Now or When? Interruption timing prediction in dyadic interaction - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Now or When? Interruption timing prediction in dyadic interaction

Résumé

Interruptions are an important aspect of human-human communication. They help to adjust the conversation flow. Our aim is to equip virtual agents with the ability to handle interruptions, that is to decide when and how to interrupt their human interlocutor. In this paper, we focus on predicting when interruptions may occur during the conversation using multimodal features only from the speaker and propose a model trained on a corpus of dyadic interactions. To assess the model's accuracy, we conduct a perceptual study where we compare different timings (ground truth, randomly chosen or predicted by our model). CCS CONCEPTS • Human-centered computing → Human agent interaction (HAI).
Fichier principal
Vignette du fichier
IVA_23_EA.pdf (623.82 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04293352 , version 1 (18-11-2023)

Identifiants

Citer

Liu Yang, Catherine Achard, Catherine Pelachaud. Now or When? Interruption timing prediction in dyadic interaction. ACM International Conference on Intelligent Virtual Agents, Sep 2023, Wursburg, Germany. ⟨10.1145/3570945.3607293⟩. ⟨hal-04293352⟩
14 Consultations
29 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More