| 摘要 |
<p>A translating apparatus includes a speech recognition unit, a machine translation unit, a speech synthesizing unit, and a dialog management unit. The speech recognition unit recognizes input speech, and supplies the result of the speech recognition to the machine translation unit. The machine translation unit translates the result of the speech recognition. When a Japanese-speaking user and an English-speaking user speak to each other, the dialog management unit stores a history of dialogs, and determines based on the dialog history and prestored knowledge whether the result of the translation by the machine translation unit is unnatural compared with the flow of the dialog. When the result of the translation is unnatural, the dialog management unit outputs, to the machine translation unit, information representing the unnatural result. This controls the machine translation unit to perform translation again. <IMAGE></p> |
