Systems, method and program product for speech translation

1. A speech translation system comprising:

a first terminal device comprising a first speech input for inputting a first speech of a first language spoken by a first user, and converting the first speech to a first speech signal;

a second terminal device comprising a second speech input for inputting a second speech of a second language spoken by a second user, and converting the second speech to a second speech signal;

a speech recognition device that receives the first speech signal and the second speech signal, recognizes the first speech signal to a first recognized text, and recognizes the second speech signal to a second recognized text;

a machine translation device that receives the first recognized text and the second recognized text, translates the first recognized text to a first translated text of the second language, and translates the second recognized text to a second translated text of the first language;

a control device; wherein the first terminal device receives (a) a first text set of the first language being the first recognized text and the second translated text, and (b) a second text set of the second language being the second recognized text and the first translated text, and comprises a first display unit that displays the first text set and the second text set; and the second terminal device receives at least one text of the second text set, and comprises a second display unit that displays the at least one text of the second text set;

a third terminal device comprising a third speech input for inputting a third speech of a third language spoken by a third user, and converting the third speech to a third speech signal;

the speech recognition device receives the third speech signal, and recognizes the third speech signal to a third recognized text;

the machine translation device receives the third recognized text and the first recognized text, further comprises a third machine translation unit that translates the third recognized text to the third translated text of the first language, and translates the first recognized text to the fourth translated text of the third language;

the first display unit displays (a) at least one text set of the second text set and a third text set of the third language being the third recognized text and the fourth translated text, and (b) the fourth text set of the first language being the first text set and the third translated text; and

the third terminal device further comprises the third display unit that displays at least one text of the third text set.

2. The system according to claim 1 , wherein the machine translation device further comprises a reverse translation unit that reverse-translates the second translated text of the first language to a second reverse-translated text of the second language; the second display unit displaying at least one text of the second text set and the third text set of the second reverse-translated text of the second language.

3. The system according to claim 1 , wherein a first size of display area on the first display unit is larger than a second size of display area on the second display unit.

4. The system according to claim 1 , wherein the first terminal device further comprises a first display selection unit that receives a selection of text from the first text set and the second text set displayed on the first display unit; the control device comprises a first display control unit that controls displaying at least one text of the second text set on the second display unit, if the first display selection unit receives the selection.

5. The system according to claim 1 , wherein the second display unit displays at least one text of the first text set, the first terminal device further comprises the second display selection unit that receives a selection of whether the second text set is displayed on the first display unit; the control device furthermore comprises a display control unit that controls that the text of the first text set is not displayed on the second display unit, if the second display selection unit receives the selection that the second text set is displayed.

6. The system according to claim 1 , wherein the control device further comprises a first confirmation direction unit that displays a notification message of the second language, when the second text set is displayed on the second display unit.

7. The system according to claim 1 , wherein the control device further comprises a second confirmation direction unit that vibrates the second terminal device and/or output a confirmation sound, when the second text set is displayed on the second display unit.

8. The system according to claim 1 , wherein the speech recognition device outputs the recognized text and a recognition likelihood representing confidence of the speech recognition process; the control device further comprises a second recognition display decision unit that decide whether the second recognition text is displayed on the second display unit, based on the recognition likelihood.

9. The system according to claim 1 , wherein the control unit further comprises the second reverse translation display decision unit decide whether the second display unit is displayed, based on a degree of coincidence between the second recognized text and the second reverse-translated text.

10. The system according to claim 1 , wherein the control unit further comprises a first display decision unit configured to decides whether the second text set is displayed on the first display unit, based on the distance between the first terminal device and the second terminal device.

11. The system according to claim 1 , wherein the control unit further comprises a first display decision unit that decides whether the second text set is displayed on the first display unit, based on a readability of the second user being able to read the first display unit.

12. The system according to claim 1 , wherein the second terminal device is portable.

13. A computer program product comprising a non-transitory computer readable medium comprising programmed instructions for performing a speech translation processing, comprising:

a first terminal device comprising a first speech input for inputting a first speech of a first language spoken by a first user, and converting the first speech to a first speech signal;

a second terminal device comprising a second speech input for inputting a second speech of a second language spoken by a second user, and converting the second speech to a second speech signal;

a speech recognition device that receives the first speech signal and the second speech signal, recognizes the first speech signal to a first recognized text, and recognizes the second speech signal to a second recognized text;

a machine translation device that receives the first recognized text and the second recognized text, translates the first recognized text to a first translated text of the second language, and translates the second recognized text to a second translated text of the first language;

a control device; wherein the first terminal device receives (a) a first text set of the first language being the first recognized text and the second translated text, and (b) a second text set of the second language being the second recognized text and the first translated text, and comprises a first display unit that displays the first text set and the second text set; the second terminal device receives at least one text of the second text set, and comprises a second display unit that displays the at least one text of the second text set;

a third terminal device comprising a third speech input for inputting a third speech of a third language spoken by a third user, and converting the third speech to a third speech signal;

the speech recognition device receives the third speech signal, and recognizes the third speech signal to a third recognized text;

the machine translation device receives the third recognized text and the first recognized text, further comprises a third machine translation unit that translates the third recognized text to the third translated text of the first language, and translates the first recognized text to the fourth translated text of the third language;

the first display unit displays (a) at least one text set of the second text set and a third text set of the third language being the third recognized text and the fourth translated text, and (b) the fourth text set of the first language being the first text set and the third translated text; and

the third terminal device further comprises the third display unit that displays at least one text of the third text set.

14. A speech translation method comprising:

inputting a first speech of a first language spoken by a first user, and converting the first speech to a first speech signal;

inputting a second speech of a second language spoken by a second user, and converting the second speech to a second speech signal;

receiving the first speech signal and the second speech signal, recognizing the first speech signal to a first recognized text, and recognizing the second speech signal to a second recognized text;

receiving the first recognized text and the second recognized text, translating the first recognized text to a first translated text of the second language, and translating the second recognized text to a second translated text of the first language;

receiving (a) a first text set of the first, language being the first recognized text and the second translated text, and (b) a second text set of the second language being the second recognized text and the first translated text, and displaying the first text set and the second text set;

receiving at least one text of the second text set, and displaying the at least one text of the second text set;

inputting a third speech of a third language spoken by a third user, and converting the third speech to a third speech signal;

receiving the third speech signal, and recognizing the third speech signal to a third recognized text;

the receiving the third recognized text and the first recognized text, further comprises translating the third recognized text to the third translated text of the first language, and translating the first recognized text to the fourth translated text of the third language;

displaying (a) at least one text set of the second text set and a third text set of the third language being the third recognized text and the fourth translated text, and (b) the fourth text set of the first language being the first text set and the third translated text; and

displaying at least one text of the third text set.