Now or When? Interruption timing prediction in dyadic interaction

Liu Yang; Catherine Achard; Catherine Pelachaud

doi:10.1145/3570945.3607293

Now or When? Interruption timing prediction in dyadic interaction

Liu Yang, Catherine Achard, Catherine Pelachaud

University Pierre and Marie Curie (Paris 6)

Research output: Chapter in Book or Report/Conference proceeding › Conference Proceeding › peer-review

1 Citation (Scopus)

Abstract

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).

Original language	English
Title of host publication	Proceedings of the 23rd ACM International Conference on Intelligent Virtual Agents, IVA 2023
Publisher	Association for Computing Machinery, Inc
ISBN (Electronic)	9781450399944
DOIs	https://doi.org/10.1145/3570945.3607293
Publication status	Published - 19 Sept 2023
Externally published	Yes
Event	23rd ACM International Conference on Intelligent Virtual Agents, IVA 2023 - Wurzburg, Germany Duration: 19 Sept 2023 → 22 Sept 2023

Publication series

Name	Proceedings of the 23rd ACM International Conference on Intelligent Virtual Agents, IVA 2023

Conference

Conference	23rd ACM International Conference on Intelligent Virtual Agents, IVA 2023
Country/Territory	Germany
City	Wurzburg
Period	19/09/23 → 22/09/23

Keywords

Interruption Prediction
multimodality
Nonverbal Behaviour
Socially Interactive Agent
Turn-Taking

Access to Document

10.1145/3570945.3607293

Cite this

Yang, L., Achard, C., & Pelachaud, C. (2023). Now or When? Interruption timing prediction in dyadic interaction. In Proceedings of the 23rd ACM International Conference on Intelligent Virtual Agents, IVA 2023 Article 44 (Proceedings of the 23rd ACM International Conference on Intelligent Virtual Agents, IVA 2023). Association for Computing Machinery, Inc. https://doi.org/10.1145/3570945.3607293

@inproceedings{151404ed61dd466bb1ba31c13844ce65,

title = "Now or When? Interruption timing prediction in dyadic interaction",

abstract = "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{\textquoteright}s accuracy, we conduct a perceptual study where we compare different timings (ground truth, randomly chosen or predicted by our model).",

keywords = "Interruption Prediction, multimodality, Nonverbal Behaviour, Socially Interactive Agent, Turn-Taking",

author = "Liu Yang and Catherine Achard and Catherine Pelachaud",

note = "Publisher Copyright: {\textcopyright} 2023 Copyright held by the owner/author(s).; 23rd ACM International Conference on Intelligent Virtual Agents, IVA 2023 ; Conference date: 19-09-2023 Through 22-09-2023",

year = "2023",

month = sep,

day = "19",

doi = "10.1145/3570945.3607293",

language = "English",

series = "Proceedings of the 23rd ACM International Conference on Intelligent Virtual Agents, IVA 2023",

publisher = "Association for Computing Machinery, Inc",

booktitle = "Proceedings of the 23rd ACM International Conference on Intelligent Virtual Agents, IVA 2023",

}

Yang, L, Achard, C & Pelachaud, C 2023, Now or When? Interruption timing prediction in dyadic interaction. in Proceedings of the 23rd ACM International Conference on Intelligent Virtual Agents, IVA 2023., 44, Proceedings of the 23rd ACM International Conference on Intelligent Virtual Agents, IVA 2023, Association for Computing Machinery, Inc, 23rd ACM International Conference on Intelligent Virtual Agents, IVA 2023, Wurzburg, Germany, 19/09/23. https://doi.org/10.1145/3570945.3607293

Now or When? Interruption timing prediction in dyadic interaction. / Yang, Liu; Achard, Catherine; Pelachaud, Catherine.
Proceedings of the 23rd ACM International Conference on Intelligent Virtual Agents, IVA 2023. Association for Computing Machinery, Inc, 2023. 44 (Proceedings of the 23rd ACM International Conference on Intelligent Virtual Agents, IVA 2023).

Research output: Chapter in Book or Report/Conference proceeding › Conference Proceeding › peer-review

TY - GEN

T1 - Now or When? Interruption timing prediction in dyadic interaction

AU - Yang, Liu

AU - Achard, Catherine

AU - Pelachaud, Catherine

PY - 2023/9/19

Y1 - 2023/9/19

N2 - 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).

AB - 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).

KW - Interruption Prediction

KW - multimodality

KW - Nonverbal Behaviour

KW - Socially Interactive Agent

KW - Turn-Taking

UR - http://www.scopus.com/inward/record.url?scp=85183580265&partnerID=8YFLogxK

U2 - 10.1145/3570945.3607293

DO - 10.1145/3570945.3607293

M3 - Conference Proceeding

AN - SCOPUS:85183580265

T3 - Proceedings of the 23rd ACM International Conference on Intelligent Virtual Agents, IVA 2023

BT - Proceedings of the 23rd ACM International Conference on Intelligent Virtual Agents, IVA 2023

PB - Association for Computing Machinery, Inc

T2 - 23rd ACM International Conference on Intelligent Virtual Agents, IVA 2023

Y2 - 19 September 2023 through 22 September 2023

ER -

Yang L, Achard C, Pelachaud C. Now or When? Interruption timing prediction in dyadic interaction. In Proceedings of the 23rd ACM International Conference on Intelligent Virtual Agents, IVA 2023. Association for Computing Machinery, Inc. 2023. 44. (Proceedings of the 23rd ACM International Conference on Intelligent Virtual Agents, IVA 2023). doi: 10.1145/3570945.3607293

Now or When? Interruption timing prediction in dyadic interaction

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this