In this article we address the task of automatic text structuring into linear and non-overlapping thematic episodes. Our investigation reports on the use of various lexical, acoustic and syntactic features, and makes a comparison of how these features influence performance of automatic topic segmentation. Using datasets containing multi-party meeting transcriptions, we base our experiments on a proven state-of-the-art approach using support vector classification.

In this paper we present a proposal for extending the standard Wizard of Oz experimental methodology to language-enabled multimodal systems. We first discuss how Wizard of Oz experiments involving multimodal systems differ from those involving voice-only systems. We then go on to discuss the Extended Wizard of Oz methodology and the Wizard of Oz testing environment and protocol that we have developed. We then describe an example of applying this methodology to Archivus, a multimodal system for multimedia meeting retrieval and browsing. We focus in particular on the tools that the wizards would need to successfully and efficiently perform their tasks in a multimodal context. We conclude with some general comments about which questions need to be addressed when developing and using the Wizard of Oz methodology for testing multimodal systems.