A Dimensional Model of Interaction Style Variation in Spoken Dialog

Nigel Ward and Jonathan E. Avila

Speech Communication, 149, pp 47-62, 2023

http://www.cs.utep.edu/nigel/istyles/

Abstract   In spoken dialog people vary their interaction styles, and dialog systems should also be able to do the same. Previous work has elucidated many aspects of style variation and adaptation, but a general model has been lacking. We here describe a dimensional model of the space of interaction styles, derived by applying Principal Component Analysis to 33022 conversation fragments from the Switchboard corpus of American English telephone speech, represented by 84 novel features that encode the frequencies of diverse interaction-related prosodic behaviors. The top 8 dimensions were meaningfully interpretable, and include aspects previously noted in the literature but also new ones. Both this vector space representation and the method used to derive it may be useful for dialog systems design, tuning, and adaptation. Further, regarding individual differences in interaction style, we find that individual style tendencies were surprisingly weak, with a predictive model based on individual tendencies outperforming a speaker-independent model by only 3.6%.

Accepted Manuscript