Electronic device and method of operating voice recognition function

Patent metadata

Field	Value
Publication number	US-12027172-B2
Application number	US-202016895577-A
Country	US
Kind code	B2
Filing date	Jun 8, 2020
Priority date	Feb 16, 2015
Publication date	Jul 2, 2024
Grant date	Jul 2, 2024

Abstract

Provided is an electronic device that includes a first processor for receiving an audio signal, performing first voice recognition on the audio signal, and transferring a driving signal to a second processor based on a result of the first voice recognition. The second processor performs second voice recognition based on a voice signal by the first voice recognition or the audio signal, in response to the driving signal.

First claim

What is claimed is:

1. An electronic device comprising:
communication circuitry configured to communicate with a server:
memory for storing instructions; and
at least one processor comprising an audio input processor, a first processor and a second processor,
wherein the instructions, when executed by the at least one processor individually or collectively, cause the electronic device to:
receive, by the audio input processor, an audio signal,
determine, by the audio input processor, whether a level of the audio signal is greater than or equal to a threshold,
in response to the level of the audio signal being greater than or equal to the threshold, transfer, by the audio input processor, a first wake up signal for waking up the first processor and the audio signal to the first processor;
wake up the first processor based on the first wake up signal,
perform, by the first processor, a first voice recognition on the audio signal to extract a voice signal, wherein the first voice recognition comprises a keyword recognition and a speaker recognition based on the audio signal,
in response to success of the first voice recognition during the first voice recognition, transfer, by the first processor, a second wake up signal for waking up the second processor and the voice signal to the second processor,
wake up the second processor based on the second wake up signal,
perform, by the second processor, a second voice recognition based on the voice signal output by the first voice recognition, wherein the second voice recognition comprises a command recognition, and maintain, by the second processor, an off state of a display of the electronic device during the second voice recognition,
execute, by the second processor, an application associated with a voice command based on a result of the second voice recognition,
and
turn on, by the second processor, the display to display an execution screen of the application in response to success of the second voice recognition,
wherein, if the second voice recognition is successful, the communication circuitry transmits, to the server, at least one of a voice signal based on the second voice recognition or the audio signal, and receives, from the server, result information on a third voice recognition based on the at least one of the voice signal or the audio signal.

2. The electronic device of claim 1 , wherein the instructions further cause the electronic device to:
recognize, by the first processor, a voice trigger of a registered speaker for triggering a voice recognition function for the audio signal, and
recognize, by the second processor, a voice command of the registered speaker for executing a voice-based function for an audio signal input after recognition of the voice trigger is successful.

3. The electronic device of claim 1 , wherein the instructions further cause the electronic device to:
perform, by the first processor, the first voice recognition by switching from a sleep mode to an operational mode, based on the first wake up signal, and
perform, by the second processor, the second voice recognition by switching from a sleep mode to an operational mode, based on the second wake up signal.

4. The electronic device of claim 1 , wherein the instructions further cause the electronic device to:
switch, by the audio input processor, the first processor from a sleep mode to an operational mode based on the level of the audio signal.

5. The electronic device of claim 4 , wherein the instructions further cause the electronic device to:
perform, by the audio input processor, voice detection by determining the level on the audio signal, and
transfer, by the audio input processor, the first wake up signal and the audio signal, to the first processor if the level of the audio signal is greater than or equal to a preset threshold.

6. The electronic device of claim 1 , wherein the instructions further cause the electronic device to:
if the first voice recognition fails, switch the first processor from an operational mode to a sleep mode and,
if the second voice recognition fails, switch the first processor and the second processor from an operational mode to a sleep mode.

7. The electronic device of claim 1 , wherein the instructions further cause the electronic device to:
turn on, by the second processor, the display to display a function execution screen if the second voice recognition is successful while the display is in an off state and maintain the display in the off state if the second voice recognition fails, and
while the second voice recognition is performed, control, by the second processor, the display to output a screen indicating that the voice recognition is being performed, display a function execution screen if the second voice recognition succeeds and turn off the display if the second voice recognition fails.

8. The electronic device of claim 1 , wherein:
the first processor is an audio processor configured to process audio data transmitted to the second processor.

9. The electronic device of claim 1 , wherein the instructions further cause the electronic device to:
if the second processor succeeds in the second voice recognition transmit at least one of the audio signal or the voice signal based on the second voice recognition to the server for the third voice recognition,
when a voice command according to the third voice recognition is received from the server, perform a function of the electronic device corresponding to the received voice command, and
if failure information on the third voice recognition is received from the server, switching the second processor to a sleep mode.

10. A method of performing voice recognition by an electronic device, the method comprising:
receiving, by an audio input processor, an audio signal;
determining, by the audio input processor, whether a level of the audio signal is greater than or equal to a preset threshold;
in response to the level of the audio signal being greater than or equal to the preset threshold, transferring, by the audio input processor, a first wake up signal for waking up a first processor and the audio signal to the first processor;
waking up the first processor based on the first wake up signal;
performing, by the first processor, a first voice recognition on the audio signal to extract a voice signal, wherein the first voice recognition comprises a keyword recognition and a speaker recognition based on the audio signal;
in response to success of the first voice recognition during the first voice recognition, transferring, by the first processor, a second wake up signal for waking up a second processor and the voice signal to the second processor;
waking up the second processor based on the second wake up signal;
performing, by the second processor, a second voice recognition based on the voice signal output by the first voice recognition, wherein the second voice recognition comprises a command recognition;
executing, by the second processor, an application associated with a voice command based on a result of the second voice recognition;
maintaining, by the second processor, an off state of a display of the electronic device; and
turning, by the second processor, on the display to display an execution screen of the application in response to success of the second voice recognition,
wherein, if the second voice recognition is successful, transmitting, by communication circuitry, to a server, at least one of a voice signal based on the second voice recognition or the audio signal, and receiving, from the server, result information on a third voice recognition based on the at least one of the voice signal or the audio signal.

Assignees

• Samsung Electronics Co Ltd

Inventors

• Lee Taejin
• Chakladar Subhojit
• Lee Sanghoon
• Kim Kyungtae
• Kim Yuna
• Kim Junhui
• Shin Eunhye
• Lee Jaegeun
• Lim Hyunwoong

Classifications

• Y02D30/50

  in wire-line communication networks, e.g. low power modes or reduced link rate · CPC title

• Y02D10/00

  Energy efficient computing, e.g. low power processors, power management or thermal management · CPC title

• G06F1/3293

  by switching to a less power-consuming processor, e.g. sub-CPU · CPC title

• G06F1/3206

  Monitoring of events, devices or parameters that trigger a change in power modality · CPC title

• G10L15/26 Primary

  Speech to text systems (G10L15/08 takes precedence) · CPC title