Speech based user recognition

Patent metadata

Field	Value
Publication number	US-2022189458-A1
Application number	US-202217584489-A
Country	US
Kind code	A1
Filing date	Jan 26, 2022
Priority date	Dec 22, 2016
Publication date	Jun 16, 2022
Grant date	—

Abstract

Systems, methods, and devices for verifying a user are disclosed. A speech-controlled device captures a spoken command, and sends audio data corresponding thereto to a server. The server performs ASR on the audio data to determine ASR confidence data. The server, in parallel, performs user verification on the audio data to determine user verification confidence data. The server may modify the user verification confidence data using the ASR confidence data. In addition or alternatively, the server may modify the user verification confidence data using at least one of a location of the speech-controlled device within a building, a type of the speech-controlled device, or a geographic location of the speech-controlled device.

First claim

1 .- 20 . (canceled)

21 . A computer-implemented method comprising:
receiving first data corresponding to location data for a wearable device; receiving second data comprising at least one of image data representing a face or audio data representing a voice; and processing the first data and the second data to determine an identity associated with a user of the wearable device.

22 . The computer-implemented method of claim 21 , further comprising:
selecting, based at least in part on the wearable device, third data associated with a known user; and processing the second data with respect to the third data to determine the identity associated with the user of the wearable device corresponds to the known user.

23 . The computer-implemented method of claim 22 , further comprising:
determining a user profile associated with the wearable device; and using the user profile to identify availability of the third data.

24 . The computer-implemented method of claim 21 , wherein the location data corresponds to where the wearable device is within a building.

25 . The computer-implemented method of claim 21 , wherein the location data corresponds to geographic coordinate data.

26 . The computer-implemented method of claim 21 , wherein the location data corresponds to a location of the wearable device relative to a second device.

27 . The computer-implemented method of claim 21 , further comprising:
receiving a user input corresponding to the wearable device; and determining the second data corresponds to the user input.

28 . The computer-implemented method of claim 21 , wherein the second data comprises both image data and audio data and the method further comprises:
determining the image data and the audio data correspond to a first user input, wherein the identity is determined based at least in part on the image data and the audio data.

29 . The computer-implemented method of claim 21 , further comprising:
determining third data indicating a type of the wearable device, wherein the identity is determined further based at least in part on the type of the wearable device.

30 . The computer-implemented method of claim 21 , further comprising:
determining the wearable device corresponds to a first user; and determining third data representing that the identity more likely corresponds to the first user than to a second user, wherein the identity is determined further based at least in part on the third data.

31 . A system comprising:
at least one processor; and at least one memory comprising instructions that, when executed by the at least one processor, cause the system to:
receive first data corresponding to location data for a wearable device;
receive second data comprising at least one of image data representing a face or audio data representing a voice; and
process the first data and the second data to determine an identity associated with a user of the wearable device.

32 . The system of claim 31 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
select, based at least in part on the wearable device, third data associated with a known user; and process the second data with respect to the third data to determine the identity associated with the user of the wearable device corresponds to the known user.

33 . The system of claim 32 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
determine a user profile associated with the wearable device; and use the user profile to identify availability of the third data.

34 . The system of claim 31 , wherein the location data corresponds to where the wearable device is within a building.

35 . The system of claim 31 , wherein the location data corresponds to geographic coordinate data.

36 . The system of claim 31 , wherein the location data corresponds to a location of the wearable device relative to a second device.

37 . The system of claim 31 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
receive a user input corresponding to the wearable device; and determine the second data corresponds to the user input.

38 . The system of claim 31 , wherein the second data comprises both image data and audio data and the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
determine the image data and the audio data correspond to a first user input, wherein the identity is determined based at least in part on the image data and the audio data.

39 . The system of claim 31 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
determine third data indicating a type of the wearable device, wherein the identity is determined further based at least in part on the type of the wearable device.

40 . The system of claim 31 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
determine the wearable device corresponds to a first user; and determine third data representing that the identity more likely corresponds to the first user than to a second user, wherein the identity is determined further based at least in part on the third data.

Assignees

• Amazon Tech Inc

Inventors

• Matsoukas Spyridon
• Khare Aparna
• Krishnamoorthy Vishwanathan
• Somashekar Shamitha
• Mandal Arindam

Classifications

• G10L15/00

  Speech recognition (G10L17/00 takes precedence) · CPC title

• G10L15/01 Primary

  Assessment or evaluation of speech recognition systems · CPC title

• G10L17/06 Primary

  Decision making techniques; Pattern matching strategies · CPC title

• G10L15/30

  Distributed recognition, e.g. in client-server systems, for mobile phones or network applications · CPC title

• G10L17/04

  Training, enrolment or model building · CPC title