Apple's Patent covering the new HomePod Mini's ability to Recognized the Voices of Household Members has Surfaced
When Apple introduced the new HomePod mini, they introduced the foundation for Apple's vision of an interconnected smart home. On Friday Patently Apple posted a report titled "Apple Reveals more of their Smart Home Plan in 6 Patent Filings covering Multi-User Devices in a Connected Home+." In today's report we cover another smart home patent published last Thursday that specifically relates to HomePod mini titled "Voice Identification in Digital Assistant Systems."
Apple's patent relates to Siri identifying users in a multi-user or shared environment like the home. This was introduced during Apple's special virtual event held on November 10, 2020 by Yael Garten, Apple's Director, Siri Data Science and Engineering as featured in our cover graphic. The text on voice recognition at the bottom of the graphic was generated by having English Subtitles turned on.
In a home of full of family members including parents, children, grandparents making a request to Siri to play music or read your messages can get complicated to execute.
As we witnessed during Apple's November 10th virtual event, the HomePod mini introduced the ability for Siri to distinguish the voices of home members and responded personally. In order that to happen, Apple engineers invented a way for HomePod mini to create a plurality of speaker profiles for Siri to respond to.
An example method includes receiving, from one or more external electronic devices, a plurality of speaker profiles for a plurality of users; receiving a natural language speech input; determining, based on comparing the natural language speech input to the plurality of speaker profiles: a first likelihood that the natural language speech input corresponds to a first user of the plurality of users; and a second likelihood that the natural language speech input corresponds to a second user of the plurality of users; determining whether the first likelihood and the second likelihood are within a first threshold; and in accordance with determining that the first likelihood and the second likelihood are not within the first threshold: providing a response to the natural language speech input, the response being personalized for the first user.
A few of Apple's patent figures below illustrate interactions with users in the home. One individual happens to be a guest and Siri politely declines to provide the requested information being sought being that the individual didn't have a personal voice profile registered with Siri's database. Translation: Apple has baked privacy measures right into the HomePod / HomePod mini system based on voice recognition.
Unknown Guest Request
It's a complex invention as you can imagine with many flow charts and method details. Those wishing to dive deeper into the details can check out Apple's patent application 20200380980 here.
Apple's patent application that was published last Thursday was originally filed on March 11, 2020, with a provisional patent on record being filed in late May 2019. Considering this was presented on November 10th in a presentation, it's clear that this is now a patent fulfilled.
Below is the HomePod mini segment set to begin with Yael Garten describing this feature. You can end the video when that segment ends.