Informatics Report Series
|
|
|
|
|
|
Title:Combining Acoustic and Pragmatic Features to Predict Recognition Performance in Spoken Dialogue Systems |
Authors:
Oliver Lemon
; Malte Gabsdil
|
Date: 2004 |
Publication Title:Proceedings of ACL 2004 (Meeting of the Association for Computational Linguistics) |
Publication Type:Conference Paper
Publication Status:Published
|
Page Nos:343-350
|
|
- Abstract:
-
We use machine learners trained on a combination of acoustic confidence and pragmatic plausibility features computed from dialogue context to predict the accuracy of incoming n-best recognition hypotheses to a spoken dialogue system. Our best results
show a 25% weighted f-score improvement over a baseline system that implements a ``grammar-switching'' approach to context-sensitive speech recognition.
- Copyright:
- ACL 2004
- Links To Paper
- 1st Link
- Bibtex format
- @InProceedings{EDI-INF-RR-0494,
- author = {
Oliver Lemon
and Malte Gabsdil
},
- title = {Combining Acoustic and Pragmatic Features to Predict Recognition Performance in Spoken Dialogue Systems},
- book title = {Proceedings of ACL 2004 (Meeting of the Association for Computational Linguistics)},
- year = 2004,
- pages = {343-350},
- url = {http://homepages.inf.ed.ac.uk/olemon},
- }
|