Electronic apparatus and method for controlling thereof

1. An electronic apparatus comprising:

a memory configured to store at least one instruction; and

a processor configured to execute the at least one instruction stored in the memory, which when executed causes the processor to control to:

acquire input data to be input into a text-to-speech (TTS) module for outputting a voice through the TTS module,

acquire a voice signal corresponding to the input data through the TTS module,

identify, by the processor, an emotion of the voice signal,

detect, by the processor, an error in the voice signal based on the identified the emotion of the voice signal,

correct the input data based on a result of detecting the error, and

acquire a corrected voice signal corresponding to the input data corrected based on the result of detecting the error through the TTS module.

2. The electronic apparatus of claim 1 , wherein the input data comprises first text data, and

the processor when executing the at least one instruction is further configured to:

convert the voice signal into second text data,

compare the first text data included in the input data and the second text data, and

detect the error in the voice signal based on a result of comparing the first text data and the second text data.

3. The electronic apparatus of claim 1 , wherein the input data comprises data related to emotions, and

the processor when executing the at least one instruction is further configured to:

identify the emotion of the voice signal based on a frequency characteristic of the voice signal,

compare the data related to emotions included in the input data and the emotion, and

detect the error in the voice signal based on a result of comparing the data related to emotions included in the input data and the emotion.

4. The electronic apparatus of claim 1 , wherein the processor when executing the at least one instruction is further configured to:

based on detecting the error in the voice signal, correct at least one of a spacing or a punctuation mark of text data included in information on the input data, and

input corrected input data having the at least one of the spacing or the punctuation mark of the text data into the TTS module.

5. The electronic apparatus of claim 1 , wherein the processor when executing the at least one instruction is further configured to:

based on detecting the error in the voice signal, correct the input data by applying a speech synthesis markup language (SSML) to text data included in the input data, and

input corrected input data having the speech synthesis markup language (SSML) applied to the text data into the TTS module.

6. The electronic apparatus of claim 1 , wherein the processor when executing the at least one instruction is further configured to:

convert a received user voice into text data by using a voice recognition module, analyze an intent of the text data, and

acquire response information corresponding to the received user voice as the input data.

7. The electronic apparatus of claim 1 , further comprising:

a speaker,

wherein the processor when executing the at least one instruction is further configured to:

add an indicator indicating correction to the voice signal, and

output the voice signal having the indicator through the speaker.

8. The electronic apparatus of claim 1 , further comprising:

a speaker; and

a microphone,

wherein the processor when executing the at least one instruction is further configured to:

output the voice signal through the speaker, and

based on the voice signal output through the speaker being received through the microphone, detect the error in the voice signal received through the microphone based on the input data.

9. The electronic apparatus of claim 8 , wherein the processor when executing the at least one instruction is further configured to:

identify an identity of the voice signal received through the microphone,

based on the voice signal received through the microphone being the voice signal output through the speaker based on the identity, detect the error in the voice signal, and

based on the voice signal received through the microphone having been uttered by a user based on the identity, convert the voice signal into text data by using a voice recognition module, and analyze an intent of the text data and acquire response information corresponding to the received user voice as the input data.

10. The electronic apparatus of claim 1 , further comprising:

a communicator,

wherein the processor when executing the at least one instruction is further configured to:

transmit the voice signal to an external apparatus through the communicator.

11. A method of controlling an electronic apparatus, the method comprising:

acquiring input data to be input into a text-to-speech (TTS) module for outputting a voice through the TTS module;

acquiring a voice signal corresponding to the input data through the TTS module;

identifying, by at least one processor of the electronic apparatus, an emotion of the voice signal;

detecting, by the at least one processor, an error in the voice signal based on the identified emotion of the voice signal;

correcting the input data based on a result of the detecting the error; and

acquiring a corrected voice signal corresponding to the input data corrected based on the result of detecting the error through the TTS module.

12. The method of claim 11 , wherein the input data comprises first text data, and

wherein the detecting the error comprises:

converting the voice signal into second text data;

comparing the first text data included in the input data and the second text data; and

detecting the error in the voice signal based on a result of the comparing the first text data and the second text data.

13. The method of claim 11 , wherein the input data comprises data related to emotions, and

wherein the detecting the error comprises:

identifying the emotion of the voice signal based on a frequency characteristic of the voice signal;

comparing the data related to emotions included in the input data and the emotion; and

detecting the error in the voice signal based on a result of comparing the data related to emotions included in the input data and the emotion.

14. The method of claim 11 , wherein the correcting comprises:

based on detecting the error in the voice signal, correcting at least one of a spacing or a punctuation mark of text data included in the input data; and

inputting corrected input data having the at least one of the spacing or the punctuation mark of the text data into the TTS module.

15. The method of claim 11 , wherein the correcting comprises:

based on detecting the error in the voice signal, correcting the input data by applying a speech synthesis markup language (SSML) to text data included in the input data; and

inputting corrected input data having the speech synthesis markup language (SSML) applied to the text data into the TTS module.

16. The method of claim 11 , wherein the acquiring input data comprises:

converting a received user voice into text data by using a voice recognition module;

analyzing an intent of the text data; and

acquiring response information corresponding to the received user voice as the input data.

17. The method of claim 11 , further comprising:

adding an indicator indicating correction to the voice signal; and

outputting the voice signal having the indicator through a speaker.

18. The method of claim 11 , further comprising:

outputting the voice signal through a speaker,

wherein the detecting the error comprises:

receiving the voice signal output through the speaker through a microphone; and

detecting the error in the voice signal received through the microphone based on the input data.

19. The electronic apparatus of claim 1 , wherein the input data comprises data related to emotions, and

the processor when executing the at least one instruction is further configured to

compare the data related to emotions included in the input data and the emotion, and

detect the error in the voice signal based on a result of comparing the data related to emotions included in the input data and the emotion.