Device and method of simultaneous interpretation based on real-time extraction of interpretation unit

1. A device of simultaneous interpretation based on real-time extraction of an interpretation unit, the device comprising:

a voice recognition module configured to recognize voice units as sentence units or translation units from vocalized speech that is input in real time;

a real-time interpretation unit extraction module configured to form one or more of the voice units into an interpretation unit; and

a real-time interpretation module configured to perform an interpretation task for each interpretation unit formed by the real-time interpretation unit extraction module.

2. The device of claim 1 , wherein the real-time interpretation unit extraction module includes:

an input buffer manager configured to store a voice unit that is input and a remaining voice unit that is not yet included in sentences to be translated due to a previous interpretation unit extraction result;

a unit-separating morpheme analyzer configured to detect morphemes of each of the voice units;

a voice unit separator configured to re-separate the voice units according to a morpheme analysis result of the unit-separating morpheme analyzer; and

an interpretation unit former configured to form an interpretation unit by combining a current voice unit and a previous voice unit.

3. The device of claim 2 , wherein the voice unit separator re-separates a voice unit stored in the input buffer manager on the basis of a lexical characteristic, a morphological characteristic, an acoustic characteristic, and a time characteristic.

4. The device of claim 3 , wherein the lexical characteristic is a characteristic of determining whether a word that is able to be determined as a beginning of a sentence in a language is present.

5. The device of claim 3 , wherein the morphological characteristic is a characteristic of determining whether a predicate or a final ending is included after acquiring a morpheme analysis result related to the voice unit.

6. The device of claim 3 , wherein the acoustic characteristic is a characteristic related to pause information and prosody and stress information.

7. The device of claim 1 , wherein the real-time interpretation module performs translation by using both a module-based method based on modules for morpheme analysis, structure analysis, conversion, and transition word generation and a mechanical learning method using statistical machine translation (SMT), a deep neural network (DNN), and the like.

8. The device of claim 7 , further comprising a context management module configured to store all previous interpretation units and results of analyzing and generating morphemes/structures and translation results related to the interpretation units.

9. A method of simultaneous interpretation based on real-time extraction of an interpretation unit, the method comprising:

recognizing, by a voice recognition module, voice units as sentence units or translation units from vocalized speech that is input in real time;

forming, by a real-time interpretation unit extraction module, one or more of the voice units into an interpretation unit; and

performing, by a real-time interpretation module, an interpretation task for each interpretation unit formed by the real-time interpretation unit extraction module.

10. The method of claim 9 , wherein the forming of the interpretation unit with the voice units includes:

storing, by an input buffer manager, a voice unit that is input and a remaining voice unit that is not yet included in sentences to be translated due to a previous interpretation unit extraction result;

detecting, by a unit-separating morpheme analyzer, morphemes of each of the voice units;

re-separating, by a voice unit separator, the voice units according to a morpheme analysis result of the unit-separating morpheme analyzer; and

forming, by an interpretation unit former, an interpretation unit by combining a current voice unit and a previous voice unit.

11. The method of claim 10 , wherein the re-separating of the voice units includes re-separating a voice unit stored in the input buffer manager on the basis of a lexical characteristic, a morphological characteristic, an acoustic characteristic, and a time characteristic.

12. The method of claim 11 , wherein the lexical characteristic is a characteristic of determining whether a word that is able to be determined as a beginning of a sentence in a language is present.

13. The method of claim 11 , wherein the morphological characteristic is a characteristic of determining whether a predicate or a final ending is included after acquiring a morpheme analysis result related to the voice unit.

14. The method of claim 11 , wherein the acoustic characteristic is a characteristic related to pause information and prosody and stress information.

15. The method of claim 9 , wherein the performing of the interpretation task for each interpretation unit includes performing translation by using both a module-based method based on modules for morpheme analysis, structure analysis, conversion, and transition word generation and a mechanical learning method using SMT, a DNN, and the like.

16. The method of claim 15 , wherein the performing of the interpretation task for each interpretation unit includes storing all previous interpretation units and results of analyzing and generating morphemes/structures and translation results related to the interpretation units.