Predicting and Managing Spoken Disfluencies During Human-Computer Interaction

This research characterizes the spontaneous spoken disfluencies 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. The studies involved within-subject factorial designs in which input modality and presentation format were varied. Spoken disfluency 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 increased speech disfluency rates: (1) length of utterance, and (2) lack of structure in the presentation format. Regression techniques revealed that a linear model based simply on utterance length accounts for over 77% of the variability in spoken disfluencies. Therefore, design techniques capable of channeling users' speech into briefer sentences potentially could eliminate most spoken disfluencies. In addition, the degree of structure in the presentation format was manipulated in a manner that successfully elimluated 60 to 70% of all disfluent speech. The long-term goal of this research is to provide empirical guidance for the design of robust spoken language technology.