@inproceedings{han-etal-2024-constructing,
title = "Constructing {K}orean Learners{'} {L}2 Speech Corpus of Seven Languages for Automatic Pronunciation Assessment",
author = "Han, Seunghee and
Kim, Sunhee and
Chung, Minhwa",
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.334",
pages = "3772--3781",
abstract = "Multilingual L2 speech corpora for developing automatic speech assessment are currently available, but they lack comprehensive annotations of L2 speech from non-native speakers of various languages. This study introduces the methodology of designing a Korean learners{'} L2 speech corpus of seven languages: English, Japanese, Chinese, French, German, Spanish, and Russian. We describe the development of reading scripts, reading tasks, scoring criteria, and expert evaluation methods in detail. Our corpus contains 1,200 hours of L2 speech data from Korean learners (400 hours for English, 200 hours each for Japanese and Chinese, 100 hours each for French, German, Spanish, and Russian). The corpus is annotated with spelling and pronunciation transcription, expert pronunciation assessment scores (accuracy of pronunciation and fluency of prosody), and metadata such as gender, age, self-reported language proficiency, and pronunciation error types. We also propose a practical verification method and a reliability threshold to ensure the reliability and objectivity of large-scale subjective evaluation data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="han-etal-2024-constructing">
<titleInfo>
<title>Constructing Korean Learners’ L2 Speech Corpus of Seven Languages for Automatic Pronunciation Assessment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Seunghee</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunhee</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minhwa</namePart>
<namePart type="family">Chung</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>Multilingual L2 speech corpora for developing automatic speech assessment are currently available, but they lack comprehensive annotations of L2 speech from non-native speakers of various languages. This study introduces the methodology of designing a Korean learners’ L2 speech corpus of seven languages: English, Japanese, Chinese, French, German, Spanish, and Russian. We describe the development of reading scripts, reading tasks, scoring criteria, and expert evaluation methods in detail. Our corpus contains 1,200 hours of L2 speech data from Korean learners (400 hours for English, 200 hours each for Japanese and Chinese, 100 hours each for French, German, Spanish, and Russian). The corpus is annotated with spelling and pronunciation transcription, expert pronunciation assessment scores (accuracy of pronunciation and fluency of prosody), and metadata such as gender, age, self-reported language proficiency, and pronunciation error types. We also propose a practical verification method and a reliability threshold to ensure the reliability and objectivity of large-scale subjective evaluation data.</abstract>
<identifier type="citekey">han-etal-2024-constructing</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.334</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>3772</start>
<end>3781</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Constructing Korean Learners’ L2 Speech Corpus of Seven Languages for Automatic Pronunciation Assessment
%A Han, Seunghee
%A Kim, Sunhee
%A Chung, Minhwa
%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 han-etal-2024-constructing
%X Multilingual L2 speech corpora for developing automatic speech assessment are currently available, but they lack comprehensive annotations of L2 speech from non-native speakers of various languages. This study introduces the methodology of designing a Korean learners’ L2 speech corpus of seven languages: English, Japanese, Chinese, French, German, Spanish, and Russian. We describe the development of reading scripts, reading tasks, scoring criteria, and expert evaluation methods in detail. Our corpus contains 1,200 hours of L2 speech data from Korean learners (400 hours for English, 200 hours each for Japanese and Chinese, 100 hours each for French, German, Spanish, and Russian). The corpus is annotated with spelling and pronunciation transcription, expert pronunciation assessment scores (accuracy of pronunciation and fluency of prosody), and metadata such as gender, age, self-reported language proficiency, and pronunciation error types. We also propose a practical verification method and a reliability threshold to ensure the reliability and objectivity of large-scale subjective evaluation data.
%U https://aclanthology.org/2024.lrec-main.334
%P 3772-3781
Markdown (Informal)
[Constructing Korean Learners’ L2 Speech Corpus of Seven Languages for Automatic Pronunciation Assessment](https://aclanthology.org/2024.lrec-main.334) (Han et al., LREC-COLING 2024)
ACL