@inproceedings{lameris-etal-2024-role,
title = "The Role of Creaky Voice in Turn Taking and the Perception of Speaker Stance: Experiments Using Controllable {TTS}",
author = "Lameris, Harm and
Szekely, Eva and
Gustafson, Joakim",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1396/",
pages = "16058--16065",
abstract = "Recent advancements in spontaneous text-to-speech (TTS) have enabled the realistic synthesis of creaky voice, a voice quality known for its diverse pragmatic and paralinguistic functions. In this study, we used synthesized creaky voice in perceptual tests, to explore how listeners without formal training perceive two distinct types of creaky voice. We annotated a spontaneous speech corpus using creaky voice detection tools and modified a neural TTS engine with a creaky phonation embedding to control the presence of creaky phonation in the synthesized speech. We performed an objective analysis using a creak detection tool which revealed significant differences in creaky phonation levels between the two creaky voice types and modal voice. Two subjective listening experiments were performed to investigate the effect of creaky voice on perceived certainty, valence, sarcasm, and turn finality. Participants rated non-positional creak as less certain, less positive, and more indicative of turn finality, while positional creak was rated significantly more turn final compared to modal phonation."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lameris-etal-2024-role">
<titleInfo>
<title>The Role of Creaky Voice in Turn Taking and the Perception of Speaker Stance: Experiments Using Controllable TTS</title>
</titleInfo>
<name type="personal">
<namePart type="given">Harm</namePart>
<namePart type="family">Lameris</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eva</namePart>
<namePart type="family">Szekely</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joakim</namePart>
<namePart type="family">Gustafson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</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">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent advancements in spontaneous text-to-speech (TTS) have enabled the realistic synthesis of creaky voice, a voice quality known for its diverse pragmatic and paralinguistic functions. In this study, we used synthesized creaky voice in perceptual tests, to explore how listeners without formal training perceive two distinct types of creaky voice. We annotated a spontaneous speech corpus using creaky voice detection tools and modified a neural TTS engine with a creaky phonation embedding to control the presence of creaky phonation in the synthesized speech. We performed an objective analysis using a creak detection tool which revealed significant differences in creaky phonation levels between the two creaky voice types and modal voice. Two subjective listening experiments were performed to investigate the effect of creaky voice on perceived certainty, valence, sarcasm, and turn finality. Participants rated non-positional creak as less certain, less positive, and more indicative of turn finality, while positional creak was rated significantly more turn final compared to modal phonation.</abstract>
<identifier type="citekey">lameris-etal-2024-role</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1396/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>16058</start>
<end>16065</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Role of Creaky Voice in Turn Taking and the Perception of Speaker Stance: Experiments Using Controllable TTS
%A Lameris, Harm
%A Szekely, Eva
%A Gustafson, Joakim
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F lameris-etal-2024-role
%X Recent advancements in spontaneous text-to-speech (TTS) have enabled the realistic synthesis of creaky voice, a voice quality known for its diverse pragmatic and paralinguistic functions. In this study, we used synthesized creaky voice in perceptual tests, to explore how listeners without formal training perceive two distinct types of creaky voice. We annotated a spontaneous speech corpus using creaky voice detection tools and modified a neural TTS engine with a creaky phonation embedding to control the presence of creaky phonation in the synthesized speech. We performed an objective analysis using a creak detection tool which revealed significant differences in creaky phonation levels between the two creaky voice types and modal voice. Two subjective listening experiments were performed to investigate the effect of creaky voice on perceived certainty, valence, sarcasm, and turn finality. Participants rated non-positional creak as less certain, less positive, and more indicative of turn finality, while positional creak was rated significantly more turn final compared to modal phonation.
%U https://aclanthology.org/2024.lrec-main.1396/
%P 16058-16065
Markdown (Informal)
[The Role of Creaky Voice in Turn Taking and the Perception of Speaker Stance: Experiments Using Controllable TTS](https://aclanthology.org/2024.lrec-main.1396/) (Lameris et al., LREC-COLING 2024)
ACL