We want to enable users to locate desired information in spoken audio documents using not only the words, but also dialog activities. Following previous research, we infer this information from prosodic features, however, instead of retrieval by matching to a predefined finite set of activities, we estimate similarity using a vector space representation. Utterances close in this vector space are frequently similar not only pragmatically, but also topically. Using this we implemented a dialog-based query-by-example function and built it into an interface for use in combination with normal lexical search. Evaluating its utility by an experiment with four searchers doing twenty tasks each, we found that searchers used the new feature and considered it helpful, but only for some search tasks. 1. Two Views of Audio Search

Some things people say are more important, and some less so. The ability to automatically judge this, even approximately, would be a useful front end for many applications. This paper empirically examines importance as it varies from moment to moment in spoken dialog. Contextual prosodic features are informative, and importance is frequently associated with specific patterns of interaction that involve both participants and stretch over several seconds. A simple linear regression model gave importance estimates that correlated well, 0.83, with human judgments.