Abstract: An input relay unit receives speech data indicating a speech entered by a speaker. An input relay unit receives a confirmation request that is output in response to a predetermined operation of the speaker. A character string relay unit controls translation of the speech indicated by the speech data, which has been received before the reception of the confirmation request, to be started in response to the reception of the confirmation request. A display control unit controls a display unit to display a screen including an image obtained by overlaying a character string representing a translation result of a speech indicated by speech data that has been received before the reception of the confirmation request on an image captured by a capturing unit.

Abstract: A bidirectional speech translation system, a bidirectional speech translation, method and a program are provided for executing speech translation by using a combination of a speech recognition engine, a translation engine, and a speech synthesis engine that are suitable for received speech or a language of the received speech. The bidirectional speech translation system executes processing for synthesizing speech by translating first language speech entered by a first speaker into a second language and processing for synthesizing speech by translating second language speech entered by a second speaker into a first language.