Downloads: 597

Files in This Item:
File Description SizeFormat 
TASL.2006.876727.pdf735.71 kBAdobe PDFView/Open
Title: Out-of-Domain Utterance Detection Using Classification Confidences of Multiple Topics
Authors: Lane, Ian
Kawahara, Tatsuya  kyouindb  KAKEN_id  orcid https://orcid.org/0000-0002-2686-2296 (unconfirmed)
Matsui, Tomoko
Nakamura, Satoshi
Author's alias: 河原, 達也
Issue Date: Jan-2007
Publisher: IEEE
Journal title: IEEE Transactions on Audio, Speech and Language Processing
Volume: 15
Issue: 1
Start page: 150
End page: 161
Abstract: One significant problem for spoken language systems is how to cope with users' out-of-domain (OOD) utterances which cannot be handled by the back-end application system. In this paper, we propose a novel OOD detection framework, which makes use of the classification confidence scores of multiple topics and applies a linear discriminant model to perform in-domain verification. The verification model is trained using a combination of deleted interpolation of the in-domain data and minimum-classification-error training, and does not require actual OOD data during the training process, thus realizing high portability. When applied to the "phrasebook" system, a single utterance read-style speech task, the proposed approach achieves an absolute reduction in OOD detection errors of up to 8.1 points (40% relative) compared to a baseline method based on the maximum topic classification score. Furthermore, the proposed approach realizes comparable performance to an equivalent system trained on both in-domain and OOD data, while requiring no OOD data during training. We also apply this framework to the "machine-aided-dialogue" corpus, a spontaneous dialogue speech task, and extend the framework in two manners. First, we introduce topic clustering which enables reliable topic confidence scores to be generated even for indistinct utterances, and second, we implement methods to effectively incorporate dialogue context. Integration of these two methods into the proposed framework significantly improves OOD detection performance, achieving a further reduction in equal error rate (EER) of 7.9 points.
Rights: © 2007 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.
URI: http://hdl.handle.net/2433/128902
DOI(Published Version): 10.1109/TASL.2006.876727
Appears in Collections:Journal Articles

Show full item record

Export to RefWorks


Export Format: 


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.