ELECTRONIC DEVICE AND METHOD OF OPERATING VOICE RECOGNITION

• US 20160240194A1
• Filed: 02/16/2016
• Published: 08/18/2016
• Est. Priority Date: 02/16/2015
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: LEE, Taejin, LEE, Sanghoon, KIM, Yuna, KIM, Junhui, SHIN, Eunhye, LEE, Jaegeun, LIM, Hyunwoong, CHAKLADAR, Subhojit, KIM, Kyungtae
• Granted Patent: US 10,679,628 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 1/3206 Monitoring of events, devices or parameters that trigger a change in power modality
• CPC Class Codes: G06F 1/3293 by switching to a less power-consuming processor, e.g. sub-CPU
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• 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: Y02D 10/00 Energy efficient computing, e.g. low power processors, power management or thermal management
• CPC Class Codes: Y02D 30/50 in wire-line communication networks, e.g. low power modes or reduced link rate

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.

Claims

1. An electronic device comprising:

a first processor configured to

receive an audio signal,

perform a first voice recognition on the audio signal, and

transfer a driving signal to a second processor based on a result of the first voice recognition; and

the second processor configured to perform a second voice recognition based on at least one of a voice signal by the first voice recognition and the audio signal, in response to the driving signal.

2. The electronic device of claim 1, wherein the second processor performs the second voice recognition by switching from a sleep mode to an operational mode, based on the driving signal.

3. The electronic device of claim 1, wherein the second processor recognizes a voice trigger of a registered speaker for triggering a voice recognition function for the audio signal and recognizes a voice command of the registered speaker for executing a voice-based function for an audio signal input.

4. The electronic device of claim 1, further comprising:

a third processor for receiving the audio signal, performing third voice recognition, and switching the first processor from a sleep mode to an operational mode based on the third voice recognition.

5. The electronic device of claim 1, further comprising:

an audio processor for processing audio data transmitted/received to/from the second processor,

wherein the first processor is included in an audio input module for receiving the audio signal.

6. The electronic device of claim 5, wherein the audio input module remains activated regardless of whether the second processor is in an operational mode or a sleep mode.

7. The electronic device of claim 3, wherein the second processor recognizes the voice trigger and a voice command of the registered speaker.

8. The electronic device of claim 1, wherein the first processor buffers the voice signal through the first voice recognition of the audio signal, and

wherein the first processor transfers the buffered voice signal and audio signal to the second processor, if the second processor switches from a sleep mode to an operational mode.

9. The electronic device of claim 1, wherein, if the first voice recognition fails, the first processor switches from an operational mode to a sleep mode and, if the second voice recognition fails, the second processor switches from the operational mode to the sleep mode.

10. The electronic device of claim 1, further comprising:

a transceiver configured to communicate with a voice recognition server,

wherein, if the second voice recognition is successful, the transceiver transmits, for a third voice recognition, at least one of a voice signal by the second voice recognition or the audio signal to the voice recognition server, and receives result information on the third voice recognition from the voice recognition server.

11. The electronic device of claim 1, further comprising:

a display,

wherein, if the second voice recognition is successful while the display is in an off state, the second processor turns on the display to display a function execution screen and, if the second voice recognition fails, the display remains in the off state.

12. The electronic device of claim 1, further comprising:

a display,

wherein, while the second voice recognition is performed, the second processor controls the display to output a screen indicating that the voice recognition is being performed, and to display a function execution screen if the second voice recognition succeeds and to turn off the display if the second voice recognition fails.

13. A method of performing voice recognition by an electronic device, the method comprising:

receiving an audio signal;

performing first voice recognition on the audio signal, by a first processor;

transferring a driving signal to a second processor based on a result of the first voice recognition, by the first processor; and

performing second voice recognition based on at least one of a voice signal by the first voice recognition and the audio signal in response to the driving signal, by the second processor.

14. The method of claim 13, wherein performing the first voice recognition comprises switching from a sleep mode to an operational mode, based on the driving signal by the second processor.

15. The method of claim 13, wherein performing the first voice recognition comprises recognizing a voice trigger of a registered speaker for triggering a voice recognition function based on the audio signal, and

wherein performing the second voice recognition comprises recognizing the voice trigger of the registered speaker for triggering the voice recognition function for the audio signal and recognizing a command voice for executing a voice-based function for an audio signal input after recognition of the voice trigger is successful.

16. The method of claim 13, wherein performing the first voice recognition comprises:

performing a third voice recognition on the audio signal, by a third processor;

switching, by the third processor, the first processor from a sleep mode to an operational mode based on a result of the third voice recognition; and

performing the first voice recognition when the first processor is in the operational mode.

17. The method of claim 13, further comprising:

switching the first processor from an operation mode to a sleep mode if the first voice recognition fails; and

switching the second processor from an operation mode to a sleep mode if the second voice recognition fails.

18. The method of claim 13, further comprising:

switching the second processor from a sleep mode to an operation mode in response to the driving signal provided by the first processor;

buffering, by the first processor, the voice signal through the first voice recognition of the audio signal; and

transferring, by the first processor, the buffered voice signal and the audio signal to the second processor if the second processor switches from a sleep mode to an operational mode.

19. The method of claim 13, wherein performing the second voice recognition comprises:

performing a function of the electronic device corresponding to a voice command through the second voice recognition if the second processor succeeds in the second voice recognition; and

switching to a sleep mode if the second processor fails in the second voice recognition.

20. The method of claim 16, wherein performing the second voice recognition comprises:

if the second processor succeeds in the second voice recognition, transmitting the audio signal and the voice signal based on the second voice recognition to a voice recognition server for a fourth voice recognition;

when a voice command according to the fourth voice recognition is received from the voice recognition server, performing a function of the electronic device corresponding to the received voice command; and

if failure information on the fourth voice recognition is received from the voice recognition server, switching the second processor to a sleep mode.