Method and electronic device for translating speech signal

1. A method of translating a first speech signal in a first language of a speaker into a second speech signal in a second language of a listener, the method comprising:

receiving the first speech signal in the first language that is spoken by the speaker;

determining a translation level, which indicates a degree of summarization or omission of at least one word included in the first speech signal, to be applied to a translation of the first speech signal based on a level of understanding of the first language by the listener receiving translated results in the second language;

translating the first speech signal in the first language into the second speech signal in the second language according to the translation level, wherein the translating comprises:

in response to the translation level being a first translation level;

omitting a first number of words included in the first speech signal in the translation into the second language, and

outputting the second speech signal that omits the first number of words included in the first speech signal as the translation of the first speech signal in the first language into the second speech signal of the second language;

in response to the translation level being a second translation level different from the first translation level;

omitting a second number of words, which is different from the first number of words, included in the first speech signal in the translation into the second language, and

outputting the second speech signal that omits the second number of words included in the first speech signal as the translation of the first speech signal in the first language into the second speech signal of the second language; and

in response to omitting translation for at least one word included in the first speech signal, outputting a message indicating that the translation is skipped.

2. The method of claim 1 , wherein the determining the translation level comprises:

determining the translation level further based on at least one of age, gender, education, occupation, nationality, and language proficiency test score of the listener.

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

setting a plurality of translation levels distinguished according to degrees of summarization or omission from the translation; and

selecting the translation level from among the plurality of translation levels based on the level of understanding of the first language by the listener.

4. The method of claim 1 , wherein the determining the translation level comprises:

determining the translation level further based on at least one of a history of previous translations, personal information of the listener, information about an environment in which translation is performed, and information input by the listener in response to reception of the first speech signal.

5. The method of claim 1 , wherein the determining the translation level comprises:

determining the translation level further based on utterance characteristics of the speaker.

6. The method of claim 1 , wherein the determining the translation level comprises:

determining the translation level further based on a translation history related to the listener, and

wherein the method further comprises:

learning the translation history related to the listener; and

updating the translation level based on the translation history.

7. The method of claim 1 , wherein the outputting comprises transmitting the second speech signal in the second language to an external electronic device of the listener through a communication network.

8. An electronic device for translating a first speech signal in a first language of a speaker into a second speech signal in a second language of a listener, the electronic device comprising:

a receiver configured to receive the first speech signal in the first language that is spoken by the speaker; and

a processor configured to:

determine a translation level, which indicates a degree of summarization or omission of at least one word included in the first speech signal, to be applied to a translation of the first speech signal based on a level of understanding of the first language by the listener receiving translated results in the second language,

translate the first speech signal in the first language into the second speech signal according to the translation level such that:

in response to the translation level being a first translation level;

omit a first number of words included in the first speech signal in the translation into the second language; and

output the second speech signal that omits the first number of words included in the first speech signal as the translation of the first speech signal in the first language into the second speech signal of the second language;

in response to the translation level being a second translation level different from the first translation level;

omit a second number of words, which is different from the first number of words, included in the first speech signal in the translation into the second language; and

output the second speech signal that omits the second number of words included in the first speech signal as the translation of the first speech signal in the first language into the second speech signal of the second language, and

in response to omitting translation for at least one word included in the first speech signal, output a message indicating that the translation is skipped.

9. The electronic device of claim 8 , wherein the processor is further configured to determine the translation level based on at least one of age, gender, education, occupation, nationality, and language proficiency test score of the listener.

10. The electronic device of claim 8 , wherein the processor is further configured to set a plurality of translation levels distinguished according to degrees of summarization or omission from the translation and select the translation level from among the plurality of translation levels based on the level of understanding of the first language by the listener.

11. The electronic device of claim 8 , wherein the processor is further configured to determine the translation level further based on at least one of a history of previous translations, personal information of the listener, information about an environment in which translation is performed, and information input by the listener in response to reception of the first speech signal.

12. The electronic device of claim 8 , wherein the processor is further configured to determine the translation level further based on utterance characteristics of the speaker.

13. The electronic device of claim 8 , wherein the processor is further configured to determine the translation level further based on a translation history related to the listener, learn the translation history related to the listener, and update the translation level based on the translation history.

14. The electronic device of claim 8 , wherein the processor is further configured to generate a speech-synthesized translated result through speech synthesis on a translated result in the second language, and

wherein the electronic device further comprises at least one of a display for displaying a user interface screen including text data translated into the second language and an audio unit for outputting the speech-synthesized translated result.

15. The electronic device of claim 8 , further comprising a communicator configured to perform data transmission and reception between the electronic device and an external electronic device under the control of the processor,

wherein the communicator is further configured to transmit the second speech signal in the second language to the external electronic device.

16. A computer program product comprising a non-transitory computer-readable recording medium having recorded thereon a program comprising instructions executable by a computer, wherein the program comprises instructions which, when executed by the computer, cause the computer to perform a method of translating a first speech signal in a first language of a speaker into a second speech signal in a second language of a listener, the method comprising:

receiving the first speech signal in the first language that is spoken by the speaker;

determining a translation level, which indicates a degree of summarization or omission of at least one word included in the first speech signal, to be applied to a translation of the first speech signal based on a level of understanding of the first language by the listener receiving translated results in the second language;

translating the first speech signal in the first language into the second speech signal in the second language according to the translation level, wherein the translating comprises:

in response to the translation level being a first translation level:

omitting a first number of words included in the first speech signal in the translation into the second language; and

outputting the second speech signal that omits the first number of words included in the first speech signal as the translation of the first speech signal in the first language into the second speech signal of the second language;

in response to the translation level being a second translation level different from the first translation level:

omitting a second number of words, which is different from the first number of words, included in the first speech signal in the translation into the second language; and

outputting the second speech signal that omits the second number of words included in the first speech signal as the translation of the first speech signal in the first language into the second speech signal of the second language, and

in response to omitting translation for at least one word included in the first speech signal, outputting a message indicating that the translation is skipped.