Spoken Language Understanding Method Using Confidence Measure and Dialogue History

In the real environment, it is hard for a speech recog-nizer to avoid misrecognitions completely. However, if misrecognitions occur, user’s intentions are usually misun-derstood by a conventional language understanding tech-nique, which simply gives priority to the higher rank hypothesis of a speech recognition result (N-best). The utterances in a dialogue are coherent and correct user’s intentions might appear in the lower rank hypothesis of N-best. To understand user’s speech intentions in the real environment, we propose the language understanding tech-nique that utilizes the dialogue context and confidence measure, which is the word posterior probability. The ex-perimental results show that proposed technique is more efficient (about 15%) than the conventional technique