Computing confidence score of any input phrases for a spoken dialog system

One of the main challenges in the development of robust dialog systems is to deal with noisy input due to imperfect results from any speech recognition module. A key step in addressing this noisy input is the computation of confidence for the portions so that the subsequent dialog modules can make use of the confidence scores to design corresponding dialog strategies. While past work in computing confidence scores have been focusing on recognized words, semantic slots, or utterances, this paper is extending the investigation on computing confidence scores for all phrases of a sentence in a dialog system setting. We demonstrated that using a Conditional Maximum Entropy (CME) classifier in combination with features in acoustic, syntactic, and semantic categories, we are able to obtain a high performance for the dialog system application in a restaurant finding domain, specifically, an annotation error rate of 5.1% is reached, which is a very good result for practical user.