Granted Patent B2

US 12,277,954 · App. 18/637,284 · Granted Apr 15, 2025

Inventors: Justin Binder (Oakland, CA); Samuel D. Post (San Jose, CA); Onur Tackin (Saratoga, CA); Thomas R. Gruber (Seattle, WA)

Assignee: Apple Inc.

G10L21/16G06F3/167G10L15/22G10L15/26G10L17/24G10L15/02G10L2015/223G10L15/30G10L25/51G10L25/84

Abstract

Claims (73)

1. A non-transitory computer-readable storage medium storing one or more programs for execution by one or more processors of an electronic device including a display screen, the one or more programs including instructions for:

determining whether the display screen is facing down or facing up;

in accordance with a determination that the display screen is facing up:

receiving a sound input;

determining whether the sound input includes predetermined content including one or more trigger words for a voice trigger that operates on the electronic device based on comparing of an input representation of the sound input to one or more reference representations corresponding to a user's voice, wherein:

the one or more reference representations are generated based on a second sound input received at the electronic device, the second sound input including the same one or more trigger words; and

the one or more reference representations are adjusted based on a third sound input received at the electronic device, the third sound input including the same one or more trigger words; and

upon a determination that the sound input includes the predetermined content, initiating a speech-based service; and

in accordance with a determination that the display screen is facing down, forgoing initiating the speech-based service based on received sound input.

2. The non-transitory computer-readable storage medium of claim 1 , wherein the electronic device includes one or more light sensors, and wherein determining whether the display screen is facing down or facing up includes determining whether the display screen is facing down or facing up based on one or more signals detected by the one or more light sensors.

3. The non-transitory computer-readable storage medium of claim 1 , wherein the one or more programs further include instructions for:

prior to determining whether the sound input includes the predetermined content, determining whether the sound input corresponds to a predetermined type of sound.

4. The non-transitory computer-readable storage medium of claim 3 , wherein the one or more programs further include instructions for:

prior to determining whether the sound input corresponds to the predetermined type of sound, determining whether the sound input satisfies a predetermined condition.

5. The non-transitory computer-readable storage medium of claim 4 , wherein the predetermined condition includes an amplitude threshold.

6. The non-transitory computer-readable storage medium of claim 3 , wherein the predetermined type of sound includes a human voice.

7. The non-transitory computer-readable storage medium of claim 3 , wherein determining whether the sound input corresponds to the predetermined type of sound is performed by a first sound detector, wherein determining whether the sound input includes the predetermined content is performed by a second sound detector, and wherein the first sound detector consumes less power while operating than the second sound detector.

8. The non-transitory computer-readable storage medium of claim 7 , wherein the second sound detector is initiated in response to a determination by the first sound detector that the sound input corresponds to the predetermined type of sound.

9. The non-transitory computer-readable storage medium of claim 7 , wherein the second sound detector is operated for at least a predetermined amount of time after a determination by the first sound detector that the sound input corresponds to the predetermined type of sound.

10. The non-transitory computer-readable storage medium of claim 1 , wherein the one or more programs further include instructions for:

storing at least a portion of the sound input in memory; and

providing the portion of the sound input to the speech-based service once the speech-based service is initiated.

11. The non-transitory computer-readable storage medium of claim 1 , wherein the second sound input and the third sound input are received during an enrollment procedure for the voice trigger.

12. An electronic device, comprising:

a display screen;

one or more processors;

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:

determining whether the display screen is facing down or facing up;

in accordance with a determination that the display screen is facing up:

receiving a sound input;

determining whether the sound input includes predetermined content including one or more trigger words for a voice trigger that operates on the electronic device based on comparing of an input representation of the sound input to one or more reference representations corresponding to a user's voice, wherein:

the one or more reference representations are generated based on a second sound input received at the electronic device, the second sound input including the same one or more trigger words; and

the one or more reference representations are adjusted based on a third sound input received at the electronic device, the third sound input including the same one or more trigger words; and

upon a determination that the sound input includes the predetermined content, initiating a speech-based service; and

in accordance with a determination that the display screen is facing down, forgoing initiating the speech-based service based on received sound input.

13. A method for operating a voice trigger, performed at an electronic device including a display screen, one or more processors, and memory storing instructions for execution by the one or more processors, the method comprising:

determining whether the display screen is facing down or facing up;

in accordance with a determination that the display screen is facing up:

receiving a sound input;

determining whether the sound input includes predetermined content including one or more trigger words for the voice trigger based on comparing of an input representation of the sound input to one or more reference representations corresponding to a user's voice, wherein:

the one or more reference representations are generated based on a second sound input received at the electronic device, the second sound input including the same one or more trigger words; and

the one or more reference representations are adjusted based on a third sound input received at the electronic device, the third sound input including the same one or more trigger words; and

upon a determination that the sound input includes the predetermined content, initiating a speech-based service; and

in accordance with a determination that the display screen is facing down, forgoing initiating the speech-based service based on received sound input.

14. The electronic device of claim 12 , wherein the electronic device includes one or more light sensors, and wherein determining whether the display screen is facing down or facing up includes determining whether the display screen is facing down or facing up based on one or more signals detected by the one or more light sensors.

15. The electronic device of claim 12 , wherein the one or more programs further include instructions for:

prior to determining whether the sound input includes the predetermined content, determining whether the sound input corresponds to a predetermined type of sound.

16. The electronic device of claim 15 , wherein the one or more programs further include instructions for:

prior to determining whether the sound input corresponds to the predetermined type of sound, determining whether the sound input satisfies a predetermined condition.

17. The electronic device of claim 16 , wherein the predetermined condition includes an amplitude threshold.

18. The electronic device of claim 15 , wherein the predetermined type of sound includes a human voice.

19. The electronic device of claim 15 , wherein determining whether the sound input corresponds to the predetermined type of sound is performed by a first sound detector, wherein determining whether the sound input includes the predetermined content is performed by a second sound detector, and wherein the first sound detector consumes less power while operating than the second sound detector.

20. The electronic device of claim 19 , wherein the second sound detector is initiated in response to a determination by the first sound detector that the sound input corresponds to the predetermined type of sound.

21. The electronic device of claim 19 , wherein the second sound detector is operated for at least a predetermined amount of time after a determination by the first sound detector that the sound input corresponds to the predetermined type of sound.

22. The electronic device of claim 12 , wherein the one or more programs further include instructions for:

storing at least a portion of the sound input in memory; and

providing the portion of the sound input to the speech-based service once the speech-based service is initiated.

23. The electronic device of claim 12 , wherein the second sound input and the third sound input are received during an enrollment procedure for the voice trigger.

24. The method of claim 13 , wherein the electronic device includes one or more light sensors, and wherein determining whether the display screen is facing down or facing up includes determining whether the display screen is facing down or facing up based on one or more signals detected by the one or more light sensors.

25. The method of claim 13 , further comprising:

prior to determining whether the sound input includes the predetermined content, determining whether the sound input corresponds to a predetermined type of sound.

26. The method of claim 25 , further comprising:

prior to determining whether the sound input corresponds to the predetermined type of sound, determining whether the sound input satisfies a predetermined condition.

27. The method of claim 26 , wherein the predetermined condition includes an amplitude threshold.

28. The method of claim 25 , wherein the predetermined type of sound includes a human voice.

29. The method of claim 25 , wherein determining whether the sound input corresponds to the predetermined type of sound is performed by a first sound detector, wherein determining whether the sound input includes the predetermined content is performed by a second sound detector, and wherein the first sound detector consumes less power while operating than the second sound detector.

30. The method of claim 29 , wherein the second sound detector is initiated in response to a determination by the first sound detector that the sound input corresponds to the predetermined type of sound.

31. The method of claim 29 , wherein the second sound detector is operated for at least a predetermined amount of time after a determination by the first sound detector that the sound input corresponds to the predetermined type of sound.

32. The method of claim 13 , further comprising:

storing at least a portion of the sound input in memory; and

providing the portion of the sound input to the speech-based service once the speech-based service is initiated.

33. The method of claim 13 , wherein the second sound input and the third sound input are received during an enrollment procedure for the voice trigger.

Continuity (9)

References Cited (400)

Cited By (1)

US 12,568,175