Rapid Prototyping for Spoken Dialogue Systems

We implemented a spoken dialogue system ar-chitecture for rapid prototyping. The features that support rapid prototyping include a clear separation of generic dialogue processing al-gorithms from domain and language specic knowledge sources. In an experiment, it could be shown that six individuals could specify these domain and language specic knowledge sources within 8 to 12 hours to come up with a prototyp-ical implementation of a spoken dialogue sys-tem. To that end, no dialogue strategy had to be specied. Rather, it was suÆcient to provide an ontology, a description of the services oered by the system, parsing grammars, database con-version rules and generation templates. Fur-thermore, the experiment shows that it is possi-ble to formulate dialogue strategies in a domain and language independent manner; thus not re-quiring a system designer to be knowledgeable about dialogue processing.