@inproceedings{kim-etal-2026-mentaled,
title = "{M}enta{LED}: A Multimodal Conversational Agent for Mental Health Support Using Linguistic and Paralinguistic Speech Cues",
author = "Kim, Changhyun and
Kim, Dahye and
Seong, Eunseon and
Lee, Harim and
Lee, Sangyool and
Chae, Dong-Kyu",
editor = "Ghaleb, Esam and
Takmaz, Ece and
Frassinelli, Diego and
Khaertdinov, Bulat and
Fern{\'a}ndez, Raquel and
Yumak, Zerrin and
Ozyurek, Asli",
booktitle = "Proceedings of the 1st Workshop on Multimodal Interaction in Face-to-Face Dialogue",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.mint-1.15/",
pages = "144--149",
ISBN = "979-8-89176-482-8",
abstract = "Mental health, defined by psychological, emotional, and social well-being, has emerged as a significant social issue in modern society. To assess an individual{'}s mental state and provide personalized support, clinician{--}patient interviews are commonly conducted. However, given the constraints on access to such interviews, conversational agents have the potential to provide more accessible mental health support. In this paper, we present , a multimodal conversational agent that assesses an individual{'}s emotional and depressive states using an audio{--}text model that jointly models linguistic and paralinguistic cues from speech, and provides personalized mental health support through LLM-based response generation. Quantitative and qualitative evaluations indicate improvements in multimodal state assessment and response quality over the considered baselines."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2026-mentaled">
<titleInfo>
<title>MentaLED: A Multimodal Conversational Agent for Mental Health Support Using Linguistic and Paralinguistic Speech Cues</title>
</titleInfo>
<name type="personal">
<namePart type="given">Changhyun</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dahye</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eunseon</namePart>
<namePart type="family">Seong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harim</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sangyool</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dong-Kyu</namePart>
<namePart type="family">Chae</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Multimodal Interaction in Face-to-Face Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Esam</namePart>
<namePart type="family">Ghaleb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ece</namePart>
<namePart type="family">Takmaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diego</namePart>
<namePart type="family">Frassinelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bulat</namePart>
<namePart type="family">Khaertdinov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raquel</namePart>
<namePart type="family">Fernández</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zerrin</namePart>
<namePart type="family">Yumak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asli</namePart>
<namePart type="family">Ozyurek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-482-8</identifier>
</relatedItem>
<abstract>Mental health, defined by psychological, emotional, and social well-being, has emerged as a significant social issue in modern society. To assess an individual’s mental state and provide personalized support, clinician–patient interviews are commonly conducted. However, given the constraints on access to such interviews, conversational agents have the potential to provide more accessible mental health support. In this paper, we present , a multimodal conversational agent that assesses an individual’s emotional and depressive states using an audio–text model that jointly models linguistic and paralinguistic cues from speech, and provides personalized mental health support through LLM-based response generation. Quantitative and qualitative evaluations indicate improvements in multimodal state assessment and response quality over the considered baselines.</abstract>
<identifier type="citekey">kim-etal-2026-mentaled</identifier>
<location>
<url>https://aclanthology.org/2026.mint-1.15/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>144</start>
<end>149</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MentaLED: A Multimodal Conversational Agent for Mental Health Support Using Linguistic and Paralinguistic Speech Cues
%A Kim, Changhyun
%A Kim, Dahye
%A Seong, Eunseon
%A Lee, Harim
%A Lee, Sangyool
%A Chae, Dong-Kyu
%Y Ghaleb, Esam
%Y Takmaz, Ece
%Y Frassinelli, Diego
%Y Khaertdinov, Bulat
%Y Fernández, Raquel
%Y Yumak, Zerrin
%Y Ozyurek, Asli
%S Proceedings of the 1st Workshop on Multimodal Interaction in Face-to-Face Dialogue
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-482-8
%F kim-etal-2026-mentaled
%X Mental health, defined by psychological, emotional, and social well-being, has emerged as a significant social issue in modern society. To assess an individual’s mental state and provide personalized support, clinician–patient interviews are commonly conducted. However, given the constraints on access to such interviews, conversational agents have the potential to provide more accessible mental health support. In this paper, we present , a multimodal conversational agent that assesses an individual’s emotional and depressive states using an audio–text model that jointly models linguistic and paralinguistic cues from speech, and provides personalized mental health support through LLM-based response generation. Quantitative and qualitative evaluations indicate improvements in multimodal state assessment and response quality over the considered baselines.
%U https://aclanthology.org/2026.mint-1.15/
%P 144-149
Markdown (Informal)
[MentaLED: A Multimodal Conversational Agent for Mental Health Support Using Linguistic and Paralinguistic Speech Cues](https://aclanthology.org/2026.mint-1.15/) (Kim et al., MINT 2026)
ACL