@inproceedings{tannander-etal-2024-revisiting,
title = "Revisiting Three Text-to-Speech Synthesis Experiments with a Web-Based Audience Response System",
author = "T{\r{a}}nnander, Christina and
Edlund, Jens 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.1230/",
pages = "14111--14121",
abstract = "In order to investigate the strengths and weaknesses of Audience Response System (ARS) in text-to-speech synthesis (TTS) evaluations, we revisit three previously published TTS studies and perform an ARS-based evaluation on the stimuli used in each study. The experiments are performed with a participant pool of 39 respondents, using a web-based tool that emulates an ARS experiment. The results of the first experiment confirms that ARS is highly useful for evaluating long and continuous stimuli, particularly if we wish for a diagnostic result rather than a single overall metric, while the second and third experiments highlight weaknesses in ARS with unsuitable materials as well as the importance of framing and instruction when conducting ARS-based evaluation."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tannander-etal-2024-revisiting">
<titleInfo>
<title>Revisiting Three Text-to-Speech Synthesis Experiments with a Web-Based Audience Response System</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christina</namePart>
<namePart type="family">Tånnander</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jens</namePart>
<namePart type="family">Edlund</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>In order to investigate the strengths and weaknesses of Audience Response System (ARS) in text-to-speech synthesis (TTS) evaluations, we revisit three previously published TTS studies and perform an ARS-based evaluation on the stimuli used in each study. The experiments are performed with a participant pool of 39 respondents, using a web-based tool that emulates an ARS experiment. The results of the first experiment confirms that ARS is highly useful for evaluating long and continuous stimuli, particularly if we wish for a diagnostic result rather than a single overall metric, while the second and third experiments highlight weaknesses in ARS with unsuitable materials as well as the importance of framing and instruction when conducting ARS-based evaluation.</abstract>
<identifier type="citekey">tannander-etal-2024-revisiting</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1230/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>14111</start>
<end>14121</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Revisiting Three Text-to-Speech Synthesis Experiments with a Web-Based Audience Response System
%A Tånnander, Christina
%A Edlund, Jens
%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 tannander-etal-2024-revisiting
%X In order to investigate the strengths and weaknesses of Audience Response System (ARS) in text-to-speech synthesis (TTS) evaluations, we revisit three previously published TTS studies and perform an ARS-based evaluation on the stimuli used in each study. The experiments are performed with a participant pool of 39 respondents, using a web-based tool that emulates an ARS experiment. The results of the first experiment confirms that ARS is highly useful for evaluating long and continuous stimuli, particularly if we wish for a diagnostic result rather than a single overall metric, while the second and third experiments highlight weaknesses in ARS with unsuitable materials as well as the importance of framing and instruction when conducting ARS-based evaluation.
%U https://aclanthology.org/2024.lrec-main.1230/
%P 14111-14121
Markdown (Informal)
[Revisiting Three Text-to-Speech Synthesis Experiments with a Web-Based Audience Response System](https://aclanthology.org/2024.lrec-main.1230/) (Tånnander et al., LREC-COLING 2024)
ACL