Patent US10102359

Device access using voice authentication
[+] Show Details

US10102359

1. A non-transitory computer-readable medium including instructions which, when executed by an electronic device, cause the device to: (4) (7)

while the device is in a locked state at a first time, receive non-voice authentication information from a user;

responsive to receiving valid authentication information, transition the device to an unlocked state;

while in the unlocked state, receive a first speech input from the user;

generate a voiceprint based on a voice sample of the first speech input;

while the device is in the locked state at a second time, receive a second speech input, the second speech input including a command associated with a restricted feature of the device;

determine a degree of match between the generated voiceprint and the second speech input; and

upon determining that the degree of match is above a predetermined threshold, execute the command including invoking the restricted feature of the device, wherein the command is executed while the device is in the locked state, and wherein the command is a request to perform an action other than unlocking the device.

2. The non-transitory computer-readable medium of claim 1, wherein the instructions further cause the device to: (0) (1)

3. The non-transitory computer-readable medium of claim 1, wherein the generated voiceprint is a text-independent voiceprint. (0)

4. The non-transitory computer-readable medium of claim 1, wherein the instructions further cause the device to: (0) (1)

5. The non-transitory computer-readable medium of claim 1, wherein the first speech input includes a command, and wherein the instructions further cause the device to execute the command of the first speech input. (0)

6. A non-transitory computer-readable medium including instructions which, when executed by an electronic device, cause the device to: (2) (1)

while the device is in a locked state: receive a voice command associated with a restricted feature of the device;

determine a degree of match between a previously generated voiceprint and the voice command;

responsive to determining that the degree of match is above a predetermined threshold, execute the voice command including invoking the restricted feature of the device; and

responsive to determining that the degree of match is not above a predetermined threshold, forgo executing the voice command, wherein the voice command is a request to perform an action other than unlocking the device.

7. The non-transitory computer-readable medium of claim 6, wherein the instructions further cause the device to: (0) (1)

8. The non-transitory computer-readable medium of claim 6, wherein the device remains in the locked state after executing the voice command, and wherein the instructions further cause the device to: (0) (1)

9. A method comprising: (2) (1)

at an electronic device: while the device is in a locked state at a first time, receiving non-voice authentication information from a user;

in response to receiving valid authentication information, transitioning the device to an unlocked state;

while in the unlocked state, receiving a first speech input from the user;

generating a voiceprint based on a voice sample of the first speech input;

while the device is in a locked state at a second time, receiving a second speech input, the second speech input including a command associated with a restricted feature of the device;

determining a degree of match between the generated voiceprint and the second speech input; and

upon determining that the degree of match is above a predetermined threshold, executing the command including invoking the restricted feature of the device, wherein the command is executed while the device is in the locked state, and wherein the command is a request to perform an actin other than unlocking the device.

10. The method of claim 9, further comprising: (0) (1)

11. The method of claim 9, wherein the first speech input includes a command, and further comprising executing the command of the first speech input. (0)

12. A method comprising: (2) (1)

at an electronic device: while the device is in a locked state: receiving a voice command associated with a restricted feature of the device;

determining a degree of match between a previously generated voiceprint and the voice command;

in response to determining that the degree of match is above a predetermined threshold, execute the voice command including invoking the restricted feature of the device; and

in response to determining that the degree of match is not above a predetermined threshold, forgo executing the voice command, wherein the voice command is a request to perform an action other than unlocking the device.

13. The method of claim 12, further comprising: (0) (1)

14. The method of claim 12, wherein the device remains in the locked state after executing the voice command, and further comprising: (0) (1)

15. An electronic device comprising: (2) (2)

one or more processors; and

memory storing instructions which, when executed by the one or more processors, cause the device to: while the device is in a locked state at a first time, receive non-voice authentication information from a user;

responsive to receiving valid authentication information, transition the device to an unlocked state;

while in the unlocked state, receive a first speech input from the user;

generate a voiceprint based on a voice sample of the first speech input;

while the device is in the locked state at a second time, receiving a second speech input, the second speech input including a command associated with a restricted feature of the device;

determine a degree of match between the generated voiceprint and the second speech input; and

16. The device of claim 15, wherein the instructions further cause the device to: (0) (1)

17. The device of claim 15, wherein the first speech input includes a command, and wherein the instructions further cause the device to execute the command of the first speech input. (0)

18. An electronic device comprising: (2) (3)

one or more processors; and

memory storing instructions which, when executed by the one or more processors, cause the device to:

while the device is in a locked state: receive a voice command associated with a restricted feature of the device;

determine a degree of match between a previously generated voiceprint and the voice command;

responsive to determining that the degree of match is above a predetermined threshold, execute the voice command including invoking the restricted feature of the device; and

19. The device of claim 18, wherein the instructions further cause the device to: (0) (1)

20. The device of claim 18, wherein the device remains in the locked state after executing the voice command, and wherein the instructions further cause the device to: (0) (1)

View Abstract and Specification Size

PDF with Images and Document Face >

Full Text Publication >

Patent US10102359

Device access using voice authentication

Patent Matrix® Search