摘要 |
<p>[Problem] To provide a speech processing system whereby the accuracy of speech recognition can be increased, and which is easy for a user to use. [Solution] When uttered speech is received, a speech processing system performs speech recognition and displays a text (158) of the recognition result. The speech processing system furthermore translates the recognition result into text (176) of another language in accordance with a setting and displays the translated result, and generates synthesized speech. The speech processing system furthermore selects an utterance candidate for which the probability of being uttered as the next utterance is high and for which a translation and speech recognition score is high using the output of various sensors at the time of utterance, an already learned utterance combination model, and a translation and speech recognition score for utterance candidates, and recommends utterance candidates as an utterance candidate recommendation list (192). A user can think of what to say next using the utterances in the utterance candidate recommendation list (192) as hints.</p> |