Predicting spoken disfluencies during human-computer interaction

This research characterizes the spontaneous spoken dis uencies typical of human-computer interaction, and presents a predictive model accounting for their occurrence. Data were collected during three empirical studies in which people spoke or wrote to a highly interactive simulated system as they completed service transactions. The studies involved within-subject factorial designs in which the input modality and presentation format were varied. Spoken dis uency rates during human-computer interaction were documented to be substantially lower than rates typically observed during comparable human-human speech. Two separate factors, both associated with increased planning demands, were statistically related to higher dis uency rates: (1) length of utterance, and (2) lack of structure in the presentation format. Regression techniques demonstrated that a linear model based simply on utterance length accounted for over 77% of the variability in spoken dis uencies. Therefore, design methods capable of guiding users' speech into briefer sentences have the potential to eliminate the majority of spoken dis uencies. In this research, for example, a structured presentation format successfully eliminated 60-70% of all dis uent speech. The long-term goal of this research is to provide empirical guidance for the design of robust spoken language technology. Predicting Spoken Dis uencies 3