| 摘要 |
PROBLEM TO BE SOLVED: To achieve smooth and highly responsive voice translation.SOLUTION: A voice translation device according to an embodiment includes an acquisition unit, a voice recognition unit, a translation unit, a retrieval unit, a selection unit and an example presentation unit. The acquisition unit acquires speech in a first language as a voice signal. The voice recognition unit performs voice recognition about the voice signal sequentially, and acquires a first language character string of the voice recognition result. The translation unit translates the first language character string into a second language different from the first language, and acquires a second language character string of the translation result. The retrieval unit retrieves a similar example which is an example in the first language that resembles the first language character string for each first language character string, and if a similar example is present, acquires the similar example and a parallel translation example which is the result in which the similar example is translated into the second language. The selection unit, according to a user instruction, selects at least either the first language character string in which the similar example is present, or the second language character string in which the parallel translation example is present as a selected character string. The example presentation unit presents one or more of similar examples and parallel translation examples regarding the selected character string. |
