Out-of-Domain Utterance Detection Using Classification Confidences of Multiple Topics-猫眼课题宝

DOI：

10.1109/tasl.2006.876727

发表时间：

2007-01

期刊：

IEEE Transactions on Audio, Speech, and Language Processing

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Ian Lane;Tatsuya Kawahara;T. Matsui;Satoshi Nakamura

口语系统的一个重要问题是如何科普后端应用系统无法处理的用户的域外（OOD）话语。在本文中，我们提出了一种新的OOD检测框架，它利用多个主题的分类置信度得分，并应用线性判别模型进行域内验证。验证模型采用域内数据删除插值和最小分类误差训练相结合的方法进行训练，训练过程中不需要实际的OOD数据，可移植性强。当应用到“短语”系统，一个单一的话语阅读风格的语音任务，所提出的方法实现了绝对减少OOD检测错误高达8.1点（40%相对）相比，基线方法的基础上的最大主题分类得分。此外，所提出的方法实现了与在域内和OOD数据上训练的等效系统相当的性能，同时在训练期间不需要OOD数据。我们也将此框架应用于“机器辅助对话”语料库，一个自发的对话语音任务，并在两种方式扩展的框架。首先，我们引入了主题聚类，使可靠的主题置信度分数生成，即使是不明确的话语，第二，我们实现的方法，有效地将对话上下文。将这两种方法集成到所提出的框架中显著提高了OOD检测性能，实现了7.9个点的等错误率（EER）的进一步降低

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

Out-of-Domain Utterance Detection Using Classification Confidences of Multiple Topics

文献摘要

被引文献

相似文献