Method of providing service based on location of sound source and speech recognition device therefor

1. A speech recognition device comprising:

at least one microphone configured to receive a sound signal from a first sound source; and

at least one processor configured to:

determine a direction of the first sound source based on the sound signal,

determine whether the direction of the first sound source is in a registered direction, and

based on whether the direction of the first sound source is in the registered direction, recognize a speech from the sound signal regardless of whether the sound signal comprises a wake-up keyword as a part of the sound signal,

wherein the at least one processor is further configured to:

based on a plurality of sound signals received from a plurality of directions, determine a frequency that a speech recognition service is requested, respectively, in correspondence to the plurality of directions, and

determine a direction, which corresponds to a determined frequency equal to or greater than a critical value from among the plurality of directions, as the registered direction.

2. The speech recognition device of claim 1 ,

wherein the sound signal requesting a speech recognition service comprises a sound signal including a wake-up keyword,

wherein the wake-up keyword comprises at least one keyword to request a speech recognition service from the speech recognition device based on a speech signal following the wake-up keyword, and

wherein the wake-up keyword comprises at least one of a human speech and a non-speech sound.

3. The speech recognition device of claim 1 , wherein the at least one processor is further configured to:

determine whether a noise signal is received based on the plurality of sound signals received from the plurality of directions, and

determine a direction, in which the noise signal is received for a reference amount of time or longer from among the plurality of directions, as a shading direction.

4. The speech recognition device of claim 3 , wherein the at least one processor is further configured to:

determine a time period during which the noise signal is received for the reference amount of time or longer, and

determine a direction, in which the noise signal is received, as the shading direction in correspondence to the time period.

5. The speech recognition device of claim 1 , wherein the at least one processor is further configured to determine whether the direction of the first sound source is in the registered direction by determining whether the direction of the first sound source is within a critical angle from the registered direction.

6. The speech recognition device of claim 5 , wherein the at least one processor is further configured to:

determine a variation of the direction of the first sound source, and

determine whether the variation is within the critical angle to determine whether the direction of the first sound source is within the critical angle from the registered direction.

7. The speech recognition device of claim 1 , further comprising:

a storage configured to store information about a device located in the registered direction,

wherein the at least one processor is further configured to, when the direction of the first sound source is in the registered direction, provide a result of speech recognition based on the information about the device corresponding to the registered direction.

8. The speech recognition device of claim 1 , further comprising:

a plurality of light-emitting devices configured to indicate a plurality of directions,

wherein the at least one processor is further configured to control a light-emitting device corresponding to the registered direction from among the plurality of light-emitting devices to emit light differently from remaining light-emitting devices of the plurality of light-emitting devices.

9. The speech recognition device of claim 1 , further comprising:

an interface including a plurality of touch elements corresponding to a plurality of directions,

wherein the at least one processor is further configured to determine a first direction as the registered direction corresponding to receiving a user input for touching a touch element corresponding to the first direction from among the plurality of touch elements.

10. The speech recognition device of claim 1 ,

wherein the at least one microphone is further configured to receive a first speech signal output from a first user and a second speech signal output from a second user different from the first user, and

wherein the at least one processor is further configured to, when a priority corresponding to a direction to the first user is higher than a priority corresponding to a direction to the second user, recognize only the first speech signal output from the first user while excluding the second speech signal output from the second user.

11. A speech recognition method, the method comprising:

receiving a sound signal from a first sound source;

determining a direction of the first sound source based on the sound signal;

determining whether the direction of the first sound source is in a registered direction; and

recognizing a speech from the sound signal regardless of whether the sound signal comprises a wake-up keyword as a part of the sound signal, based on whether the direction of the first sound source is in the registered direction,

wherein the method further comprises:

based on a plurality of sound signals received from a plurality of directions, determining a frequency that a speech recognition service is requested, respectively, in correspondence to the plurality of directions; and

determining a direction, which corresponds to a determined frequency equal to or greater than a critical value from among the plurality of directions, as the registered direction.

12. The method of claim 11 ,

wherein the sound signal requesting a speech recognition service comprises a sound signal including a wake-up keyword,

wherein the wake-up keyword comprises at least one keyword to request a speech recognition service from a speech recognition device based on a speech signal following the wake-up keyword, and

wherein the wake-up keyword comprises at least one of a human speech and a non-speech sound.

13. The method of claim 11 , further comprising:

determining whether a noise signal is received based on the plurality of sound signals received from the plurality of directions; and

determining a direction, in which the noise signal is received for a reference amount of time or longer from among the plurality of directions, as a shading direction.

14. The method of claim 13 , further comprising:

determining a time period during which the noise signal is received for the reference amount of time or longer; and

determining a direction, in which the noise signal is received, as the shading direction in correspondence to the time period.

15. The method of claim 11 , wherein the determining of whether the direction of the first sound source is in the registered direction comprises determining whether the direction of the first sound source is within a critical angle from the registered direction.

16. The method of claim 15 , wherein the determining of whether the direction of the first sound source is within the critical angle from the registered direction comprises:

determining a variation of the direction of the first sound source; and

determining whether the determined variation is within the critical angle.

17. The method of claim 11 , further comprising:

storing information about a device located in the registered direction; and

when the direction of the first sound source is in the registered direction, providing a result of speech recognition based on the information about the device corresponding to the registered direction.

18. The method of claim 11 , further comprising controlling a light-emitting device corresponding to the registered direction from among a plurality of light-emitting devices to emit light differently from the remaining light-emitting devices.

19. The method of claim 11 , further comprising determining a first direction as the registered direction corresponding to receiving user input for touching a touch element corresponding to the first direction from among a plurality of touch elements.

20. The method of claim 11 ,

wherein the receiving of the sound signal from the first sound source comprises receiving a first speech signal output from a first user and a second speech signal output from a second user different from the first user, and

wherein the recognizing of the speech comprises, when a priority corresponding to a direction to the first user is higher than a priority corresponding to a direction to the second user, recognizing only the first speech signal output from the first user while excluding the second speech signal output from the second user.

21. The method of claim 11 , wherein the registered direction is a direction input by voice indicating a direction relative to a speech recognition device.