Modeling speech disfluency to predict conceptual misalignment in speech survey interfaces
Modeling speech disfluency to predict conceptual misalignment in speech survey interfaces
复制标题
DOI：
10.1080/01638530701600839
复制
发表时间：
2007-01-01
影响因子：
2.2
通讯作者：
Conrad, Frederick G.
中科院分区：
文献类型：
--
作者：
Ehlen, Patrick;Schober, Michael F.;Conrad, Frederick G.
基于计算机的访谈系统可以使用受访者的不流利行为模型来预测调查问题中术语澄清的必要性。本研究比较了模拟语音接口，使用两个这样的模型-一个通用的模型和一个刻板的模型，区分年轻人和老年人的讲话-几个非建模语音接口的任务，受访者提供的答案调查问题从虚构的场景。建模过程中发现，概念错位的最佳预测是一个关键的金发范围的响应延迟，即响应时间，既不太慢，也不太快，其中以外的响应更有可能是概念错位。不同的金发女孩范围是有效的年轻和老年人的发言者。
Computer-based interviewing systems could use models of respondent disfluency behaviors to predict a need for clarification of terms in survey questions. This study compares simulated speech interfaces that use two such models-a generic model and a stereotyped model that distinguishes between the speech of younger and older speakers-to several non-modeling speech interfaces in a task where respondents provided answers to survey questions from fictional scenarios. The modeling procedure found that the best predictor of conceptual misalignment was a critical Goldilocks range for response latency-that is, a response time that is neither too slow nor too fast-outside of which responses are more likely to be conceptually misaligned. Different Goldilocks ranges are effective for younger and older speakers.