| CPC G10L 15/22 (2013.01) [G10L 15/063 (2013.01); G10L 15/10 (2013.01); G10L 15/142 (2013.01); G10L 15/16 (2013.01); G10L 15/30 (2013.01)] | 12 Claims |
|
1. An electronic device comprising:
a communication interface;
memory;
a microphone;
a speaker;
a display;
a main processor; and
a sub-processor configured to activate the main processor by recognizing a wake-up word included in a voice input,
wherein the memory stores instructions that, when executed, cause the main processor to:
receive from a user a first voice input to register the wake-up word through the microphone;
determine whether the first voice input includes a specified word, wherein to determine whether the first voice input includes the specified word, the instructions cause the main processor to:
transmit the first voice input to an external server through the communication interface; and
receive a determination result of determining whether the first voice input includes the specified word, from the external server through the communication interface;
when the determination result indicates that the first voice input does not include the specified word:
display a first user interface (UI) guiding the user to speak a word identical to the first voice input, through the display, wherein the first UI requests to receive a second voice input including the word identical to the first voice input;
receive the second voice input from the user, through the microphone;
when receiving the second voice input, determine whether the second voice input is identical to the first voice input;
when the first voice input is different from the second voice input, output a second UI for receiving a third voice input identical to the first voice input, through the display;
when the first voice input is identical to the second voice input, generate a wake-up word recognition model for recognizing the wake-up word based on the first voice input and the second voice input; and
store the generated wake-up word recognition model in the memory based on the first voice input and the second voice input; and
when the determination result indicates that the first voice input includes the specified word, output a third UI for requesting a fourth voice input different from the first voice input, through the display, wherein the third UI does not include the word identical to the first voice input,
wherein the sub-processor is configured to activate the main processor by recognizing the registered wake-up word,
wherein the sub-processor consumes power less than the main processor, and
wherein when the main processor is activated, the instructions cause the activated main processor to:
receive a fifth voice input to perform a specified task and the wake-up word, through the microphone;
transmit the fifth voice input and the received wake-up word to the external server through the communication interface;
determine whether the received wake-up word includes the specified word by receiving a determination result of determining whether the transmitted wake-up word includes the specified word, from the external server through the communication interface;
when the determination result indicates that the transmitted wake-up word does not include the specified word:
receive a first response corresponding to the fifth voice input from the external server through the communication interface, wherein the first response includes action information for performing the specified task and a wake-up name of the electronic device included in the wake-up word; and
output the first response, through the speaker or the display; and
when the determination result indicates that the transmitted wake-up word includes the specified word:
receive a second response corresponding to the fifth voice input from the external server through the communication interface, wherein the second response includes the action information for performing the specified task and a name different from the wake-up word; and
output the second response, through the speaker or the display.
|