| 摘要 |
<P>PROBLEM TO BE SOLVED: To realize smooth communication. <P>SOLUTION: A voice translation device comprises an input part, a voice recognition part, a feeling recognition part, a calm sentence generation part, a translation part, a supplementary sentence generation part, and a voice synthesis part. The input part converts voice of a first language into a voice signal. The voice recognition part performs a voice recognition process of the voice signal and generates a character string. The emotional identification part acquires emotional identification information including one or more emotion types by identifying what emotion type the character string has. If the character string includes a non calm phrase of the first language, the calm sentence generation part converts the non calm phrase of the first language into a corresponding calm phrase of the first language and generates a calm sentence using a model which associates non calm phrases changed with emotion with calm phrases corresponding to the non calm phrases not changed with emotion. The translation part generates a translation of the calm sentence translated into a second language. The supplementary sentence generation part generates a supplementary sentence illustrating the emotion types of the emotion identification information in the second language. The voice synthesis part converts the translation and the supplementary sentence into a voice signal. <P>COPYRIGHT: (C)2012,JPO&INPIT |
