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 more 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 be improved considerably despite the large number of speech recognition errors.

• Type: Journal
• Year: 2000
• Where: IR
• Authors: Martin Wechsler, Eugen Munteanu, Peter Schäuble
• Keywords: Document Retrieval, IR 2000, Natural Language Processing, Retrieval Effectiveness, Spoken Document Retrieval