Filtering errors and repairing linguistic anomalies for spoken dialogue systems

Abstract

Our work addresses the integration of speech recognition and language processing for whole spoken dialogue systems.To filter ill-recognized words, we design an on-line computing of word confidence scores based on the recognizer output hypothesis. To infer as much information as possible from the retained sequence of words, we propose a bottom-up syntacticosemantic robust parsing relying on a lexicalized tree grammar and on integrated repairing strategies.