Method and device for voice recognition training

• US 10,510,337 B2
• Filed: 04/10/2018
• Issued: 12/17/2019
• Est. Priority Date: 07/23/2013
• Status: Active Grant

• Current Assignee: Google Technology Holdings LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Gunn, Michael E., Bekkerman, Boris, Jasiuk, Mark A., Kamdar, Pratik M., Sierawski, Jeffrey A.
• Primary Examiner(s): He, Jialong
• Application Number:
  US15/949,145
• Publication Number:
  US 20180301142A1
• Time in Patent Office: 616 Days
• CPC Class Codes: G06F 3/04842 Selection of displayed objects or displayed text elements G06F3/0482 takes precedence
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: G10L 15/20 Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech G10L21/02 takes precedence
• CPC Class Codes: G10L 17/04 Training, enrolment or model building
• CPC Class Codes: G10L 17/20 Pattern transformations or operations aimed at increasing system robustness, e.g. against channel noise or different working conditions
• CPC Class Codes: G10L 2015/0638 Interactive procedures
• CPC Class Codes: G10L 25/84 for discriminating voice from noise
• CPC Class Codes: H04W 88/02 Terminal devices

Abstract

A method on a mobile device for voice recognition training is described. A voice training mode is entered. A voice training sample for a user of the mobile device is recorded. The voice training mode is interrupted to enter a noise indicator mode based on a sample background noise level for the voice training sample and a sample background noise type for the voice training sample. The voice training mode is returned to from the noise indicator mode when the user provides a continuation input that indicates a current background noise level meets an indicator threshold value.

Claims

1. A method comprising:

executing, by a processor of a mobile device, a first mode of the mobile device, the first mode configured to;

display on a screen in communication with the processor a first graphical user interface including a prompt instructing a user associated with the mobile device to speak a designated phrase for training a voice recognition system of the mobile device, the voice recognition system configured to recognize a voice of the user;

receive a first voice training sample corresponding to the user speaking the designated phrase; and

determine whether a noise level for the received first voice training sample exceeds a predetermined threshold; and

in response to determining that the noise level for the received first voice training sample exceeds the predetermined threshold, executing, by the processor, a second mode of the mobile device, the second mode configured to display on the screen of the mobile device a second graphical user interface comprising;

a notification that recommends an environment conducive to voice training; and

a graphical element,

wherein the second mode is further configured to enable the graphical element of the second graphical user interface for selection by the user when a background noise level does not exceed the predetermined threshold, the enabled graphical element, when selected by the user, causes the processor to transition from executing in the second mode back to executing in the first mode.

2. The method of claim 1, further comprising, in response to determining that the noise level for the first voice training sample exceeds the predetermined threshold:

ceasing, by the processor, execution of the first mode of the mobile device; and

rejecting, by the processor, the first voice training sample from use in training the voice recognition system.

3. The method of claim 1, wherein the second mode is further configured to not process any voice samples spoken by the user during execution of the second mode of the mobile device.

4. The method of claim 1, wherein the first mode is further configured to, when the noise level for the received first voice training sample does not exceed the predetermined threshold, process the first voice training sample for use in training the speech recognition system.

5. The method of claim 4, wherein the first mode is further configured to display again, in the first graphical user interface, the prompt instructing the user to speak the designated phrase.

6. The method of claim 1, wherein the designated phrase comprises a trigger phrase including one or more words.

7. A mobile device comprising:

a processor;

a screen in communication with the processor; and

memory hardware in communication with the processor and storing instructions, that when executed by the processor, cause the processor to perform one or more operations comprising;

executing a first mode of the mobile device, the first mode configured to;

display on the screen a first graphical user interface including a prompt instructing a user associated with the mobile device to speak a designated phrase for training a voice recognition system of the mobile device, the voice recognition system configured to recognize a voice of the user;

receive a first voice training sample corresponding to the user speaking the designated phrase; and

determine whether a noise level for the received first voice training sample exceeds a predetermined threshold; and

in response to determining that the noise level for the received first voice training sample exceeds the predetermined threshold, executing a second mode of the mobile device, the second mode configured to display on the screen a second graphical user interface comprising;

a notification that recommends an environment conducive to voice training; and

a graphical element,

wherein the second mode is further configured to enable the graphical element of the second graphical user interface for selection by the user when a background noise level does not exceed the predetermined threshold, the enabled graphical element, when selected by the user, causes the processor to transition from executing in the second mode back to executing in the first mode.

8. The mobile device of claim 7, wherein the operations further comprise, in response to determining that the noise level for the first voice training sample exceeds the predetermined threshold:

ceasing execution of the first mode of the mobile device; and

rejecting the first voice training sample from use in training the voice recognition system.

9. The mobile device of claim 7, wherein the second mode is further configured to not process any voice samples spoken by the user during execution of the second mode of the mobile device.

10. The mobile device of claim 7, wherein the first mode is further configured to, when the noise level for the received first voice training sample does not exceed the predetermined threshold, process the first voice training sample for use in training the speech recognition system.

11. The mobile device of claim 10, wherein the first mode is further configured to display again, in the first graphical user interface, the prompt instructing the user to speak the designated phrase.

12. The mobile device of claim 7, wherein the designated phrase comprises a trigger phrase including one or more words.

13. A method of voice recognition training, the method comprising:

receiving, at a processor of a mobile device, a voice training sample corresponding to a user speaking a designated phrase while the mobile device is displaying a first user interface on a screen of the mobile device, the first user interface prompting the user to speak the designated phrase for training voice recognition software configured to recognize a voice of the user;

determining, by the processor, whether a noise level for the received voice training sample exceeds a predetermined threshold; and

in response to determining that the noise level for the received voice training sample exceeds the predetermined threshold, displaying, by the processor, a second user interface on the screen of the mobile device, the second user interface configured to display;

a notification that recommends an environment conducive to voice training; and

a graphical element,

wherein the second mode is further configured to enable the graphical element of the second graphical user interface for selection by the user when a background noise level does not exceed the predetermined threshold, the enabled graphical element, when selected by the user, causes the processor to transition from executing in the second mode back to executing in the first mode.

14. The method of claim 13, further comprising, in response to determining that the noise level for the received voice training sample exceeds the predetermined threshold, rejecting, by the mobile device, the voice training sample from use in training the voice recognition software.

15. The method of claim 13, further comprising, when displaying the second user interface, preventing, by the processor, the mobile device from accepting voice samples spoken by the user.

16. The method of claim 13, further comprising, when the determined noise level for the received voice training sample does not exceed the predetermined threshold, processing, by the processor, the voice training sample for use in training the speech recognition software.

17. The method of claim 13, wherein the designated phrase comprises a trigger phrase including one or more words.

18. The method of claim 13, further comprising executing, by the processor, the voice recognition software on the mobile device.

19. A mobile device comprising:

a processor;

a screen in communication with the processor; and

memory hardware in communication with the processor and storing instructions, that when executed by the processor, cause the processor to perform one or more operations comprising;

receiving a voice training sample corresponding to a user speaking a designated phrase while the mobile device is displaying a first user interface on the screen, the first user interface prompting the user to speak the designated phrase for training voice recognition software configured to recognize a voice of the user;

determining whether a noise level for the received voice training sample exceeds a predetermined threshold; and

in response to determining that the noise level for the received voice training sample exceeds the predetermined threshold, displaying a second user interface on the screen, the second user interface configured to display;

a notification that recommends an environment conducive to voice training; and

a graphical element,

wherein the second mode is further configured to enable the graphical element of the second graphical user interface for selection by the user when a background noise level does not exceed the predetermined threshold, the enabled graphical element, when selected by the user, causes the processor to transition from executing in the second mode back to executing in the first mode.

20. The mobile device of claim 19, wherein the operations further comprise, in response to determining that the noise level for the received voice training sample exceeds the predetermined threshold, rejecting the voice training sample from use in training the voice recognition software.

21. The mobile device of claim 19, wherein the operations further comprise, when displaying the second user interface, preventing the mobile device from accepting voice samples spoken by the user.

22. The mobile device of claim 19, wherein the operations further comprise, when the determined noise level for the received voice training sample does not exceed the predetermined threshold, processing the voice training sample for use in training the speech recognition software.

23. The mobile device of claim 19, wherein the designated phrase comprises a trigger phrase including one or more words.

24. The mobile device of claim 19, wherein the operations further comprise executing the voice recognition software on the mobile device.