@inproceedings{yamamoto-komatani-2026-personality,
title = "Personality Expression in Spoken Dialogue Systems: From Text to Speech",
author = "Yamamoto, Kenta and
Komatani, Kazunori",
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-1.3/",
pages = "34--42",
abstract = "A consistent personality in a spoken dialogue system enhances the naturalness and friendliness of interactions. However, users may not accurately perceive all the personality traits that the system attempts to express. This study aims to identify which traits are most reliably perceived by users. We first analyzed third-party personality ratings of a dialogue corpus using principal component and factor analyses to uncover the underlying dimensions of user perception. We then conducted experiments under both text-only and speech-based dialogue conditions to evaluate how effectively each trait could be perceived. Crowd-sourced ratings showed that a trait concerning Extraversion and Openness can be reliably perceived through text alone, whereas accurate perception of the other traits requires speech-related features such as speech rate, backchannels, fillers, and turn-taking pause duration. These findings suggest that, rather than attempting to express all Big Five traits, focusing on a subset aligned with users' perceptual tendencies enables more effective and expressive personality design in spoken dialogue systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yamamoto-komatani-2026-personality">
<titleInfo>
<title>Personality Expression in Spoken Dialogue Systems: From Text to Speech</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kenta</namePart>
<namePart type="family">Yamamoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kazunori</namePart>
<namePart type="family">Komatani</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>A consistent personality in a spoken dialogue system enhances the naturalness and friendliness of interactions. However, users may not accurately perceive all the personality traits that the system attempts to express. This study aims to identify which traits are most reliably perceived by users. We first analyzed third-party personality ratings of a dialogue corpus using principal component and factor analyses to uncover the underlying dimensions of user perception. We then conducted experiments under both text-only and speech-based dialogue conditions to evaluate how effectively each trait could be perceived. Crowd-sourced ratings showed that a trait concerning Extraversion and Openness can be reliably perceived through text alone, whereas accurate perception of the other traits requires speech-related features such as speech rate, backchannels, fillers, and turn-taking pause duration. These findings suggest that, rather than attempting to express all Big Five traits, focusing on a subset aligned with users’ perceptual tendencies enables more effective and expressive personality design in spoken dialogue systems.</abstract>
<identifier type="citekey">yamamoto-komatani-2026-personality</identifier>
<location>
<url>https://aclanthology.org/2026.iwsds-1.3/</url>
</location>
<part>
<date>2026-02</date>
<extent unit="page">
<start>34</start>
<end>42</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Personality Expression in Spoken Dialogue Systems: From Text to Speech
%A Yamamoto, Kenta
%A Komatani, Kazunori
%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 yamamoto-komatani-2026-personality
%X A consistent personality in a spoken dialogue system enhances the naturalness and friendliness of interactions. However, users may not accurately perceive all the personality traits that the system attempts to express. This study aims to identify which traits are most reliably perceived by users. We first analyzed third-party personality ratings of a dialogue corpus using principal component and factor analyses to uncover the underlying dimensions of user perception. We then conducted experiments under both text-only and speech-based dialogue conditions to evaluate how effectively each trait could be perceived. Crowd-sourced ratings showed that a trait concerning Extraversion and Openness can be reliably perceived through text alone, whereas accurate perception of the other traits requires speech-related features such as speech rate, backchannels, fillers, and turn-taking pause duration. These findings suggest that, rather than attempting to express all Big Five traits, focusing on a subset aligned with users’ perceptual tendencies enables more effective and expressive personality design in spoken dialogue systems.
%U https://aclanthology.org/2026.iwsds-1.3/
%P 34-42
Markdown (Informal)
[Personality Expression in Spoken Dialogue Systems: From Text to Speech](https://aclanthology.org/2026.iwsds-1.3/) (Yamamoto & Komatani, IWSDS 2026)
ACL