Evaluation of Speech Dialog Strategies for Internet Applications in the Car

摘要

Due to the mobile Internet revolution, people tend to browse the Web while driving their car which puts the driver's safety at risk. Therefore, an intuitive and non-distractive in-car speech interface to the Web needs to be developed. Before developing a new speech dialog system in a new domain developers have to examine what the user's preferred interaction style is in order to use such a system. This paper reports from a very recent driving simulation study and its preliminary results which are conducted in order to compare different speech dialog strategies. The use of command-based and conversational SDS prototypes while driving is evaluated on usability and driving performance. Different GUIs are designed in order to support the respective dialog strategy the most and to evaluate the effect of the GUI on usability and driver distraction. The preliminary results show that the conversational speech dialog performs more efficient than the command-based dialog. However, the conversational dialog distracts more from driving than the command-based. Furthermore, the results indicate that an SDS supported by a GUI is more efficient and better accepted by the user than without GUI.