@inproceedings{chiba-higashinaka-2025-incorporating,
title = "Incorporating Dialogue State Tracking into {J}apanese Full-duplex Task-oriented Spoken Dialogue Model",
author = "Chiba, Yuya and
Higashinaka, Ryuichiro",
editor = "Inui, Kentaro and
Sakti, Sakriani and
Wang, Haofen and
Wong, Derek F. and
Bhattacharyya, Pushpak and
Banerjee, Biplab and
Ekbal, Asif and
Chakraborty, Tanmoy and
Singh, Dhirendra Pratap",
booktitle = "Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics",
month = dec,
year = "2025",
address = "Mumbai, India",
publisher = "The Asian Federation of Natural Language Processing and The Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-ijcnlp.49/",
pages = "829--836",
ISBN = "979-8-89176-303-6",
abstract = "Full-duplex spoken dialogue models, which process audio input and output simultaneously, have been actively studied for their ability to naturally model turn-taking and non-verbal phenomena in addition to generating responses. Although these models enable natural conversational flow, they lack mechanisms for language understanding and dialogue management, making them difficult to apply to task-oriented dialogue systems. We propose a method for incorporating dialogue state tracking in task-oriented dialogue into Moshi, aiming to achieve a multi-channel, full-duplex task-oriented spoken dialogue model. We evaluated the proposed method on JMultiWOZ, a benchmark corpus for Japanese task-oriented dialogue, focusing on dialogue state tracking and response generation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chiba-higashinaka-2025-incorporating">
<titleInfo>
<title>Incorporating Dialogue State Tracking into Japanese Full-duplex Task-oriented Spoken Dialogue Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuya</namePart>
<namePart type="family">Chiba</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryuichiro</namePart>
<namePart type="family">Higashinaka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haofen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derek</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Biplab</namePart>
<namePart type="family">Banerjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhirendra</namePart>
<namePart type="given">Pratap</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The Asian Federation of Natural Language Processing and The Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mumbai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-303-6</identifier>
</relatedItem>
<abstract>Full-duplex spoken dialogue models, which process audio input and output simultaneously, have been actively studied for their ability to naturally model turn-taking and non-verbal phenomena in addition to generating responses. Although these models enable natural conversational flow, they lack mechanisms for language understanding and dialogue management, making them difficult to apply to task-oriented dialogue systems. We propose a method for incorporating dialogue state tracking in task-oriented dialogue into Moshi, aiming to achieve a multi-channel, full-duplex task-oriented spoken dialogue model. We evaluated the proposed method on JMultiWOZ, a benchmark corpus for Japanese task-oriented dialogue, focusing on dialogue state tracking and response generation.</abstract>
<identifier type="citekey">chiba-higashinaka-2025-incorporating</identifier>
<location>
<url>https://aclanthology.org/2025.findings-ijcnlp.49/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>829</start>
<end>836</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Incorporating Dialogue State Tracking into Japanese Full-duplex Task-oriented Spoken Dialogue Model
%A Chiba, Yuya
%A Higashinaka, Ryuichiro
%Y Inui, Kentaro
%Y Sakti, Sakriani
%Y Wang, Haofen
%Y Wong, Derek F.
%Y Bhattacharyya, Pushpak
%Y Banerjee, Biplab
%Y Ekbal, Asif
%Y Chakraborty, Tanmoy
%Y Singh, Dhirendra Pratap
%S Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics
%D 2025
%8 December
%I The Asian Federation of Natural Language Processing and The Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-303-6
%F chiba-higashinaka-2025-incorporating
%X Full-duplex spoken dialogue models, which process audio input and output simultaneously, have been actively studied for their ability to naturally model turn-taking and non-verbal phenomena in addition to generating responses. Although these models enable natural conversational flow, they lack mechanisms for language understanding and dialogue management, making them difficult to apply to task-oriented dialogue systems. We propose a method for incorporating dialogue state tracking in task-oriented dialogue into Moshi, aiming to achieve a multi-channel, full-duplex task-oriented spoken dialogue model. We evaluated the proposed method on JMultiWOZ, a benchmark corpus for Japanese task-oriented dialogue, focusing on dialogue state tracking and response generation.
%U https://aclanthology.org/2025.findings-ijcnlp.49/
%P 829-836
Markdown (Informal)
[Incorporating Dialogue State Tracking into Japanese Full-duplex Task-oriented Spoken Dialogue Model](https://aclanthology.org/2025.findings-ijcnlp.49/) (Chiba & Higashinaka, Findings 2025)
ACL