@inproceedings{hernandez-mena-etal-2022-samromur,
title = "Samr{\'o}mur Children: An {I}celandic Speech Corpus",
author = "Hernandez Mena, Carlos Daniel and
Mollberg, David Erik and
Borsk{\'y}, Michal and
Gu{\dh}nason, J{\'o}n",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.105/",
pages = "995--1002",
abstract = "Samr{\'o}mur Children is an Icelandic speech corpus intended for the field of automatic speech recognition. It contains 131 hours of read speech from Icelandic children aged between 4 to 17 years. The test portion was meticulously selected to cover a wide range of ages as possible; we aimed to have exactly the same amount of data per age range. The speech was collected with the crowd-sourcing platform Samr{\'o}mur.is, which is inspired on the {\textquotedblleft}Mozilla`s Common Voice Project{\textquotedblright}. The corpus was developed within the framework of the {\textquotedblleft}Language Technology Programme for Icelandic 2019 {\ensuremath{-}} 2023{\textquotedblright}; the goal of the project is to make Icelandic available in language-technology applications. Samr{\'o}mur Children is the first corpus in Icelandic with children`s voices for public use under a Creative Commons license. Additionally, we present baseline experiments and results using Kaldi."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hernandez-mena-etal-2022-samromur">
<titleInfo>
<title>Samrómur Children: An Icelandic Speech Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Carlos</namePart>
<namePart type="given">Daniel</namePart>
<namePart type="family">Hernandez Mena</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">Erik</namePart>
<namePart type="family">Mollberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michal</namePart>
<namePart type="family">Borský</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jón</namePart>
<namePart type="family">Gu\dhnason</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Samrómur Children is an Icelandic speech corpus intended for the field of automatic speech recognition. It contains 131 hours of read speech from Icelandic children aged between 4 to 17 years. The test portion was meticulously selected to cover a wide range of ages as possible; we aimed to have exactly the same amount of data per age range. The speech was collected with the crowd-sourcing platform Samrómur.is, which is inspired on the “Mozilla‘s Common Voice Project”. The corpus was developed within the framework of the “Language Technology Programme for Icelandic 2019 \ensuremath- 2023”; the goal of the project is to make Icelandic available in language-technology applications. Samrómur Children is the first corpus in Icelandic with children‘s voices for public use under a Creative Commons license. Additionally, we present baseline experiments and results using Kaldi.</abstract>
<identifier type="citekey">hernandez-mena-etal-2022-samromur</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.105/</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>995</start>
<end>1002</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Samrómur Children: An Icelandic Speech Corpus
%A Hernandez Mena, Carlos Daniel
%A Mollberg, David Erik
%A Borský, Michal
%A Gu\dhnason, Jón
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F hernandez-mena-etal-2022-samromur
%X Samrómur Children is an Icelandic speech corpus intended for the field of automatic speech recognition. It contains 131 hours of read speech from Icelandic children aged between 4 to 17 years. The test portion was meticulously selected to cover a wide range of ages as possible; we aimed to have exactly the same amount of data per age range. The speech was collected with the crowd-sourcing platform Samrómur.is, which is inspired on the “Mozilla‘s Common Voice Project”. The corpus was developed within the framework of the “Language Technology Programme for Icelandic 2019 \ensuremath- 2023”; the goal of the project is to make Icelandic available in language-technology applications. Samrómur Children is the first corpus in Icelandic with children‘s voices for public use under a Creative Commons license. Additionally, we present baseline experiments and results using Kaldi.
%U https://aclanthology.org/2022.lrec-1.105/
%P 995-1002
Markdown (Informal)
[Samrómur Children: An Icelandic Speech Corpus](https://aclanthology.org/2022.lrec-1.105/) (Hernandez Mena et al., LREC 2022)
ACL
- Carlos Daniel Hernandez Mena, David Erik Mollberg, Michal Borský, and Jón Guðnason. 2022. Samrómur Children: An Icelandic Speech Corpus. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 995–1002, Marseille, France. European Language Resources Association.