Oriel — AI & technology worth noticing, every day.

Multi modal perceived conversation success prediction for spontaneous autistic and non-autistic dyadic interactions

Paper · https://arxiv.org/abs/2610.31682

arXiv:2610.31682v1 Announce Type: new Abstract: Conversation success is important for communication, social bonds, and well-being and is often reduced in autistic-neurotypical conversations. Previous studies have predicted perceived conversation success using acoustic and lexical features in pediatric autism-enriched samples, or using nonverbal behavior in non-autistic group interactions. Other work has characterized prosodic, facial, motor, and turn-taking synchrony in autistic interactions, but has primarily targeted diagnostic classification or group differences. The present study instead predicts participant perceived conversation success from complementary articulatory, facial, acoustic-prosodic, and turn-taking measures across three spontaneous dyadic-interaction datasets including autistic and non autistic individuals. By leveraging multimodal features, we demonstrate that conversational success is inherently multidimensional and requires a multi-faceted analytical framework. Combining these complementary modalities offers the potential to improve prediction of perceived conversation success by capturing information unavailable from any single modality.

First seen by Oriel on .

AI summary

The study predicts perceived success in spontaneous autistic and non-autistic conversations, arguing that complementary modalities capture dimensions unavailable to any single feature type.

  • It analyzes three dyadic-interaction datasets involving autistic and non-autistic individuals.
  • Features cover articulatory behavior, facial cues, acoustic-prosodic patterns, and turn-taking.
  • The work focuses on participants’ perceived conversation success rather than diagnostic classification or group differences.
  • The abstract reports potential benefits from combining modalities but gives no quantitative performance results.

#autism #multimodal analysis #conversation modeling

Generated by gpt-5.6-sol. Check the original for details.

Aliases

SourceExternal IDURL
arXiv AI Papersoai:arXiv.org:2610.31682v1https://arxiv.org/abs/2610.31682 Read discussion