Electronic device and method for controlling the same, and storage medium

1. An electronic device, comprising:

a voice receiver; and

a processor configured to:

obtain a recognition character converted from a character section of a user voice input received through the voice receiver,

identify confusion probabilities of a plurality of candidate characters in association with the obtained recognition character, and similarities of the plurality of candidate characters for an acoustic feature of the character section, and

based on reflecting information about a weight assigned according to utterance type indicating whether the user voice input is continuously or discontinuously uttered to the identified confusion probabilities and the identified similarities, identify one of the plurality of candidate characters as an utterance character of the character section.

2. The electronic device of claim 1 , wherein the processor is configured to:

convert the user voice input received through the voice receiver into a character string, and

divide the character string into each character.

3. The electronic device of claim 2 , wherein the processor is configured to analyze whether a pause section exists between characters of the character string.

4. The electronic device of claim 3 , wherein the processor is configured to assign a lower weight to a confusion probability of the recognition character in which the pause section exists than when no pause section exists.

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

a memory,

wherein the processor is configured to store history information associated with an identification result of the candidate character in the memory.

6. The electronic device of claim 5 , wherein the processor is configured to identify the confusion probabilities of the plurality of candidate characters based on a confusion matrix.

7. The electronic device of claim 6 , wherein the processor is configured to update the confusion matrix based on the history information associated with the identification result of the candidate character.

8. The electronic device of claim 1 , wherein the processor is configured to identify the similarities of the plurality of candidate characters for the acoustic feature of the character section based on acoustic feature models of a plurality of pre-stored candidate characters.

9. The electronic device of claim 8 , wherein the processor is configured to update an acoustic feature model among the acoustic feature models based on history information associated with identification result of the candidate character.

10. The electronic device of claim 1 , wherein the processor is configured to obtain correction probabilities by applying the confusion probabilities which are identified based on a confusion matrix for the plurality of candidate characters and the similarities for the acoustic feature of the character section which are identified based on acoustic feature models for a plurality of pre-stored candidate characters.

11. A method for controlling an electronic device, comprising:

obtaining a recognition character converted from a character section of a user voice input received through a voice receiver;

identifying confusion probabilities of a plurality of candidate characters in association with the obtained recognition character, and similarities of the plurality of candidate characters for an acoustic feature of the character section; and

based on reflecting information about a weight assigned according to utterance type indicating whether the user voice input is continuously or discontinuously uttered to the identified confusion probabilities and the identified similarities, identifying one of the plurality of candidate as an utterance character of the character section.

12. The method of claim 11 , further comprising:

converting the user voice input received through the voice receiver into a character string; and

dividing the character string into each character.

13. The method of claim 12 , further comprising:

analyzing whether a pause section exists between the characters of the character string; and

assigning a lower weight to a confusion probability of a recognition character in which there exists the pause section than when no pause section exists.

14. The method of claim 11 , further comprising:

storing history information associated with an identification result of the candidate character.

15. The method of claim 14 , further comprising:

identifying the confusion probabilities based on a confusion matrix for the plurality of candidate characters.

16. The method of claim 15 , further comprising:

updating history information associated with the identification result of the candidate character.

17. The method of claim 11 , further comprising:

identifying the similarities of the plurality of candidate characters for the acoustic feature of the character section based on acoustic feature models of a plurality of pre-stored candidate characters.

18. The method of claim 11 , further comprising:

obtaining correction probabilities by applying the confusion probabilities which are identified based on a confusion matrix for the plurality of candidate characters and the similarities for the acoustic feature of the character section which are identified based on acoustic feature models for a plurality of pre-stored candidate characters.

19. A non-transitory computer-readable storage medium in which a computer program executable by a computer is stored, wherein the computer is configured to execute an operation of:

obtaining a recognition character converted from a character section of a user voice input received through a voice receiver,

identifying confusion probabilities of a plurality of candidate characters in association with the obtained recognition character, and similarities of the plurality of candidate characters for an acoustic feature of the character section, and

based on reflecting information a weight assigned according to utterance type indicating whether the user voice input is continuously or discontinuously uttered the identified confusion probabilities and the identified similarities, identifying one of the plurality of candidate as an utterance character of the character section.

20. The non-transitory computer-readable storage medium of claim 19 , wherein the computer executes an operation of:

converting the user voice input received through the voice receiver into a character string; and

dividing the character string into each character.