A system for understanding time utterances spoken in German language is presented. Stochastic models contain the knowledge in the semantic, syntactic and acoustic-phonetic levels. An adequate semantic representation allows the integration of these models within a one-pass Viterbi search. The simultaneous use of all knowledge sources for the search procedure results in the smallest possible search space for the determination of the most probable semantic content accurately following the Bayes classification rule. Both the recognition accuracy and the computing speed facilitate a realistic application. Keywords: speech recognition, language understanding, spoken man-machine-dialogue, stochastic models, one-pass search, representation of syntactic and semantic knowledge
Bibliographic reference. Bauer, Josef G. / Stahl, Holger / Müller, Johannes (1995): "A one-pass search algorithm for understanding natural spoken time utterances by stochastic models", In EUROSPEECH-1995, 567-570.