Device access using voice authentication

Patent metadata

Field	Value
Publication number	US-10417405-B2
Application number	US-201816128337-A
Country	US
Kind code	B2
Filing date	Sep 11, 2018
Priority date	Mar 21, 2011
Publication date	Sep 17, 2019
Grant date	Sep 17, 2019

Abstract

A device can be configured to receive speech input from a user. The speech input can include a command for accessing a restricted feature of the device. The speech input can be compared to a voiceprint (e.g., text-independent voiceprint) of the user's voice to authenticate the user to the device. Responsive to successful authentication of the user to the device, the user is allowed access to the restricted feature without the user having to perform additional authentication steps or speaking the command again. If the user is not successfully authenticated to the device, additional authentication steps can be request by the device (e.g., request a password).

First claim

What is claimed is:

1. A non-transitory computer-readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by one or more processors of an electronic device, cause the electronic device to:
receive a first speech input at the electronic device, the first speech input including a command associated with a feature of the electronic device;
while generating an initial text-independent voiceprint based on the first speech input, determine an action corresponding to the command;
store the generated text-independent voice print;
provide access to the feature of the device according to the command;
receive a second speech input at the electronic device; and
determine whether voice characteristics of the second speech input match voice characteristics of the stored text-independent voice print.

2. The computer-readable storage medium of claim 1 ,
wherein the instructions further cause the electronic device to:
generate voice samples based on the first speech input;
store the voice samples on the device; and
generate the initial text-independent voiceprint based on the voice samples.

3. The computer-readable storage medium of claim 1 ,
wherein generating an initial text-independent voiceprint based on the first speech input further comprises:
determining one or more phonemes based on the first speech input; and
generating a model based on the one or more phonemes.

4. The computer-readable storage medium of claim 3 , wherein generating a model based on the one or more phonemes includes identifying one or more characteristics associated with a user pronunciation of the determined one or more phonemes.

5. The computer-readable storage medium of claim 4 , wherein generating a model based on the one or more phonemes includes vector quantization.

6. The computer-readable storage medium of claim 4 ,
wherein generating a model based on the one or more phonemes further comprises:
determining one or more transitions between states associated with voice characteristics of the first speech input.

7. The computer-readable storage medium of claim 6 , wherein the one or more transitions include stochastic Markovian transitions.

8. The computer-readable storage medium of claim 6 , wherein the one or more transitions are associated with at least one voice characteristic, silence characteristic, nasal characteristic, liquid characteristic, or frication characteristic.

9. The computer-readable storage medium of claim 1 ,
wherein the initial text-independent voiceprint is generated while the device is in an unlocked state.

10. The computer-readable storage medium of claim 1 , wherein the electronic device receives the second speech input while the electronic device is locked.

11. The computer-readable storage medium of claim 1 ,
wherein the instructions further cause the electronic device to:
in accordance with a determination that characteristics of the second speech input match characteristics of the stored text-independent voiceprint, perform a task; and
in accordance with a determination that characteristics of the second speech input do not match characteristics of the stored text-independent voiceprint, provide a notification.

12. The computer-readable storage medium of claim 11 , wherein performing a task includes executing a command included in the second speech input.

13. The computer-readable storage medium of claim 11 , wherein performing a task includes unlocking the electronic device.

14. The computer-readable storage medium of claim 11 , wherein the notification includes at least one of a sound or a vibration.

15. The computer-readable storage medium of claim 11 , wherein the notification includes a prompt requesting a user to provide a password or code.

16. The computer-readable storage medium of claim 11 , wherein performing a task further comprises:
obtaining biometric data associated with a user;
determining whether the user is authorized based on the biometric data;
in accordance with a determination that the user is authorized based on the biometric data, performing a task associated with the second speech input.

17. The computer-readable storage medium of claim 16 , wherein the biometric data includes at least one of facial recognition data or finger print data.

18. The computer-readable storage medium of claim 1 ,
wherein the initial text-independent voiceprint is generated by a voiceprint service.

19. The non-transitory computer-readable storage medium of claim 1 , wherein the instructions further cause the electronic device to:
cause the initial text-independent voiceprint to be generated by a network server, wherein the generated text-independent voiceprint is stored at the network server.

20. The non-transitory computer-readable storage medium of claim 1 , wherein the instructions further cause the electronic device to:
transmit, to a network server, a first plurality of voice samples at a first time;
transmit, to the network server, a second plurality of voice samples at a second time; and
cause the initial text-independent voiceprint to be generated by the network server based on the first plurality of voice samples and the second plurality of voice samples.

21. The non-transitory computer-readable storage medium of claim 20 , wherein the first plurality of voice samples and the second plurality of voice samples are transmitted to the network server during a period when the electronic device is idle or when the electronic device is using less than a predetermined amount of resources.

22. An electronic device, comprising:
one or more processors;
a memory; and
one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including instructions for:
receiving a first speech input at the electronic device, the first speech input including a command associated with a feature of the electronic device;
while generating an initial text-independent voiceprint based on the first speech input, determining an action corresponding to the command;
storing the generated text-independent voice print;
providing access to the feature of the device according to the command;
receiving a second speech input at the electronic device; and
determining whether voice characteristics of the second speech input match voice characteristics of the stored text-independent voice print.

23. The electronic device of claim 22 , wherein the one or more programs further include instructions for:
generating voice samples based on the first speech input;
storing the voice samples on the device; and
generating the initial text-independent voiceprint based on the voice samples.

24. The electronic device of claim 22 , wherein generating the initial text-independent voiceprint based on the first speech input further comprises:
determining one or more phonemes based on the first speech input; and
generating a model based on the one or more phonemes.

25. The electronic device of claim 24 , wherein generating a model based on the one or more phonemes includes identifying one or more characteristics associated with a user pronunciation of the determined one or more phonemes.

26. The electronic device of claim 25 , wherein generating a model based on the one or more phonemes includes vector quantization.

Assignees

• Apple Inc

Inventors

• Cheyer Adam John

Classifications

• G10L17/00

  Speaker identification or verification techniques · CPC title

• H04L63/0861

  using biometrical features, e.g. fingerprint, retina-scan (cryptographic mechanisms or cryptographic arrangements for entity authentication using biological data H04L9/3231) · CPC title

• G06F21/32 Primary

  using biometric data, e.g. fingerprints, iris scans or voiceprints · CPC title

• H04L63/10

  for controlling access to devices or network resources · CPC title

• G10L17/24

  the user being prompted to utter a password or a predefined phrase · CPC title