok Google’ and ‘Hey Google’ two times each,” the company explained. “Those phrases are then analyzed by a neural network, which can detect certain characteristics of a person’s voice. From that point on, anytime 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.”