Towards Quality-Adaptive Spoken Dialogue Management

Stefan Ultes, Alexander Schmitt, Wolfgang Minker

Abstract: Information about the quality of a Spoken Dialogue System (SDS) is usually used only for comparing SDSs with each other or manually improving the dialogue strategy. This information, however, provides a means for inherently improving the dialogue performance by adapting the Dialogue Manager during the interaction accordingly. For a quality metric to be suitable, it must suffice certain conditions. Therefore, we address requirements for the quality metric and, additionally, present approaches for quality-adaptive dialogue management.