Acknowledgment Use with Synthesized and Recorded Prompts

Acknowledgments, e.g., “yeah” and “uh-huh,” are ubiquitous in human conversation but are rarer in human-computer interaction. What interface factors might contribute to this difference? Using a simple spoken-language interface that responded to acknowledgments, we compared subjects’ use of acknowledgments when the interface used recorded speech with that seen when the interface used synthesized speech. Contrary to our hypothesis, we saw a drop in the numbers of subjects using acknowledgments: subjects appeared to interpret the recorded-voice interface as signalling a more limited interface. These results were consistent for both Mexican Spanish and American English versions of the interface.