@inproceedings{obi-etal-2026-reproducing,
title = "Reproducing Proficiency-Conditioned Dialogue Features with Full-duplex Spoken Dialogue Models",
author = "Obi, Takao and
Yoshikawa, Sadahiro and
Saeki, Mao and
Eguchi, Masaki and
Matsuyama, Yoichi",
editor = "Riccardi, Giuseppe and
Mousavi, Seyed Mahed and
Torres, Maria Ines and
Yoshino, Koichiro and
Callejas, Zoraida and
Chowdhury, Shammur Absar and
Chen, Yun-Nung and
Bechet, Frederic and
Gustafson, Joakim and
Damnati, G{\'e}raldine and
Papangelis, Alex and
D{'}Haro, Luis Fernando and
Mendon{\c{c}}a, John and
Bernardi, Raffaella and
Hakkani-Tur, Dilek and
Di Fabbrizio, Giuseppe {''}Pino{''} and
Kawahara, Tatsuya and
Alam, Firoj and
Tur, Gokhan and
Johnston, Michael",
booktitle = "Proceedings of the 16th International Workshop on Spoken Dialogue System Technology",
month = feb,
year = "2026",
address = "Trento, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.iwsds-1.4/",
pages = "43--51",
abstract = "Real-time, human-centered conversational {AI} requires systems that handle spoken dialogue with overlap and rapid turn-taking. Although full-duplex models promise these capabilities, empirical work applying them to conversational {AI} is still nascent. To fill this gap, this study investigates whether the full-duplex model can reproduce the human dialogue features. We adapt a full-duplex spoken dialogue model to a large corpus of second-language ({L}2) learner interviews and train proficiency-conditioned models. We then conduct real-time interview sessions between these models and a spoken dialogue system designed to elicit spontaneous learner speech, and analyze reaction time, response frequency, and fluency metrics across aggregated {CEFR} levels (A/{B}/{C}). Our results show that proficiency-conditioned models partially reproduce levelwise trends and distributions observed in human interviews across multiple metrics. These findings suggest that full-duplex models can reproduce dialogue features of human dialogues and offer a promising foundation for conversational {AI} systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="obi-etal-2026-reproducing">
<titleInfo>
<title>Reproducing Proficiency-Conditioned Dialogue Features with Full-duplex Spoken Dialogue Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Takao</namePart>
<namePart type="family">Obi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadahiro</namePart>
<namePart type="family">Yoshikawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mao</namePart>
<namePart type="family">Saeki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masaki</namePart>
<namePart type="family">Eguchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoichi</namePart>
<namePart type="family">Matsuyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-02</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th International Workshop on Spoken Dialogue System Technology</title>
</titleInfo>
<name type="personal">
<namePart type="given">Giuseppe</namePart>
<namePart type="family">Riccardi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seyed</namePart>
<namePart type="given">Mahed</namePart>
<namePart type="family">Mousavi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Ines</namePart>
<namePart type="family">Torres</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koichiro</namePart>
<namePart type="family">Yoshino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zoraida</namePart>
<namePart type="family">Callejas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shammur</namePart>
<namePart type="given">Absar</namePart>
<namePart type="family">Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frederic</namePart>
<namePart type="family">Bechet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joakim</namePart>
<namePart type="family">Gustafson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Géraldine</namePart>
<namePart type="family">Damnati</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Papangelis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="given">Fernando</namePart>
<namePart type="family">D’Haro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Mendonça</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raffaella</namePart>
<namePart type="family">Bernardi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giuseppe</namePart>
<namePart type="given">”Pino”</namePart>
<namePart type="family">Di Fabbrizio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tatsuya</namePart>
<namePart type="family">Kawahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Firoj</namePart>
<namePart type="family">Alam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gokhan</namePart>
<namePart type="family">Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Johnston</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Trento, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Real-time, human-centered conversational AI requires systems that handle spoken dialogue with overlap and rapid turn-taking. Although full-duplex models promise these capabilities, empirical work applying them to conversational AI is still nascent. To fill this gap, this study investigates whether the full-duplex model can reproduce the human dialogue features. We adapt a full-duplex spoken dialogue model to a large corpus of second-language (L2) learner interviews and train proficiency-conditioned models. We then conduct real-time interview sessions between these models and a spoken dialogue system designed to elicit spontaneous learner speech, and analyze reaction time, response frequency, and fluency metrics across aggregated CEFR levels (A/B/C). Our results show that proficiency-conditioned models partially reproduce levelwise trends and distributions observed in human interviews across multiple metrics. These findings suggest that full-duplex models can reproduce dialogue features of human dialogues and offer a promising foundation for conversational AI systems.</abstract>
<identifier type="citekey">obi-etal-2026-reproducing</identifier>
<location>
<url>https://aclanthology.org/2026.iwsds-1.4/</url>
</location>
<part>
<date>2026-02</date>
<extent unit="page">
<start>43</start>
<end>51</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Reproducing Proficiency-Conditioned Dialogue Features with Full-duplex Spoken Dialogue Models
%A Obi, Takao
%A Yoshikawa, Sadahiro
%A Saeki, Mao
%A Eguchi, Masaki
%A Matsuyama, Yoichi
%Y Riccardi, Giuseppe
%Y Mousavi, Seyed Mahed
%Y Torres, Maria Ines
%Y Yoshino, Koichiro
%Y Callejas, Zoraida
%Y Chowdhury, Shammur Absar
%Y Chen, Yun-Nung
%Y Bechet, Frederic
%Y Gustafson, Joakim
%Y Damnati, Géraldine
%Y Papangelis, Alex
%Y D’Haro, Luis Fernando
%Y Mendonça, John
%Y Bernardi, Raffaella
%Y Hakkani-Tur, Dilek
%Y Di Fabbrizio, Giuseppe ”Pino”
%Y Kawahara, Tatsuya
%Y Alam, Firoj
%Y Tur, Gokhan
%Y Johnston, Michael
%S Proceedings of the 16th International Workshop on Spoken Dialogue System Technology
%D 2026
%8 February
%I Association for Computational Linguistics
%C Trento, Italy
%F obi-etal-2026-reproducing
%X Real-time, human-centered conversational AI requires systems that handle spoken dialogue with overlap and rapid turn-taking. Although full-duplex models promise these capabilities, empirical work applying them to conversational AI is still nascent. To fill this gap, this study investigates whether the full-duplex model can reproduce the human dialogue features. We adapt a full-duplex spoken dialogue model to a large corpus of second-language (L2) learner interviews and train proficiency-conditioned models. We then conduct real-time interview sessions between these models and a spoken dialogue system designed to elicit spontaneous learner speech, and analyze reaction time, response frequency, and fluency metrics across aggregated CEFR levels (A/B/C). Our results show that proficiency-conditioned models partially reproduce levelwise trends and distributions observed in human interviews across multiple metrics. These findings suggest that full-duplex models can reproduce dialogue features of human dialogues and offer a promising foundation for conversational AI systems.
%U https://aclanthology.org/2026.iwsds-1.4/
%P 43-51
Markdown (Informal)
[Reproducing Proficiency-Conditioned Dialogue Features with Full-duplex Spoken Dialogue Models](https://aclanthology.org/2026.iwsds-1.4/) (Obi et al., IWSDS 2026)
ACL