Electronic device for providing text and control method therefor

1. An electronic device configured to provide content comprising an image and a speech, the device, the electronic device comprising:

a display configured to display the image;

a memory storing a speech recognition module; and

a processor configured to:

obtain an expected word with a possibility of being included in the speech based on information on the content, perform speech recognition on the speech through the speech recognition module using the expected word, and display in the display a text converted from the speech based on the speech recognition,

perform, based on there being an error present in the text displayed on the display, speech recognition on the speech using a different expected word similar to the expected word which was the basis of converting the text with the error from among a plurality of expected words obtained based on information on the content.

2. The electronic device of claim 1 , wherein the processor is configured to: determine a type of the content, determine a content broadcast or published within a pre-set period based on a point at which the content is broadcast from among different contents of a same type as with the type of the content, and obtain a word associated with the determined content as the expected word.

3. The electronic device of claim 1 , wherein the processor is configured to: determine a type of the content, and obtain an expected word corresponding to the type of the content from a database in which an expected word for respective types of content is stored.

4. The electronic device of claim 1 , wherein the processor is configured to: perform a search on the content, and obtain a keyword extracted from the search result as the expected word.

5. The electronic device of claim 1 , wherein the processor is configured to: determine content expected to be viewed based on information on a viewing history or viewing reservation, obtain a word associated with the content expected to be viewed as the expected word, and perform, based on the content expected to be viewed being displayed in the display, speech recognition on a speech of the displayed content through the speech recognition module using the expected word.

6. The electronic device of claim 1 , wherein the processor is configured to: update, based on there being an error present in the text displayed in the display, the expected word based on a word a user uploaded to a server with respect to the content.

7. The electronic device of claim 1 , wherein the processor is configured to: obtain one or more sign language images corresponding to the text, and control the display to display the obtained sign language image.

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

a communicator comprising communication circuitry,

wherein the processor is configured to:

identify, based on information on a sign language broadcast being received from an external device through the communicator, content corresponding to the sign language broadcast based on the received information on the sign language broadcast;

control the display to display a list comprising the identified content; and

control, based on a content included in the list being selected, the display to display a composite image in which an image of the selected content and an image of a sign language broadcast corresponding to the selected content are combined.

9. A method of controlling an electronic device providing

content comprising an image and a speech, the method comprising:

displaying the image;

obtaining an expected word with a possibility of being included in the speech based on information on the content;

performing speech recognition on the speech through a pre-stored speech recognition module using the expected word; and

displaying a text converted from the speech based on the speech recognition,

wherein the method further comprises performing, based on there being an error present in the displayed text, speech recognition on the speech using a different expected word similar with the expected word which was the basis of converting the text with the error from among a plurality of expected words obtained based on information on the content.

10. The method of claim 9 , wherein the obtaining the expected word comprises: determining a type of the content, determining content broadcast or published within a pre-set period based on a point at which the content is broadcast from among different contents of a same type as with the type of the content, and obtaining a word associated with the determined content as the expected word.

11. The method of claim 9 , wherein the obtaining the expected word comprises: determining a type of the content, and obtaining an expected word corresponding to the type of the content from a database in which an expected word for respective types of content is stored.

12. The method of claim 9 , wherein the obtaining the expected word comprises: performing a search on the content, and obtaining a keyword extracted from the search result as the expected word.

13. The method of claim 9 , further comprising:

determining content expected to be viewed by a user based on information on a viewing history or a viewing reservation;

obtaining a word associated with the content expected to be viewed as the expected word; and

performing, based on the content expected to be viewed being displayed in a display of the electronic device, speech recognition on a speech of the displayed content through the speech recognition module using the expected word.