A model for robust processing of spontaneous speech by integrating viable fragments

Abstract

We describe the design and function of a robust processing component which is being developed for me Verbmobil speech translation system. Its task consists of collecting partial analyses of an input utterance produced by three parsers and attempting to combine them into more meaningful, larger units. It is used as a fallback mechanism in cases where no complete analysis spanning the whole input can be achieved, owing to spontaneous speech phenomena or speech recognition errors.