In order to create a useful, gracefully functioning system for travel arrangements, we have first observed the task as it is accomplished by a human. We then imitated the human while making the user believe he was dialoguing with an automatic system. As we gradually built our system, we devised ways to assess progress and to detect errors. The following described the manner in which the Carnegie Mellon Communicator was built, data collected, and assessment begun using these criteria.
Cite as: Eskenazi, M., Rudnicky, A.I., Gregory, K., Constantinides, P., Brennan, R., Bennett, C., Allen, J. (1999) Data collection and processing in the carnegie mellon communicator. Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999), 2695-2698, doi: 10.21437/Eurospeech.1999-494
@inproceedings{eskenazi99b_eurospeech,
author={Maxine Eskenazi and Alexander I. Rudnicky and Karin Gregory and Paul Constantinides and Robert Brennan and Christina Bennett and Jwan Allen},
title={{Data collection and processing in the carnegie mellon communicator}},
year=1999,
booktitle={Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999)},
pages={2695--2698},
doi={10.21437/Eurospeech.1999-494}
}