@inproceedings{mollberg-etal-2020-samromur,
title = "{S}amr{\'o}mur: Crowd-sourcing Data Collection for {I}celandic Speech Recognition",
author = "Mollberg, David Erik and
J{\'o}nsson, {\'O}lafur Helgi and
{\TH}orsteinsd{\'o}ttir, Sunneva and
Steingr{\'i}msson, Stein{\th}{\'o}r and
Magn{\'u}sd{\'o}ttir, Eyd{\'i}s Huld and
Gudnason, Jon",
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
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.425/",
pages = "3463--3467",
language = "eng",
ISBN = "979-10-95546-34-4",
abstract = "This contribution describes an ongoing project of speech data collection, using the web application Samr{\'o}mur which is built upon Common Voice, Mozilla Foundation`s web platform for open-source voice collection. The goal of the project is to build a large-scale speech corpus for Automatic Speech Recognition (ASR) for Icelandic. Upon completion, Samr{\'o}mur will be the largest open speech corpus for Icelandic collected from the public domain. We discuss the methods used for the crowd-sourcing effort and show the importance of marketing and good media coverage when launching a crowd-sourcing campaign. Preliminary results exceed our expectations, and in one month we collected data that we had estimated would take three months to obtain. Furthermore, our initial dataset of around 45 thousand utterances has good demographic coverage, is gender-balanced and with proper age distribution. We also report on the task of validating the recordings, which we have not promoted, but have had numerous hours invested by volunteers."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mollberg-etal-2020-samromur">
<titleInfo>
<title>Samrómur: Crowd-sourcing Data Collection for Icelandic Speech Recognition</title>
</titleInfo>
<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">Ólafur</namePart>
<namePart type="given">Helgi</namePart>
<namePart type="family">Jónsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunneva</namePart>
<namePart type="family">\THorsteinsdóttir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stein\thór</namePart>
<namePart type="family">Steingrímsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eydís</namePart>
<namePart type="given">Huld</namePart>
<namePart type="family">Magnúsdóttir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jon</namePart>
<namePart type="family">Gudnason</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth 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">Asuncion</namePart>
<namePart type="family">Moreno</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>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>This contribution describes an ongoing project of speech data collection, using the web application Samrómur which is built upon Common Voice, Mozilla Foundation‘s web platform for open-source voice collection. The goal of the project is to build a large-scale speech corpus for Automatic Speech Recognition (ASR) for Icelandic. Upon completion, Samrómur will be the largest open speech corpus for Icelandic collected from the public domain. We discuss the methods used for the crowd-sourcing effort and show the importance of marketing and good media coverage when launching a crowd-sourcing campaign. Preliminary results exceed our expectations, and in one month we collected data that we had estimated would take three months to obtain. Furthermore, our initial dataset of around 45 thousand utterances has good demographic coverage, is gender-balanced and with proper age distribution. We also report on the task of validating the recordings, which we have not promoted, but have had numerous hours invested by volunteers.</abstract>
<identifier type="citekey">mollberg-etal-2020-samromur</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.425/</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>3463</start>
<end>3467</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Samrómur: Crowd-sourcing Data Collection for Icelandic Speech Recognition
%A Mollberg, David Erik
%A Jónsson, Ólafur Helgi
%A \THorsteinsdóttir, Sunneva
%A Steingrímsson, Stein\thór
%A Magnúsdóttir, Eydís Huld
%A Gudnason, Jon
%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 Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G eng
%F mollberg-etal-2020-samromur
%X This contribution describes an ongoing project of speech data collection, using the web application Samrómur which is built upon Common Voice, Mozilla Foundation‘s web platform for open-source voice collection. The goal of the project is to build a large-scale speech corpus for Automatic Speech Recognition (ASR) for Icelandic. Upon completion, Samrómur will be the largest open speech corpus for Icelandic collected from the public domain. We discuss the methods used for the crowd-sourcing effort and show the importance of marketing and good media coverage when launching a crowd-sourcing campaign. Preliminary results exceed our expectations, and in one month we collected data that we had estimated would take three months to obtain. Furthermore, our initial dataset of around 45 thousand utterances has good demographic coverage, is gender-balanced and with proper age distribution. We also report on the task of validating the recordings, which we have not promoted, but have had numerous hours invested by volunteers.
%U https://aclanthology.org/2020.lrec-1.425/
%P 3463-3467
Markdown (Informal)
[Samrómur: Crowd-sourcing Data Collection for Icelandic Speech Recognition](https://aclanthology.org/2020.lrec-1.425/) (Mollberg et al., LREC 2020)
ACL
- David Erik Mollberg, Ólafur Helgi Jónsson, Sunneva Þorsteinsdóttir, Steinþór Steingrímsson, Eydís Huld Magnúsdóttir, and Jon Gudnason. 2020. Samrómur: Crowd-sourcing Data Collection for Icelandic Speech Recognition. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 3463–3467, Marseille, France. European Language Resources Association.