@inproceedings{olstad-etal-2024-collecting,
title = "Collecting Linguistic Resources for Assessing Children{'}s Pronunciation of {N}ordic Languages",
author = {Olstad, Anne Marte Haug and
Smolander, Anna and
Str{\"o}mbergsson, Sofia and
Ylinen, Sari and
Lehtonen, Minna and
Kurimo, Mikko and
Getman, Yaroslav and
Gr{\'o}sz, Tam{\'a}s and
Cao, Xinwei and
Svendsen, Torbj{\o}rn and
Salvi, Giampiero},
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.313",
pages = "3529--3537",
abstract = "This paper reports on the experience collecting a number of corpora of Nordic languages spoken by children. The aim of the data collection is providing annotated data to develop and evaluate computer assisted pronunciation assessment systems both for non-native children learning a Nordic language (L2) and for L1 children with speech sound disorder (SSD). The paper presents the challenges encountered recording and annotating data for Finnish, Swedish and Norwegian, as well as the ethical considerations related with making this data publicly available. We hope that sharing this experience will encourage others to collect similar data for other languages. Of the different data collections, we were able to make the Norwegian corpus publicly available in the hope that it will serve as a reference in pronunciation assessment research.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="olstad-etal-2024-collecting">
<titleInfo>
<title>Collecting Linguistic Resources for Assessing Children’s Pronunciation of Nordic Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anne</namePart>
<namePart type="given">Marte</namePart>
<namePart type="given">Haug</namePart>
<namePart type="family">Olstad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Smolander</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sofia</namePart>
<namePart type="family">Strömbergsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sari</namePart>
<namePart type="family">Ylinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minna</namePart>
<namePart type="family">Lehtonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikko</namePart>
<namePart type="family">Kurimo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaroslav</namePart>
<namePart type="family">Getman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tamás</namePart>
<namePart type="family">Grósz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinwei</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Torbjørn</namePart>
<namePart type="family">Svendsen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giampiero</namePart>
<namePart type="family">Salvi</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>This paper reports on the experience collecting a number of corpora of Nordic languages spoken by children. The aim of the data collection is providing annotated data to develop and evaluate computer assisted pronunciation assessment systems both for non-native children learning a Nordic language (L2) and for L1 children with speech sound disorder (SSD). The paper presents the challenges encountered recording and annotating data for Finnish, Swedish and Norwegian, as well as the ethical considerations related with making this data publicly available. We hope that sharing this experience will encourage others to collect similar data for other languages. Of the different data collections, we were able to make the Norwegian corpus publicly available in the hope that it will serve as a reference in pronunciation assessment research.</abstract>
<identifier type="citekey">olstad-etal-2024-collecting</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.313</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>3529</start>
<end>3537</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Collecting Linguistic Resources for Assessing Children’s Pronunciation of Nordic Languages
%A Olstad, Anne Marte Haug
%A Smolander, Anna
%A Strömbergsson, Sofia
%A Ylinen, Sari
%A Lehtonen, Minna
%A Kurimo, Mikko
%A Getman, Yaroslav
%A Grósz, Tamás
%A Cao, Xinwei
%A Svendsen, Torbjørn
%A Salvi, Giampiero
%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 olstad-etal-2024-collecting
%X This paper reports on the experience collecting a number of corpora of Nordic languages spoken by children. The aim of the data collection is providing annotated data to develop and evaluate computer assisted pronunciation assessment systems both for non-native children learning a Nordic language (L2) and for L1 children with speech sound disorder (SSD). The paper presents the challenges encountered recording and annotating data for Finnish, Swedish and Norwegian, as well as the ethical considerations related with making this data publicly available. We hope that sharing this experience will encourage others to collect similar data for other languages. Of the different data collections, we were able to make the Norwegian corpus publicly available in the hope that it will serve as a reference in pronunciation assessment research.
%U https://aclanthology.org/2024.lrec-main.313
%P 3529-3537
Markdown (Informal)
[Collecting Linguistic Resources for Assessing Children’s Pronunciation of Nordic Languages](https://aclanthology.org/2024.lrec-main.313) (Olstad et al., LREC-COLING 2024)
ACL
- Anne Marte Haug Olstad, Anna Smolander, Sofia Strömbergsson, Sari Ylinen, Minna Lehtonen, Mikko Kurimo, Yaroslav Getman, Tamás Grósz, Xinwei Cao, Torbjørn Svendsen, and Giampiero Salvi. 2024. Collecting Linguistic Resources for Assessing Children’s Pronunciation of Nordic Languages. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 3529–3537, Torino, Italia. ELRA and ICCL.