@inproceedings{wevelsiep-etal-2025-voice,
title = "A Voice-Controlled Dialogue System for {NPC} Interaction using Large Language Models",
author = "Wevelsiep, Milan and
Walker, Nicholas Thomas and
Wagner, Nicolas and
Ultes, Stefan",
editor = "Torres, Maria Ines and
Matsuda, Yuki and
Callejas, Zoraida and
del Pozo, Arantza and
D'Haro, Luis Fernando",
booktitle = "Proceedings of the 15th International Workshop on Spoken Dialogue Systems Technology",
month = may,
year = "2025",
address = "Bilbao, Spain",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.iwsds-1.4/",
pages = "29--38",
ISBN = "979-8-89176-248-0",
abstract = "This paper explores the integration of voice-controlled dialogue systems in narrative-driven video games, addressing the limitations of existing approaches. We propose a hybrid interface that allows players to freely paraphrase predefined dialogue options, combining player expressiveness with narrative cohesion. The prototype was developed in Unity, and a large language model was used to map the transcribed voice input to existing dialogue options. The approach was evaluated in a user study (n=14) that compared the hybrid interface to traditional point-and-click methods. Results indicate the proposed interface enhances player{'}s degree of joy and perceived freedom while maintaining narrative consistency. The findings provide insights into the design of scalable and engaging voice-controlled systems for interactive storytelling. Future research should focus on reducing latency and refining language model accuracy to further improve user experience and immersion."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wevelsiep-etal-2025-voice">
<titleInfo>
<title>A Voice-Controlled Dialogue System for NPC Interaction using Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Milan</namePart>
<namePart type="family">Wevelsiep</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicholas</namePart>
<namePart type="given">Thomas</namePart>
<namePart type="family">Walker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicolas</namePart>
<namePart type="family">Wagner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Ultes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Workshop on Spoken Dialogue Systems Technology</title>
</titleInfo>
<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">Yuki</namePart>
<namePart type="family">Matsuda</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">Arantza</namePart>
<namePart type="family">del Pozo</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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bilbao, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-248-0</identifier>
</relatedItem>
<abstract>This paper explores the integration of voice-controlled dialogue systems in narrative-driven video games, addressing the limitations of existing approaches. We propose a hybrid interface that allows players to freely paraphrase predefined dialogue options, combining player expressiveness with narrative cohesion. The prototype was developed in Unity, and a large language model was used to map the transcribed voice input to existing dialogue options. The approach was evaluated in a user study (n=14) that compared the hybrid interface to traditional point-and-click methods. Results indicate the proposed interface enhances player’s degree of joy and perceived freedom while maintaining narrative consistency. The findings provide insights into the design of scalable and engaging voice-controlled systems for interactive storytelling. Future research should focus on reducing latency and refining language model accuracy to further improve user experience and immersion.</abstract>
<identifier type="citekey">wevelsiep-etal-2025-voice</identifier>
<location>
<url>https://aclanthology.org/2025.iwsds-1.4/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>29</start>
<end>38</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Voice-Controlled Dialogue System for NPC Interaction using Large Language Models
%A Wevelsiep, Milan
%A Walker, Nicholas Thomas
%A Wagner, Nicolas
%A Ultes, Stefan
%Y Torres, Maria Ines
%Y Matsuda, Yuki
%Y Callejas, Zoraida
%Y del Pozo, Arantza
%Y D’Haro, Luis Fernando
%S Proceedings of the 15th International Workshop on Spoken Dialogue Systems Technology
%D 2025
%8 May
%I Association for Computational Linguistics
%C Bilbao, Spain
%@ 979-8-89176-248-0
%F wevelsiep-etal-2025-voice
%X This paper explores the integration of voice-controlled dialogue systems in narrative-driven video games, addressing the limitations of existing approaches. We propose a hybrid interface that allows players to freely paraphrase predefined dialogue options, combining player expressiveness with narrative cohesion. The prototype was developed in Unity, and a large language model was used to map the transcribed voice input to existing dialogue options. The approach was evaluated in a user study (n=14) that compared the hybrid interface to traditional point-and-click methods. Results indicate the proposed interface enhances player’s degree of joy and perceived freedom while maintaining narrative consistency. The findings provide insights into the design of scalable and engaging voice-controlled systems for interactive storytelling. Future research should focus on reducing latency and refining language model accuracy to further improve user experience and immersion.
%U https://aclanthology.org/2025.iwsds-1.4/
%P 29-38
Markdown (Informal)
[A Voice-Controlled Dialogue System for NPC Interaction using Large Language Models](https://aclanthology.org/2025.iwsds-1.4/) (Wevelsiep et al., IWSDS 2025)
ACL