Device and method for providing voice recognition service based on artificial intelligence

1. A method for recognizing a voice based on artificial intelligence for waking up an electronic device by distinguishing a user, the method comprising:

a first step of receiving a voice signal having a plurality of frames according to the user;

a second step of configuring a template associated with a wake-up voice according to the user; and

a third step of receiving a first voice signal and comparing the first voice signal with the template to determine whether the first voice signal matches the user, and controlling whether to wake-up the electronic device based on the determination result,

wherein the first step includes:

converting the voice signal into a frequency domain signal having a plurality of voice frames in a time domain; and

extracting at least one spectrum associated with each voice frame of the frequency domain signal,

wherein the second step includes:

distinguishing the user from the voice signals;

collecting the wake-up voice according to the user; and

matching the user with the wake-up voice according to the user,

wherein the third step includes:

extracting a spectrum for the first voice signal; and

comparing the spectrum for the first voice signal with the template preset for each user to calculate a distance,

wherein the calculating of the distance includes:

comparing a length of the distance with a predetermined error range; and

outputting a wake-up signal or a non-wake-up signal to control the electronic device when the length of the distance is greater than the predetermined error range.

2. The method of claim 1 , wherein the matching of the wake-up voice includes:

extracting a representative value or an average value from the at least one spectrum; and

materializing the at least one spectrum by clustering the representative value or the average value.

3. A device for recognizing a voice based on artificial intelligence for waking up an electronic device by distinguishing a user, the device comprising:

an input interface configured to receive a voice signal having a plurality of frames according to the user; and

a processor configured to:

convert the voice signal into a frequency domain signal having a plurality of voice frames in a time domain to extract at least one spectrum associated with each voice frame of the frequency domain signal,

configure a template associated with a wake-up voice according to the user, and

receive a first voice signal and compare the first voice signal with the template to determine whether the first voice signal matches the user, and control whether to wake-up the electronic device based on the determination result,

wherein the processor is configured to convert the voice signal into the frequency domain signal having the plurality of voice frames in the time domain to extract the at least one spectrum associated with each voice frame of the frequency domain signal,

wherein the processor is configured to:

distinguish the user from the voice signals,

collect the wake-up voice according to the user, and

match the user with the wake-up voice according to the user,

wherein the processor is configured to:

extract a spectrum for the first voice signal, and

compare the spectrum for the first voice signal with the template preset for each user to calculate a distance, and

wherein the device further comprises an output interface configured to:

compare a length of the distance with a predetermined error range, and

output a wake-up signal or a non-wake-up signal to control the electronic device when the length of the distance is greater than the predetermined error range.

4. The device of claim 3 , wherein the processor is configured to:

extract a representative value or an average value from the at least one spectrum; and

materialize the at least one spectrum by clustering the representative value or the average value to match the wake-up voice.