Multi-user personalization at a voice interface device

Abstract

A method at an electronic device with one or more microphones and a speaker includes receiving a first voice input; comparing the first voice input to one or more voice models; based on the comparing, determining whether the first voice input corresponds to any of a plurality of occupants, and according to the determination, authenticating an occupant and presenting a response, or restricting functionality of the electronic device.

What is claimed is: 
     
         1 . A method performed by a computing system, the method comprising: receiving a first voice input associated with a request for a service;
 determining whether the first voice input corresponds with any of a plurality of occupants based on a comparison of the first voice input to one or more voice models trained to each of the plurality of occupants;   in accordance with a determination that the first voice input corresponds to a first occupant of the plurality of occupants, causing, at an electronic device, a personalized response to the request to be presented, the personalized response being personalized for the first occupant; and   in accordance with a determination that the first voice input corresponds to none of the plurality of occupants, causing functionality of the electronic device to be restricted.   
     
     
         2 . The method of  claim 1 , wherein the request is a request for a music service, the personalized response is based on a user account associated with a subscription to the music service, and causing the functionality of the electronic device to be restricted comprises causing a generic response that does not involve the user account associated with the subscription to the music service to be presented. 
     
     
         3 . The method of  claim 2 , further comprising:
 receiving a second voice input;   comparing the second voice input to the one or more voice models;   determining that the second voice input corresponds to a second occupant of the plurality of occupants; and   causing, at the electronic device, a personalized response to the second voice input to be presented, the personalized response being personalized for the second occupant.   
     
     
         4 . The method of  claim 1 , wherein the request is a request for personal information, the personalized response includes the requested personal information with respect to the first occupant, and causing the functionality of the electronic device to be restricted comprises acting on only requests that involve non-personal information. 
     
     
         5 . The method of  claim 4 , wherein the response is an audible response including personal account data in numerical form, and presenting the response comprises:
 receiving the audible response from a content host; and   outputting the audible response.   
     
     
         6 . The method of  claim 4 , further comprising:
 determining the request based on the first voice input; and   generating the response in accordance with the determined request.   
     
     
         7 . The method of  claim 6 , wherein:
 the determined request includes a request to the electronic device to awaken; and   the response includes an audible greeting, wherein the audible greeting includes an indication of an identity of the first occupant.   
     
     
         8 . The method of  claim 6 , wherein:
 the personal information includes an email, a calendar event, or a bank balance; and   generating the personalized response in accordance with the determined request comprises obtaining the requested personal information with respect to the first occupant.   
     
     
         9 . The method of  claim 4 , further comprising:
 receiving a second voice input;   comparing the second voice input to the one or more voice models;   determining that the second voice input corresponds to a second occupant of the plurality of occupants; and   causing, at the electronic device, a personalized response to the second voice input to be presented, the personalized response being personalized for the second occupant.   
     
     
         10 . A computing system comprising:
 a hardware processor that is configured to:
 receive a first voice input associated with a request for a service; 
 determine whether the first voice input corresponds with any of a plurality of occupants based on a comparison of the first voice input to one or more voice models trained to each of the plurality of occupants; 
 in accordance with a determination that the first voice input corresponds to a first occupant of the plurality of occupants, cause, at an electronic device, a personalized response to the request to be presented, the personalized response being personalized for the first occupant; and 
 in accordance with a determination that the first voice input corresponds to none of the plurality of occupants, cause functionality of the electronic device to be restricted. 
   
     
     
         11 . The computing system of  claim 10 , wherein the request is a request for a music service, the personalized response is based on a user account associated with a subscription to the music service, and causing the functionality of the electronic device to be restricted comprises causing a generic response that does not involve the user account associated with the subscription to the music service to be presented. 
     
     
         12 . The computing system of  claim 11 , wherein the hardware processor is further configured to:
 receive a second voice input;   compare the second voice input to the one or more voice models;   determine that the second voice input corresponds to a second occupant of the plurality of occupants; and   cause, at the electronic device, a personalized response to the second voice input to be presented, the personalized response being personalized for the second occupant.   
     
     
         13 . The method of  claim 10 , wherein the request is a request for personal information, the personalized response includes the requested personal information with respect to the first occupant, and causing the functionality of the electronic device to be restricted comprises acting on only requests that involve non-personal information. 
     
     
         14 . The method of  claim 13 , wherein the response is an audible response including personal account data in numerical form, and presenting the response comprises:
 receiving the audible response from a content host; and   outputting the audible response.   
     
     
         15 . The method of  claim 13 , wherein the hardware processor is further configured to:
 determine the request based on the first voice input; and   generate the response in accordance with the determined request.   
     
     
         16 . The method of  claim 15 , wherein:
 the determined request includes a request to the electronic device to awaken; and   the response includes an audible greeting, wherein the audible greeting includes an indication of an identity of the first occupant.   
     
     
         17 . The method of  claim 15 , wherein:
 the personal information includes an email, a calendar event, or a bank balance; and   generating the personalized response in accordance with the determined request comprises obtaining the requested personal information with respect to the first occupant.   
     
     
         18 . The method of  claim 13 , wherein the hardware processor is further configured to:
 receive a second voice input;   compare the second voice input to the one or more voice models;   determine that the second voice input corresponds to a second occupant of the plurality of occupants; and   cause, at the electronic device, a personalized response to the second voice input to be presented, the personalized response being personalized for the second occupant.   
     
     
         19 . A non-transitory computer readable storage medium storing one or more programs, the one or more programs comprising instructions, which, when executed by a first electronic device with one or more microphones, a speaker, and one or more processors, cause the first electronic device to perform operations of a method including:
 receiving a first voice input associated with a request for a service;   determining whether the first voice input corresponds with any of a plurality of occupants based on a comparison of the first voice input to one or more voice models trained to each of the plurality of occupants;   in accordance with a determination that the first voice input corresponds to a first occupant of the plurality of occupants, causing, at an electronic device, a personalized response to the request to be presented, the personalized response being personalized for the first occupant; and   in accordance with a determination that the first voice input corresponds to none of the plurality of occupants, causing functionality of the electronic device to be restricted.