New approaches to spoken document retrieval

This paper presents four novel techniques for open-vocabulary spoken document retrieval: a method to detect slots that possibly contain a query Feature; a method to estimate occurrence probabilities: a technique that we call collection-wide probability re-estimation and a weighting scheme which takes advantage of the fact that long query features are detected mon reliably. These four techniques have been evaluated using the TREC-6 spoken document retrieval test collection to determine the improvements in retrieval effectiveness with respect to a baseline retrieval method. Results show that the retrieval effectiveness can he improved considerably despite the large number of speech recognition errors.