@inproceedings{kim-etal-2025-egospeak,
title = "{E}go{S}peak: Learning When to Speak for Egocentric Conversational Agents in the Wild",
author = "Kim, Junhyeok and
Kim, Min Soo and
Chung, Jiwan and
Cho, Jungbin and
Kim, Jisoo and
Kim, Sungwoong and
Sim, Gyeongbo and
Yu, Youngjae",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-naacl.163/",
doi = "10.18653/v1/2025.findings-naacl.163",
pages = "2990--3005",
ISBN = "979-8-89176-195-7",
abstract = "Predicting when to initiate speech in real-world environments remains a fundamental challenge for conversational agents. We introduce , a novel framework for real-time speech initiation prediction in egocentric streaming video. By modeling the conversation from the speaker{'}s first-person viewpoint, is tailored for human-like interactions in which a conversational agent must continuously observe its environment and dynamically decide when to talk.Our approach bridges the gap between simplified experimental setups and complex natural conversations by integrating four key capabilities: (1) first-person perspective, (2) RGB processing, (3) online processing, and (4) untrimmed video processing. We also present YT-Conversation, a diverse collection of in-the-wild conversational videos from YouTube, as a resource for large-scale pretraining. Experiments on EasyCom and Ego4D demonstrate that outperforms random and silence-based baselines in real time. Our results also highlight the importance of multimodal input and context length in effectively deciding when to speak. Code and data are available at website."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2025-egospeak">
<titleInfo>
<title>EgoSpeak: Learning When to Speak for Egocentric Conversational Agents in the Wild</title>
</titleInfo>
<name type="personal">
<namePart type="given">Junhyeok</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min</namePart>
<namePart type="given">Soo</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiwan</namePart>
<namePart type="family">Chung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jungbin</namePart>
<namePart type="family">Cho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jisoo</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sungwoong</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gyeongbo</namePart>
<namePart type="family">Sim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Youngjae</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-195-7</identifier>
</relatedItem>
<abstract>Predicting when to initiate speech in real-world environments remains a fundamental challenge for conversational agents. We introduce , a novel framework for real-time speech initiation prediction in egocentric streaming video. By modeling the conversation from the speaker’s first-person viewpoint, is tailored for human-like interactions in which a conversational agent must continuously observe its environment and dynamically decide when to talk.Our approach bridges the gap between simplified experimental setups and complex natural conversations by integrating four key capabilities: (1) first-person perspective, (2) RGB processing, (3) online processing, and (4) untrimmed video processing. We also present YT-Conversation, a diverse collection of in-the-wild conversational videos from YouTube, as a resource for large-scale pretraining. Experiments on EasyCom and Ego4D demonstrate that outperforms random and silence-based baselines in real time. Our results also highlight the importance of multimodal input and context length in effectively deciding when to speak. Code and data are available at website.</abstract>
<identifier type="citekey">kim-etal-2025-egospeak</identifier>
<identifier type="doi">10.18653/v1/2025.findings-naacl.163</identifier>
<location>
<url>https://aclanthology.org/2025.findings-naacl.163/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>2990</start>
<end>3005</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EgoSpeak: Learning When to Speak for Egocentric Conversational Agents in the Wild
%A Kim, Junhyeok
%A Kim, Min Soo
%A Chung, Jiwan
%A Cho, Jungbin
%A Kim, Jisoo
%A Kim, Sungwoong
%A Sim, Gyeongbo
%A Yu, Youngjae
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Findings of the Association for Computational Linguistics: NAACL 2025
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-195-7
%F kim-etal-2025-egospeak
%X Predicting when to initiate speech in real-world environments remains a fundamental challenge for conversational agents. We introduce , a novel framework for real-time speech initiation prediction in egocentric streaming video. By modeling the conversation from the speaker’s first-person viewpoint, is tailored for human-like interactions in which a conversational agent must continuously observe its environment and dynamically decide when to talk.Our approach bridges the gap between simplified experimental setups and complex natural conversations by integrating four key capabilities: (1) first-person perspective, (2) RGB processing, (3) online processing, and (4) untrimmed video processing. We also present YT-Conversation, a diverse collection of in-the-wild conversational videos from YouTube, as a resource for large-scale pretraining. Experiments on EasyCom and Ego4D demonstrate that outperforms random and silence-based baselines in real time. Our results also highlight the importance of multimodal input and context length in effectively deciding when to speak. Code and data are available at website.
%R 10.18653/v1/2025.findings-naacl.163
%U https://aclanthology.org/2025.findings-naacl.163/
%U https://doi.org/10.18653/v1/2025.findings-naacl.163
%P 2990-3005
Markdown (Informal)
[EgoSpeak: Learning When to Speak for Egocentric Conversational Agents in the Wild](https://aclanthology.org/2025.findings-naacl.163/) (Kim et al., Findings 2025)
ACL
- Junhyeok Kim, Min Soo Kim, Jiwan Chung, Jungbin Cho, Jisoo Kim, Sungwoong Kim, Gyeongbo Sim, and Youngjae Yu. 2025. EgoSpeak: Learning When to Speak for Egocentric Conversational Agents in the Wild. In Findings of the Association for Computational Linguistics: NAACL 2025, pages 2990–3005, Albuquerque, New Mexico. Association for Computational Linguistics.