Electronic device and method of controlling the same

1. An electronic device comprising:

communication circuitry configured to perform communication with a voice recognition server;

a microphone configured to receive a first voice information; and

one or more processors configured to:

determine whether a wake-up word is received within a preset time, wherein the preset time begins after receiving the voice information; and

perform voice recognition on the received first voice information prior to the wake-up word based on the wake-up word being received within the preset time;

receive a second voice information within a second preset time and conversation information between a plurality of people, wherein the second preset time begins when the wake-up word is received;

determine whether a function that may be performed in the electronic device exists based on context information extracted from the received conversation information;

perform voice recognition on the received conversation information based on a determination that the function that may be performed in the electronic device exists;

transmit, to the voice recognition server via the communication circuitry, a portion of the received first voice information, the received second voice information and the received conversation information based on satisfying a preset condition and a determination that the function does not exist, wherein the preset condition corresponds to the wake-up word being received within the preset time and the received second voice information being received within received second preset time; and

execute a specific function based on the portion of the received first voice information and the received second voice information.

2. The electronic device of claim 1 , wherein the received first voice information representing the wake-up word comprises at least a frequency or a waveform related to the wake-up word,

wherein the one or more processors are further configured to determine whether the wake-up word is received based on whether the frequency or waveform related to the wake-up word matches the received first voice information.

3. The electronic device of claim 1 , wherein the one or more processors are further configured to perform no voice recognition on the received first voice information based on the wake-up word not being received within the preset time.

4. The electronic device of claim 1 , wherein the one or more processors are further configured to transmit, to the voice recognition server via the communication circuitry, a first portion of the received first voice information based on the second voice information being received after a lapse of the second preset time and execute a first specific function based on the first portion of the received first voice information.

5. The electronic device of claim 1 , wherein the first preset time or the second preset time are set by a user.

6. The electronic device of claim 1 , wherein the transmitting the portion of the received first voice information and the received second voice information based on satisfying the preset condition is transmitted in real-time or on a word-by-word basis.

7. The electronic device of claim 6 , wherein the one or more processors are further configured to:

combine the received first voice information received before the wake-up word and the received second voice information received after the wake-up word into a single voice information; and

transmit, to the voice recognition server via the communication circuitry, the single voice information.

8. The electronic device of claim 1 , further comprising a memory, wherein the one or more processors are further configured to store a preset recording time duration of the received voice information in the memory.

9. The electronic device of claim 8 , wherein the one or more processors are further configured to delete the preset recording time duration of the received first voice information when the wake-up word is not received within the preset time.

10. The electronic device of claim 1 , wherein the one or more processors are further configured to output notification information comprising a selectable option to execute a voice recognition function when the wake-up word is received within the preset time.

11. The electronic device of claim 1 , further comprising a memory configured to store a plurality of category information corresponding to voice recognition functions,

wherein the one or more processors are further configured to:

determine a category of the received first voice information; and

perform voice recognition on the received first voice information when the determined category corresponds to one of the plurality of category information stored at the memory.

12. The electronic device of claim 11 , wherein:

the stored plurality of category information comprises categorized keywords and voice information corresponding to the categorized keywords; and

the one or more processors are further configured to determine a category of the received first voice information based on a comparison of the received first voice information and stored voice information corresponding to the categorized keywords.

13. The electronic device of claim 11 , wherein the one or more processors are further configured to output a response corresponding to the received first voice information prior to the wake-up word when the second voice information is not received for the second preset time following the wake-up word.

14. The electronic device of claim 11 , wherein the one or more processors are further configured to:

store a determined category of the received first voice information in the memory, and

perform voice recognition based on the determined category.

15. The electronic device of claim 14 , wherein the one or more processors are further configured to determine the determined category by extracting category information of a frequently uttered voice command.

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

a memory configured to store voice information of a preset speaker,

wherein the one or more processors are further configured to perform voice recognition on the received first voice information prior to the wake-up word when the received first voice information matches the stored voice information of the preset speaker.

17. The electronic device of claim 1 , wherein the one or more processors are further configured to:

determine whether the context information extracted from the received conversation information ends with an affirmative answer; and

perform voice recognition on the received conversation information without utterance of the wake-up word based on a determination that the context information extracted from the received conversation information ends with the affirmative answer to a search for specific information.