Comparing Synthesized versus Pre-Recorded Tutor Speech in an Intelligent Tutoring Spoken Dialogue System

We evaluate the impact of tutor voice quality in the context of our intelligent tutoring spoken dialogue system. We rst describe two versions of our system which yielded two cor- pora of human-computer tutoring dialogues: one using a tutor voice pre-recorded by a human, and the other using a low- cost text-to-speech tutor voice. We then discuss the results of two-tailed t-tests comparing student learning gains, sys- tem usability, and dialogue efcienc y across the two corpora and across corpora subsets. Overall, our results suggest that tutor voice quality may have only a minor impact on these metrics in the context of our tutoring system. We nd that tutor voice quality does not impact learning gains, but it may impact usability and efcienc y for some corpora subsets.