Transitioning an electronic device between device states

• US 9,466,286 B1
• Filed: 01/16/2013
• Issued: 10/11/2016
• Est. Priority Date: 01/16/2013
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Hart, Gregory Michael, Barton, William Folwell, Bezos, Jeffrey P.
• Primary Examiner(s): Saint Cyr, Leonard
• Application Number:
  US13/743,259
• Time in Patent Office: 1,364 Days
• Field of Search: 704246-252
• US Class Current: 1/1
• CPC Class Codes: G10L 15/10 using distance or distortion measures between unknown speech and reference templates
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

This disclosure describes techniques for transitioning an electronic device between device states. In one example, a voice-controlled device is configured to transition from a low power state to an interactive state in response to identifying a user speaking a defined utterance. If, however, the device determines that the user has spoken an utterance that is close, but not equivalent to, the defined utterance, then the device may lower a threshold for subsequent speech such that the device is more likely to determine that the subsequent speech is equivalent to the defined utterance.

Claims

1. An apparatus comprising:

a microphone;

a processor; and

computer-readable media storing computer-executable instructions that, when executed by the processor, cause the processor to perform acts comprising;

receiving, from the microphone, a first audio signal including a representation of a first utterance;

determining a first similarity score for the first utterance, wherein the first similarity score indicates a similarity between the representation of the first utterance and a representation of a defined word or phrase;

determining that the first similarity score is less than a first similarity threshold and greater than a second similarity threshold;

setting a temporary third similarity threshold for a defined amount of time, wherein the third similarity threshold is less than the first similarity threshold and greater than the second similarity threshold;

receiving, from the microphone and within the defined amount of time, a second audio signal including a representation of a second utterance;

causing speech-recognition to be performed on the second audio signal;

determining a second similarity score for the second utterance, wherein the second similarity score indicates a similarity between the representation of the second utterance and the representation of the defined word or phrase;

determining that the second similarity score is greater than the third similarity threshold; and

in response to the determining that the second similarity score is greater than the third similarity threshold, changing a state of the apparatus from a first state to a second state.

2. The apparatus as recited in claim 1, the acts further comprising:

linearly or exponentially increasing the third similarity threshold to the first similarity threshold over the defined amount of time.

3. The apparatus as recited in claim 1, wherein the apparatus operates with additional functionality in the second state than in the first state.

4. The apparatus as recited in claim 1, wherein:

the first state comprises a state in which the apparatus performs speech-recognition on audio signals to identify the defined word or phrase; and

the second state comprises a state in which the apparatus provides additional functionality.

5. The apparatus as recited in claim 4, wherein the additional functionality includes providing audio signals to a remote computing device over a network.

6. A non-transitory computer-readable storage medium storing instructions that when executed by a processor cause the processor to:

receive a first audio signal including a representation of a first utterance;

determine a first similarity score for the first utterance, wherein the first similarity score indicates a similarity between the representation of the first utterance and a representation of a defined word or phrase;

determine that the first similarity score does not satisfy a first similarity acceptance criterion and does satisfy a second similarity acceptance criterion;

modify the first similarity acceptance criterion for a period of time;

receive a second audio signal including a representation of a second utterance within the period of time;

determine a second similarity score for the second utterance, wherein the second similarity score indicates a similarity between the representation of the second utterance and the representation of the defined word or phrase; and

change a state of an electronic device based at least in part on a determination that the second similarity score satisfies the modified first similarity acceptance criterion.

7. The non-transitory computer-readable storage medium of claim 6, wherein modifying the first similarity acceptance criterion includes lowering a similarity threshold associated with the first similarity acceptance criterion.

8. The non-transitory computer-readable storage medium of claim 7, the instructions that when executed by the processor further cause the processor to:

increase the similarity threshold over the period of time after lowering the similarity threshold.

9. The non-transitory computer-readable storage medium of claim 6, wherein the first similarity acceptance criterion includes comparing a similarity score to a similarity threshold and wherein modifying the first similarity acceptance criterion includes increasing the similarity score before comparing the similarity score to the similarity threshold.

10. The non-transitory computer-readable storage medium of claim 6, wherein the first similarity score is determined based at least in part on a comparison of the representation of the first utterance and the representation of the defined word or phrase.

11. The non-transitory computer-readable storage medium of claim 6, the instructions that when executed by the processor further cause the processor to:

determine a third similarity score between the first audio signal and the second audio signal, and wherein the state of the electronic device is changed based at least in part on the third similarity score.

12. The non-transitory computer-readable storage medium of claim 6, the instructions that when executed by a processor further cause the processor to:

attenuate audio output by the electronic device at least partly in response to the determination that the first similarity score does not satisfy the first similarity acceptance criterion and does satisfy the second similarity acceptance criterion.

13. The non-transitory computer-readable storage medium of claim 6, the instructions that when executed by the processor further cause the processor to:

cause an indicator of the electronic device to activate at least partly in response to the determination that the first similarity score does not satisfy the first similarity acceptance criterion and does satisfy the second similarity acceptance criterion.

14. The non-transitory computer-readable storage medium of claim 13, wherein activating the indicator includes outputting audio.

15. A method implemented at least in part by an electronic device that is configured to transition from a first state to a second state in response to a received audio signal having a similarity to a representation of a defined word or phrase, the method comprising:

receiving, at the electronic device, the audio signal;

determining an occurrence of an event while the electronic device is in the first state;

modifying a similarity acceptance criterion for a period of time, based at least in part on the occurrence of the event;

determining a similarity score between the audio signal and a representation of a defined word or phrase; and

transitioning the electronic device from the first state to the second state based at least in part on a determination that the similarity score satisfies the modified similarity acceptance criterion.

16. The method as recited in claim 15, wherein the event comprises:

receiving the audio signal including a representation of an utterance;

determining a similarity score using;

the representation of the utterance, and

the representation of the defined word or phrase; and

determining that the similarity score does not satisfy the similarity acceptance criterion.

17. The method as recited in claim 15, wherein the event comprises the electronic device outputting audio.

18. The method as recited in claim 15, wherein the event comprises determining that a user is within a proximity of the electronic device.

19. The method as recited in claim 15, wherein the event comprises determining that the electronic device has received an input from a user.

20. The method as recited in claim 15, wherein modifying the similarity acceptance criterion for a period of time includes lowering a similarity threshold associated with the similarity acceptance criterion.

21. The method as recited in claim 20, further comprising:

increasing the similarity threshold associated with the similarity acceptance criterion after the lowering and over the period of time.

22. A non-transitory computer-readable media storing computer-executable instructions that, when executed by a processor, cause the processor to perform acts comprising:

receiving an audio signal comprising a representation of an utterance;

monitoring for an occurrence of an event;

at least partly in response to identifying the occurrence of the event, determining a similarity score for the utterance based on a comparison between the representation of the utterance and a representation of a defined word or phrase;

modifying the similarity score;

modifying a similarity acceptance criterion for a period of time; and

transitioning an electronic device from a first state to a second state based at least in part on a determination that the modified similarity score satisfies the modified similarity acceptance criterion.

23. The non-transitory computer-readable media as recited in claim 22, further comprising:

at least partly in response to identifying the occurrence of the event, lowering a similarity threshold associated with the similarity acceptance criterion for a period of time.

24. The non-transitory computer-readable media as recited in claim 22, wherein the electronic device operates with additional functionality in the second state than when in the first state.

25. The non-transitory computer-readable media as recited in claim 24, wherein the first state is a low power state.

26. The non-transitory computer-readable media as recited in claim 22, wherein:

the first state comprises a state in which the electronic device performs speech-recognition to identify the utterance; and

the second state comprises a state in which the electronic device provides additional functionality.

27. The non-transitory computer-readable media as recited in claim 26, wherein the additional functionality includes providing audio signals to a remote computing device over a network.