Evaluating Spoken Dialogue Processing for Time-Offset Interaction (bibtex)
by Traum, David, Georgila, Kallirroi, Artstein, Ron and Leuski, Anton
Abstract:
This paper presents the first evaluation of a full automated prototype system for time-offset interaction, that is, conversation between a live person and recordings of someone who is not temporally co-present. Speech recognition reaches word error rates as low as 5% with general purpose language models and 19% with domain-specific models, and language understanding can identify appropriate direct responses to 60–66% of user utterances while keeping errors to 10–16% (the remainder being indirect, or off-topic responses). This is sufficient to enable a natural flow and relatively open-ended conversations, with a collection of under 2000 recorded statements.
Reference:
Evaluating Spoken Dialogue Processing for Time-Offset Interaction (Traum, David, Georgila, Kallirroi, Artstein, Ron and Leuski, Anton), In Proceedings of 16th Annual SIGdial Meeting on Discourse and Dialogue (SIGDIAL), Association for Computational Linguistics, 2015.
Bibtex Entry:
@inproceedings{traum_evaluating_2015,
	address = {Prague, Czech Republic},
	title = {Evaluating {Spoken} {Dialogue} {Processing} for {Time}-{Offset} {Interaction}},
	isbn = {978-1-941643-75-4},
	url = {http://ict.usc.edu/pubs/Evaluating%20Spoken%20Dialogue%20Processing%20for%20Time-Offset%20Interaction.pdf},
	abstract = {This paper presents the first evaluation of a full automated prototype system for time-offset interaction, that is, conversation between a live person and recordings of someone who is not temporally co-present. Speech recognition reaches word error rates as low as 5\% with general purpose language models and 19\% with domain-specific models, and language understanding can identify appropriate direct responses to 60–66\% of user utterances while keeping errors to 10–16\% (the remainder being indirect, or off-topic responses). This is sufficient to enable a natural flow and relatively open-ended conversations, with a collection of under 2000 recorded statements.},
	booktitle = {Proceedings of 16th {Annual} {SIGdial} {Meeting} on {Discourse} and {Dialogue} ({SIGDIAL})},
	publisher = {Association for Computational Linguistics},
	author = {Traum, David and Georgila, Kallirroi and Artstein, Ron and Leuski, Anton},
	month = sep,
	year = {2015},
	keywords = {Virtual Humans, UARC},
	pages = {199--208}
}
Powered by bibtexbrowser