Empirically evaluating an adaptable spoken dialogue system
UM '99 Proceedings of the seventh international conference on User modeling
The dual of denial: two uses of disconfirmations in dialogue and their prosodic correlates
Speech Communication - Dialogue and prosody
Predicting automatic speech recognition performance using prosodic cues
NAACL 2000 Proceedings of the 1st North American chapter of the Association for Computational Linguistics conference
Characterizing and recognizing spoken corrections in human-computer dialogue
COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 1
Predicting user reactions to system error
ACL '01 Proceedings of the 39th Annual Meeting on Association for Computational Linguistics
Identifying user corrections automatically in spoken dialogue systems
NAACL '01 Proceedings of the second meeting of the North American Chapter of the Association for Computational Linguistics on Language technologies
Learning trees and rules with set-valued features
AAAI'96 Proceedings of the thirteenth national conference on Artificial intelligence - Volume 1
Hi-index | 0.00 |
This paper deals with user corrections and aware sites of system errors in the TOOT spoken dialogue system. We first describe our corpus, and give details on our procedure to label corrections and aware sites. Then, we show that corrections and aware sites exhibit some prosodic and other properties which set them apart from 'normal' utterances. It appears that some correction types, such as simple repeats, are more likely to be correctly recognized than other types, such as paraphrases. We also present evidence that system dialogue strategy affects users' choice of correction type, suggesting that strategy-specific methods of detecting or coaching users on corrections may be useful. Aware sites tend to be shorter than other utterances, and are also more difficult to recognize correctly for the ASR system.