Granted Patent B1

US 10,026,401 · App. 14/980,533 · Granted Jul 17, 2018

Inventors: Rohan Mutagi (Redmond, WA); Isaac Michael Taylor (Seattle, WA)

Assignee: Amazon Technologies, Inc.

G10L15/22G10L15/265G10L2015/223

Abstract

Claims (90)

1. A method implemented by a computing device, the method comprising:

receiving a first audio signal generated by a microphone of a voice-controlled device based on first audio captured by the microphone;

performing speech recognition on the first audio signal to generate first text;

determining that a first portion of the first text includes a phrase indicating that the voice-controlled device is to be named;

determining that a second portion of the first text subsequent to the first portion of the first text includes a first functional identifier to be associated with the voice-controlled device;

storing, in memory of the computing device, the first functional identifier in association with an identifier of the voice-controlled device;

sending, to the voice-controlled device, a first configuration code to cause the voice-controlled device to perform first functionality corresponding to the first functional identifier;

receiving a second audio signal generated by the microphone of the voice-controlled device based on second audio captured by the microphone;

performing speech recognition on the second audio signal to generate second text;

determining that a first portion of the second text includes the phrase indicating that the voice-controlled device is to be named;

determining that a second portion of the second text subsequent to the first portion of the second text includes a second functional identifier to be associated with the voice-controlled device;

replacing, in the memory of the computing device, the first functional identifier with the second functional identifier; and

sending, to the voice-controlled device, a second configuration code to cause the voice-controlled device to perform second functionality corresponding to the second functional identifier.

2. The method as recited in claim 1 , further comprising:

determining that the first functional identifier includes a location qualifier from a plurality of predefined location qualifiers, the location qualifier indicating a location of the voice-controlled device within an environment; and

storing the location qualifier in association with the identifier of the voice-controlled device.

3. The method as recited in claim 2 , further comprising:

receiving a third audio signal;

performing speech recognition on the third audio signal to generate third text;

determining that third text represents a request that the voice-controlled device and a second device also associated with the location qualifier both perform an operation; and

sending an instruction to at least the voice-controlled device and the second device to perform the operation.

4. The method as recited in claim 1 , further comprising:

determining that the first functional identifier includes a device-type qualifier from a plurality of predefined device-type qualifiers, the device-type qualifier indicating a location of the voice-controlled device within an environment, and

storing the device-type qualifier in association with the identifier of the voice-controlled device.

5. The method as recited in claim 4 , further comprising:

receiving a third audio signal;

performing speech recognition on the third audio signal to generate third text;

determining that third text represents a request that voice-controlled device and a second device also associated with the device-type qualifier both perform an operation; and

sending an instruction to at least the voice-controlled device and the second device to perform the operation.

6. A method comprising:

receiving a first audio signal from a device that includes a microphone, the first audio signal generated based at least in part on sound captured by the microphone;

performing speech recognition on the first audio signal;

determining that a first portion of the first audio signal represents first speech indicating that the device is to be named;

determining that a second portion of the first audio signal, subsequent to the first portion of the first audio signal, indicates a functional identifier to be associated with the device;

storing the functional identifier in association with an identifier of the device;

receiving a second audio signal;

performing speech recognition on the second audio signal;

determining that the second audio signal represents second speech associated with the functional identifier and requesting to perform an operation;

determining that the functional identifier corresponds to the identifier of the device; and

sending an instruction to the device to perform the operation.

7. The method as recited in claim 6 , wherein the functional identifier includes a location qualifier that indicates a location of the device within an environment, and further comprising storing the location qualifier in association with the identifier of the device.

8. The method as recited in claim 7 , wherein the operation comprises a first operation, the instruction comprises a first instruction, and further comprising:

receiving a third audio signal;

performing speech recognition on the third audio signal;

determining that the third audio signal represents third speech requesting that the device and a second device also associated with the location qualifier both perform a second operation; and

sending a second instruction to at least the device and the second device to perform the second operation.

9. The method as recited in claim 6 , wherein the functional identifier includes a device-type qualifier that indicates a type of the device, and further comprising storing the device-type qualifier in association with the identifier of the device.

10. The method as recited in claim 9 , wherein the operation comprises a first operation, the instruction comprises a first instruction, and further comprising:

receiving a third audio signal;

performing speech recognition on the third audio signal;

determining that the third audio signal represents third speech requesting that the device and a second device also associated with the device-type qualifier both perform a second operation; and

sending a second instruction to at least the device and the second device to perform the second operation.

11. The method as recited in claim 6 , wherein the receiving the first audio signal from the device comprises receiving the first audio signal from the device at least partly in response to the device determining that an utterance includes a predefined word or phrase.

12. The method as recited in claim 6 , wherein the functional identifier comprises a first functional identifier, the storing comprises storing the first functional identifier in memory of a computing device, and further comprising:

receiving a third audio signal;

performing speech recognition on the third audio signal;

determining that the third audio signal represents third speech requesting that the device be associated with a second functional identifier; and

replacing, in the memory of the computing device, the first functional identifier with the second functional identifier.

13. The method as recited in claim 6 , further comprising sending, to the device and at least partly prior to the receiving of the first audio signal, data representing a suggestion of a functional identifier the device, the data for causing the device to present the suggestion of the functional identifier.

14. A system comprising:

one or more processors; and

one or more computer-readable media storing computer-executable instructions that, when executed, cause the one or more processors to:

receive a first audio signal from a device that includes a microphone, the first audio signal generated based at least in part on sound captured by the microphone;

perform speech recognition on the first audio signal;

determine that a first portion of the first audio signal represents first speech indicating that the device is to be named;

determining that a second portion of the first audio signal, subsequent to the first portion of the first audio signal, indicates a functional identifier to be associated with the device;

store the functional identifier in association with an identifier of the device;

receive a second audio signal;

perform speech recognition on the second audio signal;

determine that the second audio signal represents second speech specifying the functional identifier and a request to perform an operation;

determine that the functional identifier corresponds to the identifier of the device; and

send a command to the device to perform the operation.

15. The system as recited in claim 14 , wherein the functional identifier includes a location qualifier that indicates a location of the device within an environment, and the one or more processors are further caused to store the location qualifier in association with the identifier of the device.

16. The system as recited in claim 15 , wherein the operation comprises a first operation, the command comprises a first command, and the one or more processors are further caused to:

receive a third audio signal;

perform speech recognition on the third audio signal;

determine that the third audio signal represents third speech requesting that the device and a second device also associated with the location qualifier both perform a second operation; and

send a second command to at least the device and the second device to perform the second operation.

17. The system as recited in claim 14 , wherein the functional identifier includes a device-type qualifier that indicates a type of the device, and the one or more processors are further caused to store the device-type qualifier in association with the identifier of the device.

18. The system as recited in claim 17 , wherein the operation comprises a first operation, the command comprises a first command, and the one or more processors are further caused to:

receive a third audio signal;

perform speech recognition on the third audio signal;

determine that the third audio signal represents third speech requesting that the device and a second device also associated with the device-type qualifier both perform a second operation; and

send a second command to at least the device and the second device to perform the second operation.

19. The system as recited in claim 14 , wherein receive the first audio signal from the device comprises receive the first audio signal from the device at least partly in response to the device determining that an utterance includes a predefined word or phrase.

20. The system as recited in claim 14 , wherein the functional identifier comprises a first functional identifier, store the functional identifier comprises storage of the first functional identifier in memory of a computing device, and the one or more processors are further caused to:

receive a third audio signal;

perform speech recognition on the third audio signal;

determine that the third audio signal represents third speech requesting that the device be associated with a second functional identifier; and

replace, in the memory of the computing device, the first functional identifier with the second functional identifier.

Assignments (1)

Cited By (44)

US 12,197,817 US 12,198,057 US 12,200,297 US 12,211,490 US 12,211,502 US 12,216,894 US 12,217,748 US 12,219,314 US 12,230,291 US 12,236,932 US 12,236,952 US 12,260,234 US 12,277,954 US 12,283,269 US 12,293,763 US 12,301,635 US 12,316,706 US 12,327,549 US 12,327,556 US 12,333,404 US 12,347,433 US 12,360,734 US 12,361,943 US 12,367,879 US 12,386,434 US 12,386,491 US 12,387,716 US 12,401,720 US 12,401,721 US 12,424,220 US 12,477,470 US 12,505,832 US 12,513,479 US 12,518,756 US 12,526,337 US 12,556,606 US 12,608,171 US 12,609,988 US 12,615,313 US 12,619,452 US 12,626,700 US 12,627,738 US 12,699,543 US 12,711,962