DEVICE LEADERSHIP NEGOTIATION AMONG VOICE INTERFACE DEVICES

• US 20180040322A1
• Filed: 10/19/2017
• Published: 02/08/2018
• Est. Priority Date: 10/09/2014
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Mixter, Kenneth, Melendo Casado, Diego, Gruenstein, Alexander Houston, Tai, Terry, Hughes, Christopher Thaddeus, Sharifi, Matthew Nirvan
• Granted Patent: US 10,102,857 B2
• Time in Patent Office: Days
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/32 Multiple recognisers used in sequence or in parallel; Score combination systems therefor, e.g. voting systems
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 25/60 for measuring the quality of voice signals

Abstract

The various implementations described herein include methods and systems for determining device leadership among voice interface devices. In one aspect, a method is performed at an electronic device that includes microphones, a speaker, processors, and memory storing one or more programs for execution by the one or more processors. The electronic device: (1) detects a voice input; (2) determines a first quality score for the detected voice input; (3) receives quality scores generated by other electronic devices for detection of the voice input by the other electronic devices; (4) in accordance with a determination that the first quality score is not the highest amongst the quality scores for the voice input, identifies a criterion associated with the voice input; and (5) in accordance with a determination that the identified criterion is the most relevant to the electronic device, responds to the detected input.

Claims

1. A method, comprising:

at a first electronic device of a plurality of electronic devices, each electronic device of the plurality of electronic devices comprising one or more microphones, a speaker, one or more processors, and memory storing one or more programs for execution by the one or more processors;

detecting a voice input;

determining a first quality score for the detected voice input;

receiving quality scores generated by the other devices of the plurality of electronic devices for detection of the voice input by the other devices;

in accordance with a determination that the first quality score is not the highest amongst the quality scores for the voice input generated by the plurality of electronic devices;

identifying a criterion associated with the voice input; and

in accordance with a determination that the identified criterion is the most relevant to the first electronic device, responding to the detected input.

2. The method of claim 1, further comprising forgoing outputting an audible response to the detected voice input in accordance with the determination that the identified criterion is not the most relevant to the first electronic device.

3. The method of claim 2, wherein forgoing outputting the audible response further includes changing a state of operation of the first electronic device.

4. The method of claim 1, further comprising communicating to the other devices of the plurality of electronic devices to forgo responding to the detected input.

5. The method of claim 1, wherein responding to the detected input comprises outputting an audible and/or a visual response to the detected voice input.

6. The method of claim 1, wherein the detecting a voice input is performed at intervals of a predefined number of voice inputs.

7. The method of claim 1, wherein the plurality of electronic devices is communicatively coupled through a local network;

and

the communicating and receiving are performed through the local network.

8. The method of claim 1, wherein the first electronic device is further configured to be awakened by a plurality of affordances including a voice-based affordance;

and

wherein detecting the voice input is in response to the awakening of the first electronic device.

9. The method of claim 1, wherein the first quality score comprises a confidence level of detection of the voice input.

10. The method of claim 1, wherein the first quality score comprises a signal-to-noise rating of detection of the voice input.

11. The method of claim 1, wherein the criterion comprises one or more of:

a type of request, a command in the voice input, and a state of each electronic device of the plurality of electronic devices.

12. The method of claim 1, further comprising:

recognizing a command in the voice input; and

in accordance with a determination that a type of the command is related to the first electronic device, responding to the detected voice input.

13. A first electronic device of a plurality of electronic devices, each of the plurality of electronic devices comprising:

one or more microphones;

a speaker;

one or more processors; and

memory storing one or more programs to be executed by the one or more processors, the one or more programs comprising instructions for;

detecting a voice input;

determining a first quality score for the detected voice input;

receiving quality scores generated by the other devices of the plurality of electronic devices for detection of the voice input by the other devices;

in accordance with a determination that the first quality score is not the highest amongst the quality scores for the voice input generated by the plurality of electronic devices;

identifying a criterion associated with the voice input; and

in accordance with a determination that the identified criterion is the most relevant to the first electronic device, responding to the detected input.

14. The device of claim 13, further comprising instructions for:

awakening the first electronic device by a plurality of affordances including a voice-based affordance; and

wherein detecting the voice input is in response to the awakening of the first electronic device.

15. The device of claim 13, wherein the first quality score comprises a confidence level of detection of the voice input and/or a signal-to-noise rating of detection of the voice input.

16. The device of claim 13, wherein the criterion comprises one or more of:

a type of request, a command in the voice input, and a state of each electronic device of the plurality of electronic devices.

17. A non-transitory computer readable storage medium storing one or more programs, the one or more programs comprising instructions which, when executed by a first electronic device of a plurality of electronic devices, cause the first electronic device to perform operations comprising:

detecting a voice input;

determining a first quality score for the detected voice input;

receiving quality scores generated by the other devices of the plurality of electronic devices for detection of the voice input by the other devices;

in accordance with a determination that the first quality score is not the highest amongst the quality scores for the voice input generated by the plurality of electronic devices;

identifying a criterion associated with the voice input; and

in accordance with a determination that the identified criterion is the most relevant to the first electronic device, responding to the detected input.

18. The computer readable storage medium of claim 17, further comprising instructions which, when executed by the first electronic device, cause the first electronic device to perform operations comprising:

communicating to the other devices of the plurality of electronic devices to forgo responding to the detected output.

19. The computer readable storage medium of claim 17, wherein the responding to the detected input comprises outputting an audible and/or a visual response to the detected voice input.

20. The computer readable storage medium of claim 17, wherein the plurality of electronic devices is communicatively coupled through a local network;

and

the communicating and receiving are performed through the local network.