This study analyzes user corrections of system errors in the TOOT spoken dialogue system. We find that corrections differ from noncorrections prosodically, in ways consistent with hyperarticulated speech, although many corrections are not hyperarticulated. Yet both are misrecognized more frequently than non-corrections - though no more likely to be rejected by the system. Corrections more distant from the error they correct tend to exhibit greater prosodic differences, and also to be recognized more poorly. System dialogue strategy affects usersÂ’ choice of correction type, suggesting that strategy-specific methods of detecting or coaching users on corrections may be useful. Strategies that produce longer tasks but fewer misrecognitions and subsequent corrections are preferred by users.
Cite as: Swerts, M., Litman, D., Hirschberg, J. (2000) Corrections in spoken dialogue systems. Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000), vol. 2, 615-618, doi: 10.21437/ICSLP.2000-344
@inproceedings{swerts00b_icslp,
author={Marc Swerts and Diane Litman and Julia Hirschberg},
title={{Corrections in spoken dialogue systems}},
year=2000,
booktitle={Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000)},
pages={vol. 2, 615-618},
doi={10.21437/ICSLP.2000-344}
}