Systems and methods for providing prompts for voice commands

• US 9,082,407 B1
• Filed: 06/05/2014
• Issued: 07/14/2015
• Est. Priority Date: 04/15/2014
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Tickner, Simon, Faaborg, Alexander James
• Primary Examiner(s): Shah, Paras D
• Application Number:
  US14/296,936
• Time in Patent Office: 404 Days
• Field of Search: 704/231, 704/235, 704/251, 704/254, 704/270, 704/275, 739/88.01
• US Class Current: 1/1
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 25/48 specially adapted for particular use

Abstract

In an example implementation of the disclosed technology, a method includes setting a command entry timer based on a predetermined command entry threshold. The method also includes receiving an indication of user input to prompt receipt of an audio command and, responsive to determining that the command entry timer has expired since receiving the indication of user input, outputting, for display, at least one indicator associated with at least one supported audio command that is associated with at least one function of the computing device. The method also includes receiving a plurality of audio input samples and updating the command entry threshold based on plurality of audio input samples.

Claims

1. A method, comprising:

setting, by a computing device, a time threshold, the time threshold indicating a predetermined amount of time;

receiving, by the computing device, an indication of user input to prompt the computing device to detect a plurality of audio samples;

responsive to determining that the predetermined amount of time has elapsed and that the computing device has received no audio command executable by the computing device since receipt of the indication of user input, outputting, for display, an indicator associated with at least one audio command executable by the computing device;

receiving, at the computing device, the plurality of audio samples;

generating, at the computing device and based on the plurality of audio samples, information indicative of a speech pattern of the user, the information indicative of the speech pattern of the user being based on lengths of pauses between words detected in the plurality of audio samples; and

updating, by the computing device and based on the information indicative of the speech pattern of the user, the predetermined amount of time indicated by the time threshold.

2. The method of claim 1, wherein information indicative of the speech pattern of the user is computing device information indicative of the speech pattern of the user, the method further comprising:

receiving, from a remote processing device and based on the plurality of audio samples, remote processing device information indicative of the speech pattern of the user.

3. The method of claim 1, wherein the information indicative of the speech pattern of the user is further based on lengths of pauses between syllables detected in the plurality of audio samples.

4. The method of claim 1, wherein the information indicative of the speech pattern of the user is further based on an amount of time before decipherable speech is detected in the plurality of audio samples.

5. The method of claim 3, wherein updating, by the computing device and based on the information indicative of speech pattern of the user, the predetermined amount of time indicated by the time threshold further comprises:

comparing the delay time to a predetermined reference delay time;

responsive to determining that the delay time exceeds the predetermined reference delay time by a predetermined factor, increasing the predetermined amount of time indicated by the time threshold; and

responsive to determining that the predetermined reference delay time exceeds the delay time by the predetermined factor, decreasing the predetermined amount of time indicated by the time threshold.

6. The method of claim 5, wherein the predetermined reference delay time is determined from a plurality of audio samples from a plurality of users.

7. The method of claim 5, wherein the delay time is a mean delay time, and the mean delay time is calculated by taking the mean of a plurality of delay times from the plurality of audio samples.

8. The method of claim 1, wherein the at least one indicator is associated with at least one of a word, a phrase, a graphical icon, and a picture.

9. The method of claim 1, wherein the at least one indicator is determined, by the computing device, based on at least one of a time of day, a geolocation of the computing device, a recency of use by a user of an application associated with the indicator, and a frequency of use by the user of an application associated with the indicator.

10. The method of claim 1, wherein user input to prompt the computing device to detect a plurality of audio samples comprises at least one of a press-and-hold gesture, a spoken predefined word, a spoken predefined sound, and a spoken predefined phrase.

11. The method of claim 1, wherein information indicative of a speech pattern of the user is indicative of a regional dialect.

12. A system, comprising:

one or more processors;

a memory coupled to the one or more processors and storing instructions that, when executed by the one or more processors, cause the system to;

set a time threshold, the time threshold indicating a predetermined amount of time;

receive an indication of user input to prompt the system to detect a plurality of audio samples;

responsive to determining that the predetermined amount of time has elapsed and that the system has received no audio command executable by the system since receipt of the indication of user input, output, for display, an indicator associated with at least one audio command executable by the system;

receive the plurality of audio samples;

generate, based on the plurality of audio samples, information indicative of a speech pattern of the user, the information indicative of the speech pattern of the user being based on lengths of pauses between words detected in the plurality of audio samples; and

update, based on the information indicative of the speech pattern of the user, the predetermined amount of time indicated by the time threshold.

13. The system of claim 12, wherein information indicative of the speech pattern of the user is system information indicative of a speech pattern of the user, and wherein the memory further stores instructions that, when executed by the one or more processors, cause the system to:

receive, from a remote processing device and based on the plurality of audio samples, remote processing device information indicative of the speech pattern of the user.

14. The system of claim 12, wherein the information indicative of the speech pattern of the user is further based on lengths of pauses between syllables detected in the plurality of audio samples.

15. The system of claim 12, wherein the information indicative of the speech pattern of the user is further based on an amount of time before decipherable speech is detected in the plurality of audio samples.

16. The system of claim 14, wherein updating, based on the information indicative of the speech pattern of the user, the predetermined amount of time indicated by the time threshold further comprises:

comparing the delay time to a predetermined reference delay time;

responsive to determining that the delay time exceeds the predetermined reference delay time by a predetermined factor, increasing the predetermined amount of time indicated by the time threshold; and

responsive to determining that the predetermined reference delay time delay time exceeds the delay time by the predetermined factor, decreasing the predetermined amount of time indicated by the time threshold.

17. The system of claim 16, wherein the predetermined reference delay time is determined from a plurality of audio samples from a plurality of users.

18. The system of claim 16, wherein the delay time is a mean delay time, and the mean delay time is calculated by taking the mean of a plurality of delay times from the plurality of audio samples.

19. A non-transitory computer-readable medium storing instructions that, when executed by one or more processors, cause a computing device to:

set a time threshold, the time threshold indicating a predetermined amount of time;

receive an indication of user input to prompt the computing device to detect a plurality of audio samples;

responsive to determining that the predetermined amount of time has elapsed and that the computing device has received no audio command executable by the computing device since receipt of the indication of user input, output, for display, an indicator associated with at least one audio command executable by the computing device;

receive the plurality of audio samples;

generate, based on the plurality of audio samples, information indicative of the speech pattern of the user, the information indicative of the speech pattern of the user being based on lengths of pauses between words detected in the plurality of audio samples; and

update, based on the information indicative of the speech pattern of the user, the predetermined amount of time indicated by the time threshold.

20. The non-transitory computer-readable medium of claim 19, wherein

information indicative of the speech pattern of the user is computing device information indicative of the speech pattern of the user, and wherein the non-transitory computer readable medium further stores instructions that, when executed by the one or more processors, further cause the computing device to:

receive, from a remote processing device and based on the plurality of audio samples, remote processing device information indicative of the speech pattern of the user.

21. The non-transitory computer-readable medium of claim 19, wherein the information indicative of the speech pattern of the user is further based on an amount of time before decipherable speech is detected in the plurality of audio samples.

22. The non-transitory computer-readable medium of claim 19, wherein the information indicative of the speech pattern of the user is further based on lengths of pauses between syllables detected in the plurality of audio samples.

23. The non-transitory computer-readable medium of claim 19, wherein updating, based on the information indicative of the speech pattern of the user, the predetermined amount of time indicated by the time threshold further comprises:

comparing the delay time to a predetermined reference delay time;

responsive to determining that the delay time exceeds the predetermined reference delay time by a predetermined factor, increasing the predetermined amount of time indicated by the time threshold; and

responsive to determining that the predetermined reference delay time delay time exceeds the delay time by the predetermined factor, decreasing the predetermined amount of time indicated by the time threshold.

24. The non-transitory computer-readable medium of claim 23, wherein the predetermined reference delay time is determined from a plurality of audio samples from a plurality of users.

25. The non-transitory computer-readable medium of claim 23, wherein the delay time is a mean delay time, and the mean delay time is calculated by taking the mean of a plurality of delay times from the plurality of audio samples.

26. The non-transitory computer-readable medium of claim 19, wherein the at least one indicator is determined, by the computing device, based on at least one of a time of day, a geolocation of the computing device, a recency of use by a user of an application associated with the indicator, and a frequency of use by the user of an application associated with the indicator.