In this paper we present the application of a boosting classification algorithm to confidence scoring. We derive feature vectors from speech recognition lattices and feed them into a boosting classifier. This classifier combines hundreds of very simple `weak learners' and derives classification rules that can reduce the confidence error rate by up to 34%. We compare our results to those obtained using two other standard classification techniques, Support Vector Machines (SVMs) and Classification and Regression Trees (CART), and show significant improvements. Furthermore, the nature of the boosting algorithm allows us to combine the best single classifier and improve its performance.

Abstract not found

Browsing through large volumes of spoken audio is known to be a challenging task for end users. One way to alleviate this problem is to allow users to gist a spoken audio document by glancing over a transcript generated through Automatic Speech Recognition. Unfortunately, such transcripts typically contain many recognition errors which are highly distracting and make gisting more difficult. In this paper we present an approach that detects recognition errors by identifying words which are semantic outliers with respect to other words in the transcript. We describe several variants of this approach. We investigate a wide range of evaluation measures and we show that we can significantly reduce the number of errors in content words, with the trade-off of losing some good content words. 1

are those of the author and should not be interpreted as representing the official policies, either express or implied, of any sponsoring institution, the U.S. government, or any other entity. Keywords: spoken dialog systems, conversational spoken language interfaces, error detection, error recovery strategies, error recovery policies, dialog management, RavenClaw, implicitly-supervised One of the most important and persistent problems in the development of conversational spoken language interfaces is their lack of robustness when confronted with understanding-errors. Most of these errors stem from limitations in current speech recognition technology, and, as a result, appear across all domains and interaction types. There are two approaches towards increased robustness: prevent the errors from happening, or recover from them through conversation, by interacting with the users. In this dissertation we have engaged in a research program centered on the second approach. We argue that three capabilities are needed in order to seamlessly and efficiently recover from errors: (1) systems must be able to detect the errors, preferably as soon as they happen, (2) systems must be equipped with a rich repertoire of error recovery strategies that can be used to set the conversation back on track, and (3) systems must know how to choose optimally between different recovery

This paper addresses the issue of Out-Of-Vocabulary (OOV) word detection in Large Vocabulary Continuous Speech Recognition (LVCSR) systems. We propose a method inspired by confidence measures, that consists in analyzing the recognition system outputs in order to automatically detect errors due to OOV words. This method combines various features based on acoustic, linguistic, decoding graph and semantics. We evaluate separately each feature and we estimate their complementarity. Experiments are conducted on a large French broadcast news corpus from the ESTER evaluation campaign. Results show good performance in real conditions: the method obtains an OOV word detection rate of 43%-90 % with 2.5%-17.5 % of false detection. Index Terms: OOV word detection, confidence measures, speech recognition