Understanding how people speak when they interact with spoken dialogue systems is critical to improving the performance of those systems. This talk describes several experiments on data collected from subjects using TOOT, a system for accessing train information by phone, showing a) that user corrections of system errors differ from other user speech along several prosodic dimensions; and b) that prosodic information, together with other automatically available features, can be used to classify turns as corrections with a high degree of accuracy. From the Series:CSE Colloquia - 2001