Method of receiving commands for activating voice-recognition service and electronic device for implementing same

Patent metadata

Field	Value
Publication number	US-10692495-B2
Application number	US-201816113602-A
Country	US
Kind code	B2
Filing date	Aug 27, 2018
Priority date	Aug 25, 2017
Publication date	Jun 23, 2020
Grant date	Jun 23, 2020

Abstract

An electronic device is provided. The electronic device includes at least one processor and a memory electrically connected to the processor. The memory stores instructions, and the instructions are configured to cause the processor, when executed, to activate a voice recognition service in response receiving a specified user input, receive a voice command while activating the voice recognition service, provide a feedback for the voice command, deactivate the voice recognition service after providing the feedback, receive a voice signal distinct from the specified user input while deactivating the voice recognition service, in response to receiving the voice signal, identify whether at least a portion of the voice signal corresponds to a wake-up command that is obtained from the voice command, and in response to identifying that the at least the portion of the voice signal corresponds to the wake-up command, activate the voice recognition service.

First claim

What is claimed is:

1. An electronic device comprising:
a speaker;
a microphone;
a communication interface;
at least one processor electrically connected to the speaker, the microphone, and the communication interface; and
a memory electrically connected to the processor,
wherein the memory stores instructions, and the instructions are configured to cause the processor, when executed, to:
activate a voice recognition service in response receiving a specified user input, receive a voice command during activation of the voice recognition service;
provide a feedback for the voice command;
deactivate the voice recognition service after providing the feedback;
receive a voice signal distinct from the specified user input during deactivation of the voice recognition service,
in response to receiving the voice signal, identify whether at least a portion of the voice signal corresponds to a wake-up command that is obtained from the voice command, and
in response to identifying that the at least the portion of the voice signal corresponds to the wake-up command, activate the voice recognition service.

2. The electronic device of claim 1 , wherein the instructions are further configured to cause the processor, when executed, to:
extract text information from the voice command,
acquire at least one word from the text information, and
register the acquired word as the wake-up command.

3. The electronic device of claim 2 , wherein the instructions are further configured to cause the processor, when executed, to:
acquire at least one first word from the text information,
acquire at least one second word related to the at least one first word, and
register the at least one first word or the at least one second word as the wake-up command, and
wherein the at least one second word includes synonym words of the at least one first word.

4. The electronic device of claim 3 , wherein the instructions are further configured to cause the processor, when executed, to:
acquire at least one third word based on the at least one first word and the at least one second word, and
register the at least one third word as the wake-up command.

5. The electronic device 1 , wherein the instructions are further configured to cause the processor, when executed, to count an activation standby time after providing the feedback for the voice command, and when a voice is not detected during the activation standby time, deactivate the voice recognition service.

6. The electronic device of claim 1 , wherein the instructions are further configured to cause the processor, when executed, to determine whether the voice signal includes the specified user input, and if the voice signal includes the specified user input, delete the obtained wake-up command.

7. The electronic device of claim 1 , wherein the instructions are further configured to cause the processor, when executed, to detect, by using a camera or a microphone of the electronic device, that a plurality of users is located within a predetermined area from the electronic device,
determine, based on the plurality of users, whether to enable or disable the wake-up command which is obtained from the voice command.

8. The electronic device of claim 7 , wherein the instructions are further configured to cause the processor, when executed, to disable the wake-up command to activate the voice recognition service if the number of speakers is not equal to one.

9. The electronic device of claim 1 , wherein the instructions are further configured to cause the processor, when executed, to determine whether a current condition corresponds to condition information, and when the current condition corresponds to the condition information, enable at least one wake-up command corresponding to the condition information.

10. The electronic device of claim 9 , wherein the instructions are further configured to cause the processor, when executed, to determine whether the condition information expires, and when the condition information expires, disable at least one wake-up command corresponding to the condition information.

11. The electronic device of claim 1 , wherein the specified user input includes at least one of a sound signal of a specified word, a specified touch, and a specified button.

12. The electronic device of claim 1 , wherein the instructions are further configured to cause the processor, when executed, to display a user interface for controlling the wake-up command after providing of the feedback for the voice command.

13. The electronic device of claim 1 , wherein the instructions are further configured to cause the processor, when executed, to control the voice recognition service using the wake-up command according to speaker identification while the voice recognition service is activated.

14. The electronic device of claim 1 , wherein the at least one processor includes a first processor corresponding to a low power processor, and a second processor corresponding to a main processor, and
wherein the first processor is configured to receive the voice signal by controlling at least one of the speaker, the microphone, and the memory, while the second processor is in a sleep mode for deactivating the voice recognition service.

15. An electronic device comprising:
a speaker;
a microphone;
a communication interface;
at least one processor electrically connected to the speaker, the microphone, or the communication interface; and
a memory electrically connected to the at least one processor,
wherein the memory stores instructions, and the instructions are configured to cause the processor, when executed, to:
receive at least one main wake word through the microphone,
in response to the received main wake word, activate a voice recognition function provided from an external server or implemented in the electronic device,
receive a user's speech including at least one user wake word through the microphone, and
activate the voice recognition function in response to the received user wake word without the main wake word.

16. The electronic device of claim 15 , wherein the at least one main wake word includes a name or a title related to the electronic device.

17. The electronic device of claim 15 , wherein the at least one user wake word includes a name or a title selected by a user.

18. The electronic device of claim 15 , wherein the instructions are further configured to cause the processor, when executed, to activate the voice recognition function in response to the received user wake word only during a set time period.

19. The electronic device of claim 15 , wherein the at least one processor includes a first processor corresponding to a low power processor, and a second processor corresponding to a main processor, and
wherein the first processor is configured to receive the voice signal by controlling at least one of the speaker, the microphone, and the memory, while the second processor is in a sleep mode for deactivating the voice recognition service.

20. An electronic device comprising:
a speaker;
a microphone;
a communication interface;
a processor electrically connected to the speaker, the microphone, or the communication interface; and
a memory electrically connected to the processor,
wherein the memory stores instructions, and the instructions are configured to cause the processor, when executed, to:
in response to receiving in a state disabling a voice recognition service, a first voice signal that is distinct from a specified user input for enab

Assignees

• Samsung Electronics Co Ltd

Inventors

• Woo Kwang-Taek
• Park Kwan-Shik
• Shin Chang-Hoon
• Kim Ki-Seok
• An Jin-Wan

Classifications

• G10L2015/086

  Recognition of spelled words · CPC title

• G10L17/24

  the user being prompted to utter a password or a predefined phrase · CPC title

• G10L15/02

  Feature extraction for speech recognition; Selection of recognition unit · CPC title

• G10L15/28 Primary

  Constructional details of speech recognition systems · CPC title

• G10L2015/088

  Word spotting · CPC title