Electronic apparatus and controlling method thereof

1. An electronic apparatus comprising:

a processor; and

a memory configured to store at least one instruction executable by the processor,

wherein the processor is configured to:

input first audio data to an artificial intelligence model corresponding to user information, and

obtain second audio data from the artificial intelligence model,

wherein the artificial intelligence model is a model learned based on first learning audio data obtained by recording a sound source with a first recording device, second learning audio data obtained by recording the sound source with a second recording device, and information on a recording device for obtaining the second learning audio data, and

wherein the second learning audio data is binaural audio data.

2. The electronic apparatus as claimed in claim 1 , further comprising:

a camera;

an outputter; and

a display,

wherein the processor is configured to:

obtain the user information based on a user image obtained through the camera,

identify whether or not a sound output device is connected to the outputter, and

control the display to display a guide user interface (UI) for guiding the connection of the sound output device based on identifying that the sound output device is not connected to the outputter, and

wherein the sound output device is at least one of an earphone or a headphone.

3. The electronic apparatus as claimed in claim 1 , wherein the processor is configured to input the first audio data to an artificial intelligence model corresponding to at least one of context information of the electronic apparatus or information on a space where the user is located, based on at least one of the context information of the electronic apparatus or the information on the space where the user is located being obtained, and

wherein the artificial intelligence model is a model learned based on at least one of the context information of the electronic apparatus or the information on the space where the user is located, the first learning audio data, the second learning audio data, and the information on the recording device for obtaining the second learning audio data.

4. The electronic apparatus as claimed in claim 3 , wherein the context information of the electronic apparatus includes at least one of information on an application executed in the electronic apparatus or audio volume information set in the electronic apparatus.

5. The electronic apparatus as claimed in claim 3 , further comprising:

a display,

wherein the context information of the electronic apparatus is information on an application executed in the electronic apparatus, and

wherein the processor is configured to control the display to display a UI that inquires whether to obtain the second audio data from the artificial intelligence model, based on the application executed in the electronic apparatus being an audio related application.

6. The electronic apparatus as claimed in claim 1 , wherein the user information includes at least one of user body information or user identification information,

wherein the user body information includes at least one of a user head size, a user head shape, a user head circumference, a position of a user ear, a user ear shape, or a user ear size, and

wherein the user identification information includes at least one of user gender, user age, or user hearing.

7. The electronic apparatus as claimed in claim 1 , wherein the recording device includes at least one of a human head model, a human ear model, or a plurality of microphones, and the information on the recording device for obtaining the second learning audio data includes information on at least one of a human head model size, a human head model shape, a human ear model size, or a human ear model shape.

8. The electronic apparatus as claimed in claim 1 , wherein the artificial intelligence model is a model learned based on the first learning audio data, the second learning audio data, the information on the recording device for obtaining the second learning audio data, and information on a recording situation of the first learning audio data and the second learning audio data,

wherein the information on the recording situation includes at least one of sound source distance information or recording space information, and

wherein the processor is configured to obtain virtual space content including sound source information and space information, based on an application executed in the electronic apparatus being an application related to a virtual space, and input the first audio data to an artificial intelligence model corresponding to the obtained virtual space content.

9. The electronic apparatus as claimed in claim 1 , wherein a neural network in which the artificial intelligence model is learned is configured to:

include a plurality of layers,

receive the first learning audio data, and

output prediction audio data in a time domain based on a calculation through the plurality of layers, and

wherein parameters used in the plurality of layers are learned based on a cost function for comparing the prediction audio data output in the time domain and the second learning audio data, respectively, in a frequency domain.

10. The electronic apparatus as claimed in claim 9 , wherein the cost function uses a first loss value obtained based on signal intensity of the prediction audio data and signal intensity of the second learning audio data, a second loss value obtained based on intensity for each frequency of the prediction audio data and intensity for each frequency of the second learning audio data, or a third loss value obtained based on noise information of the prediction audio data and noise information of the second learning audio data.

11. The electronic apparatus as claimed in claim 10 , wherein a first weight applied to a difference between first frequency intensity of the prediction audio data and the first frequency intensity of the second learning audio data is different from a second weight applied to a difference between second frequency intensity of the prediction audio data and the second frequency intensity of the second learning audio data.

12. A controlling method of an electronic apparatus that stores at least one instruction executable by the electronic apparatus, the controlling method comprising:

inputting first audio data to an artificial intelligence model corresponding to user information; and

obtaining second audio data from the artificial intelligence model,

wherein the artificial intelligence model is a model learned based on first learning audio data obtained by recording a sound source with a first recording device, second learning audio data obtained by recording the sound source with a second recording device, and information on a recording device for obtaining the second learning audio data, and

wherein the second learning audio data is binaural audio data.

13. The controlling method as claimed in claim 12 , further comprising:

obtaining the user information based on a user image obtained through a camera,

identifying whether or not a sound output device is connected to an outputter, and

displaying a guide user interface (UI) for guiding the connection of the sound output device based on identifying that the sound output device is not connected to the outputter,

wherein the sound output device is at least one of an earphone or a headphone.

14. The controlling method as claimed in claim 12 , wherein in the inputting of the first audio data, based on at least one of context information of the electronic apparatus or information on a space where the user is located being obtained, the first audio data is input to an artificial intelligence model corresponding to at least one of the context information of the electronic apparatus or the information on the space where the user is located, and

wherein the artificial intelligence model is a model learned based on at least one of the context information of the electronic apparatus or the information on the space where the user is located, the first learning audio data, the second learning audio data, and the information on the recording device for obtaining the second learning audio data.

15. The controlling method as claimed in claim 14 , wherein the context information of the electronic apparatus includes at least one of information on an application executed in the electronic apparatus or audio volume information set in the electronic apparatus.

16. The controlling method as claimed in claim 14 , wherein the context information of the electronic apparatus is information on an application executed in the electronic apparatus, and

wherein the controlling method further includes displaying a UI that inquires whether to obtain the second audio data from the artificial intelligence model, based on the application executed in the electronic apparatus being an audio related application.

17. The controlling method as claimed in claim 12 , wherein the user information includes at least one of user body information or user identification information,

wherein the user body information includes at least one of a user head size, a user head shape, a user head circumference, a position of a user ear, a user ear shape, or a user ear size, and

wherein the user identification information includes at least one of user gender, user age, or user hearing.

18. The controlling method as claimed in claim 12 , wherein the recording device includes at least one of a human head model, a human ear model, or a plurality of microphones, and the information on the recording device for obtaining the second learning audio data includes information on at least one of a human head model size, a human head model shape, a human ear model size, or a human ear model shape.

19. The controlling method as claimed in claim 12 , wherein the artificial intelligence model is a model learned based on the first learning audio data, the second learning audio data, the information on the recording device for obtaining the second learning audio data, and information on a recording situation of the first learning audio data and the second learning audio data,

wherein the information on the recording situation includes at least one of sound source distance information or recording space information, and

wherein the controlling method further includes obtaining virtual space content including sound source information and space information, based on an application executed in the electronic apparatus being an application related to a virtual space, and inputting the first audio data to an artificial intelligence model corresponding to the obtained virtual space content.

20. A non-transitory computer readable medium storing computer instructions for causing an electronic apparatus to perform an operation when executed by a processor of the electronic apparatus, wherein the operation includes:

obtaining user information based on a user image obtained through a camera;

inputting input audio data to an artificial intelligence model corresponding to the user information; and

obtaining output audio data from the artificial intelligence model,

wherein the artificial intelligence model is a model learned based on first learning audio data obtained by recording a sound source with a first recording device, second learning audio data obtained by recording the sound source with a second recording device, and information on a recording device for obtaining the second learning audio data, and

wherein the second learning audio data is binaural audio data.