Modeling Speech Disfluency to Predict Conceptual Misalignment in Speech Survey Interfaces

Abstract

Computer-based interviewing systems could use models of respondent disfluency behaviors to predict a need for clarification of terms in survey questions. We compare 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. Our modeling procedure found that the best predictor of conceptual misalignment was a critical Goldilocks range for response latency, outside of which responses are more likely to be conceptually misaligned. Different Goldilocks ranges are effective for younger and older speakers.