Automated extraction of speech and turn-taking parameters in autism allows for diagnostic classification using a multivariable prediction model.

Autism spectrum disorder (ASD) is diagnosed on the basis of speech and communication differences, amongst other symptoms. Since conversations are essential for building connections with others, it is important to understand the exact nature of differences between autistic and non-autistic verbal behaviour and evaluate the potential of these differences for diagnostics. In this study, we recorded dyadic conversations and used automated extraction of speech and interactional turn-taking features of 54 non-autistic and 26 autistic participants. The extracted speech and turn-taking parameters showed high potential as a diagnostic marker. A linear support vector machine was able to predict the dyad type with 76.2% balanced accuracy (sensitivity: 73.8%, specificity: 78.6%), suggesting that digitally assisted diagnostics could significantly enhance the current clinical diagnostic process due to their objectivity and scalability. In group comparisons on the individual and dyadic level, we found that autistic interaction partners talked slower and in a more monotonous manner than non-autistic interaction partners and that mixed dyads consisting of an autistic and a non-autistic participant had increased periods of silence, and the intensity, i.e. loudness, of their speech was more synchronous.

The role of interpersonal synchrony in forming impressions of autistic and non-autistic adults.

When people meet, they almost instantaneously form an impression of each other. First impressions of character traits and rapport are less favourable when people with autism spectrum condition (ASC) are judged compared to non-autistic people. Little is known about the behavioural differences that drive these altered impressions. In the present study, we investigated the influence of interpersonal synchrony on impression formation of autistic and non-autistic people. Specifically, we used lagged cross-correlations to assess how much each interactant's motion energy, a measure which can be determined from video recordings, influenced the other interactant's motion energy. In short, silent clips of dyadic conversations, we asked non-autistic participants to rate their impression of one of the two interactants, which was solely based on the outlines of both interactants. We expected that the amount of leading of the target interactant, their diagnostic status as well as the interaction of these factors would influence impression formation. We found that while the amount of leading had a positive effect on the impressions of non-autistic interactants, this was not true for interactants with ASC. This suggests that interpersonal synchrony of motion energy is one driver of less favourable impressions of autistic compared to non-autistic people.