Electronic device and method for controlling the same

1. An electronic device comprising:

a microphone to receive audio;

a communicator;

a memory configured to store computer-executable instructions; and

a processor configured to execute the computer-executable instructions to:

determine whether the received audio includes a predetermined trigger word spoken by a user,

based on determining that the predetermined trigger word is included in the received audio, activate a speech recognition function of the electronic device,

detect a movement of the user while the speech recognition function is activated, and

based on detecting the movement of the user, transmit a control signal, to a second electronic device to activate a speech recognition function of the second electronic device,

wherein the processor is further configured to:

compare a signal-to-noise ratio (SNR) of each of a plurality of frames constituting the received audio,

determine a frame among the plurality of frames having the SNR greater than or equal to a predetermined value,

recognize the predetermined trigger word based on the determined frame,

obtain first speech recognition information by performing speech recognition on the received audio,

receive second speech recognition information through the communicator from the second electronic device receiving the control signal,

obtain a final recognition result based on the first speech recognition information and the second speech recognition information,

obtain the final recognition result by applying a language model to the second speech recognition information when the second speech recognition information received from the second electronic device is information indicating that an acoustic model is applied and the language model is not applied, and

obtain the final recognition result by applying the acoustic model and the language model to the second speech recognition information when the second speech recognition information received from the second electronic device is information indicating that the acoustic model and the language model are not applied.

2. The electronic device according to claim 1 , wherein the processor is further configured to detect the movement of the user based on the received audio obtained through the microphone after the speech recognition function is activated.

3. The electronic device according to claim 1 , wherein the memory stores information on a plurality of electronic devices that receive the audio, and

wherein the processor is further configured to:

based on the movement of the user, identify one of the plurality of electronic devices that is closest to the user, and

control the communicator to transmit the control signal to the identified electronic device.

4. The electronic device according to claim 1 , wherein the processor is further configured to:

obtain time information on a time at which the control signal is transmitted to the second electronic device, and

match the first speech recognition information and the second speech recognition information based on the obtained time information to obtain the final recognition result.

5. The electronic device according to claim 4 , wherein the obtained time information includes information on an absolute time at which the control signal is transmitted and information on a relative time at which the control signal is transmitted to the second electronic device based on a time at which the speech recognition function of the electronic device is activated.

6. The electronic device according to claim 1 , wherein the processor is further configured to control the communicator to transmit the control signal, to the second electronic device, for providing a feedback on the final recognition result of the electronic device.

7. The electronic device according to claim 1 , wherein the processor is further configured to activate the speech recognition function of the electronic device when a second control signal for activating the speech recognition function is received from the second electronic device.

8. The electronic device according to claim 7 , wherein the processor is further configured to:

receive user information from the second electronic device, and

identify the received audio corresponding to the user information among a plurality of audios received through the microphone after the speech recognition function is activated by the second control signal.

9. The electronic device according to claim 7 , wherein the processor is further configured to:

obtain speech recognition information by performing speech recognition on the received audio until an utterance of the user ends after the speech recognition function is activated by the second control signal, and

transmit the obtained speech recognition information to the second electronic device.

10. The electronic device according to claim 7 , wherein the processor is further configured to identify a first user and a second user based on the received audio among a plurality of audios.

11. A method for controlling an electronic device, the method comprising:

receiving audio through a microphone of the electronic device;

determining whether the received audio includes a predetermined trigger word spoken by a user;

based on determining that the predetermined trigger word is included in the received audio, activating a speech recognition function of the electronic device;

detecting a movement of the user moves the speech recognition function is activated; and

based on detecting the movement of the user, transmitting a control signal, to a second electronic device to activate a speech recognition function of the second electronic device,

wherein the method further comprises:

comparing a signal-to-noise ratio (SNR) of each of a plurality of frames constituting the received audio,

determining a frame among the plurality of frames having the SNR greater than or equal to a predetermined value,

recognizing the predetermined trigger word based on the determined frame,

obtaining first speech recognition information by performing speech recognition on the received audio,

receiving second speech recognition information through a communicator from the second electronic device receiving the control signal,

obtaining a final recognition result based on the first speech recognition information and the second speech recognition information,

applying a language model to the second speech recognition information when the second speech recognition information received from the second electronic device is information indicating that an acoustic model is applied and the language model is not applied, and

applying the acoustic model and the language model to the second speech recognition information when the second speech recognition information received from the second electronic device is information indicating that the acoustic model and the language model are not applied.

12. The method according to claim 11 , wherein in the detecting the movement of the user is based on the received audio obtained through the microphone after the speech recognition function is activated.

13. The method according to claim 11 , wherein the electronic device stores information on a plurality of electronic devices that receive the audio, and

wherein the method further comprises: based on the movement of the user, identifying one of the plurality of electronic devices that is closest to the user, and

transmitting the control signal to the identified electronic device.

14. The method according to claim 11 , further comprising:

obtaining time information on a time at which the control signal is transmitted to the second electronic device, and

matching the first speech recognition information and the second speech recognition information based on the obtained time information to obtain the final recognition result.

15. The method according to claim 14 , wherein the obtained time information includes information on an absolute time at which the control signal is transmitted and information on a relative time at which the control signal is transmitted to the second electronic device based on a time at which the speech recognition function of the electronic device is activated.

16. An electronic device comprising:

a communicator;

a memory configured to include at least one instruction; and

a processor configured to execute the at least one instruction,

wherein the processor is configured to:

receive a first audio signal of a user speech through the communicator from a first external device,

determine whether the first audio signal of the user speech includes a predetermined trigger word spoken by a user,

based on determining that the first audio signal of the user speech includes the predetermined trigger word, control the communicator to transmit a control signal, to a second external device, for receiving a second audio signal of the user speech from the second external device located in a movement direction of the user when a movement of the user is detected based on information included in the received first audio signal,

receive the second audio signal through the communicator from the second external device, and

match the received first audio signal and the received second audio signal to perform speech recognition on the user speech,

wherein the processor is further configured to:

compare a signal-to-noise ratio (SNR) of each of a plurality of frames constituting the first audio signal,

determine a frame among the plurality of frames having the SNR greater than or equal to a predetermined value,

recognize the predetermined trigger word based on the determined frame,

obtain first speech recognition information by performing speech recognition on the first audio signal,

receive second speech recognition information through the communicator from a second electronic device receiving the control signal,

obtain a final recognition result based on the first speech recognition information and the second speech recognition information,

obtain the final recognition result by applying a language model to the second speech recognition information when the second speech recognition information received from the second electronic device is information indicating that an acoustic model is applied and the language model is not applied, and

obtain the final recognition result by applying the acoustic model and the language model to the second speech recognition information when the second speech recognition information received from the second electronic device is information indicating that the acoustic model and the language model are not applied.