Method and apparatus with real-time translation

1. A processor-implemented translation method comprising:

receiving, by a processor, a content;

determining, by the processor, a time-shift value for each of a plurality of languages;

storing, by the processor, the time-shift value for each of the plurality of languages on a table;

determining, by the processor, a time-shift of the received content based on a determined language used in the received content and the table;

determining, by the processor, a delay time for a real-time translation based on the time-shift of the received content and a silence interval in the received content;

generating, by the processor, a translation result through a trained automated translation model by translating a phrasing used in the received content based on the delay time;

synthesizing, by the processor, the generated translation result and the received content; and

providing a user with the synthesized result of the generated translation result and the received content in real-time,

wherein the generating of the translation result by the processor comprises adjusting an utterance length of the translation result to have a shorter length than a length of the delay time.

2. The method of claim 1 , further comprising:

storing an amount of the received content corresponding to the determined time-shift.

3. The method of claim 1 , wherein the determining of the delay time comprises:

determining the delay time based on the silence interval; and

determining the delay time based on an utterance interval.

4. The method of claim 3 , wherein the determining of the delay time based on the silence interval comprises:

extracting the silence interval from the received content; and

determining the delay time based on a time corresponding to the silence interval.

5. The method of claim 3 , wherein the determining of the delay time further comprises:

extracting an audio in the utterance interval from the received content; and

filtering an utterance from the extracted audio.

6. The method of claim 1 , wherein the generating of the translation result comprises:

generating at least one candidate translation result by translating the phrasing used in the received content;

comparing an utterance length of the generated candidate translation result to the delay time; and

replacing the generated candidate translation result with a second candidate translation result based on a result of the comparing of the utterance length of the generated candidate translation result to the delay time.

7. The method of claim 6 , wherein the generating of the translation result comprises:

comparing an utterance length of the second candidate translation result to the delay time; and

rephrasing the second candidate translation result based on a result of the comparing of the utterance length of the second candidate translation result to the delay time.

8. The method of claim 7 , wherein the generating of the translation result comprises:

comparing an utterance length of the rephrased second candidate translation result to the delay time; and

adjusting an utterance speed of the rephrased second candidate translation result based on a result of the comparing of the utterance length of the rephrased second candidate translation result to the delay time.

9. The method of claim 1 , wherein the generating of the translation result comprises:

generating the translation result by directly translating a speech included in the received content into speech in a target language; or generating the translation result by translating the speech included in the received content into a text in the target language.

10. The method of claim 1 , further comprising selecting a candidate translation result time from a plurality of candidate translation results, wherein the selected candidate translation result has an utterance length that is less than the delay time.

11. A translation apparatus comprising:

a receiver configured to receive a content; and

a processor configured to:

determine a time-shift value for each of a plurality of languages;

store the time-shift value for each of the plurality of languages on a table;

determine, a time-shift of the received content based on a determined language used in the received content and the table;

determine, a delay time for a real-time translation based on the time-shift of the received content and a silence interval in the received content;

generate a translation result through a trained automated translation model by translating a phrasing used in the received content based on the delay time;

synthesize the generated translation result and the received content; and

provide a user with a synthesized result of the generated translation result and the received content in real-time,

wherein the processor is further configured to adjust an utterance length of the translation result to have a shorter length than a length of the delay time.

12. The apparatus of claim 11 , wherein the processor is configured to:

store an amount of the received content corresponding to the determined time-shift.

13. The apparatus of claim 11 , wherein the processor is configured to:

determine the delay time based on the silence interval; and

determine the delay time based on an utterance interval.

14. The apparatus of claim 13 , wherein the processor is configured to:

extract the silence interval from the content; and

determine the delay time based on a time corresponding to the silence interval.

15. The apparatus of claim 13 , wherein the processor is configured to:

extract an audio in the utterance interval from the received content; and

filter an utterance from the extracted audio.

16. The apparatus of claim 11 , wherein the processor is configured to:

generate at least one candidate translation result by translating the phrasing used in the received content;

compare an utterance length of the generated candidate translation result to the delay time; and

replace the generated candidate translation result with a second candidate translation result based on a result of the comparing of the utterance length of the generated candidate translation result to the delay time.

17. The apparatus of claim 16 , wherein the processor is configured to:

compare an utterance length of the second candidate translation result to the delay time; and

rephrase the second candidate translation result based on a result of the comparing of the utterance length of the second candidate translation result to the delay time.

18. The apparatus of claim 17 , wherein the processor is configured to:

compare an utterance length of the rephrased second candidate translation result to the delay time; and

adjust an utterance speed of the rephrased second candidate translation result based on a result of the comparing of the utterance length of the rephrased second candidate translation result to the delay time.

19. The apparatus of claim 11 , wherein the processor is configured to:

generate the translation result by directly translating a speech included in the received content into a speech in a target language; or generate the translation result by translating the speech included in the received content into a text in the target language.

20. A processor-implemented method comprising:

determining, by a processor, a language in a received content;

determining, by the processor, a time-shift value for each of a plurality of languages;

storing, by the processor, the time-shift value for each of the plurality of languages on a table;

determining, by the processor, a time-shift of the received content based on a determined language used in the received content and the table;

determining, by the processor, a delay time based on the time-shift of the received content and an utterance interval in the received content;

extracting, by the processor, an audio utterance from the utterance interval;

generating a translation result through a trained automated translation model by translating speech included in the content, in the determined language, into speech in a target language based on the delay time; and

providing a user with the translation result in real-time,

wherein the generating the translation result by the processor comprises adjusting an utterance length of the translation result to have a shorter length than a length of the delay time.

21. The method of claim 20 , further comprising extracting a silence interval from the received content, and determining the delay time based on a time corresponding to the silence interval.

22. The method of claim 20 , further comprising synthesizing the translation result and the received content.