@inproceedings{hedstrom-etal-2022-samromur,
title = "Samr{\'o}mur: Crowd-sourcing large amounts of data",
author = {Hedstr{\"o}m, Staffan and
Mollberg, David Erik and
{\TH}{\'o}rhallsd{\'o}ttir, Ragnhei{\dh}ur 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-1.247/",
pages = "2311--2316",
abstract = "This contribution describes the collection of a large and diverse corpus for speech recognition and similar tools using crowd-sourced donations. We have built a collection platform inspired by Mozilla Common Voice and specialized it to our needs. We discuss the importance of engaging the community and motivating it to contribute, in our case through competitions. Given the incentive and a platform to easily read in large amounts of utterances, we have observed four cases of speakers freely donating over 10 thousand utterances. We have also seen that women are keener to participate in these events throughout all age groups. Manually verifying a large corpus is a monumental task and we attempt to automatically verify parts of the data using tools like Marosijo and the Montreal Forced Aligner. The method proved helpful, especially for detecting invalid utterances and halving the work needed from crowd-sourced verification."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hedstrom-etal-2022-samromur">
<titleInfo>
<title>Samrómur: Crowd-sourcing large amounts of data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Staffan</namePart>
<namePart type="family">Hedström</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">Ragnhei\dhur</namePart>
<namePart type="family">\THórhallsdóttir</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>This contribution describes the collection of a large and diverse corpus for speech recognition and similar tools using crowd-sourced donations. We have built a collection platform inspired by Mozilla Common Voice and specialized it to our needs. We discuss the importance of engaging the community and motivating it to contribute, in our case through competitions. Given the incentive and a platform to easily read in large amounts of utterances, we have observed four cases of speakers freely donating over 10 thousand utterances. We have also seen that women are keener to participate in these events throughout all age groups. Manually verifying a large corpus is a monumental task and we attempt to automatically verify parts of the data using tools like Marosijo and the Montreal Forced Aligner. The method proved helpful, especially for detecting invalid utterances and halving the work needed from crowd-sourced verification.</abstract>
<identifier type="citekey">hedstrom-etal-2022-samromur</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.247/</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>2311</start>
<end>2316</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Samrómur: Crowd-sourcing large amounts of data
%A Hedström, Staffan
%A Mollberg, David Erik
%A \THórhallsdóttir, Ragnhei\dhur
%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 hedstrom-etal-2022-samromur
%X This contribution describes the collection of a large and diverse corpus for speech recognition and similar tools using crowd-sourced donations. We have built a collection platform inspired by Mozilla Common Voice and specialized it to our needs. We discuss the importance of engaging the community and motivating it to contribute, in our case through competitions. Given the incentive and a platform to easily read in large amounts of utterances, we have observed four cases of speakers freely donating over 10 thousand utterances. We have also seen that women are keener to participate in these events throughout all age groups. Manually verifying a large corpus is a monumental task and we attempt to automatically verify parts of the data using tools like Marosijo and the Montreal Forced Aligner. The method proved helpful, especially for detecting invalid utterances and halving the work needed from crowd-sourced verification.
%U https://aclanthology.org/2022.lrec-1.247/
%P 2311-2316
Markdown (Informal)
[Samrómur: Crowd-sourcing large amounts of data](https://aclanthology.org/2022.lrec-1.247/) (Hedström et al., LREC 2022)
ACL
- Staffan Hedström, David Erik Mollberg, Ragnheiður Þórhallsdóttir, and Jón Guðnason. 2022. Samrómur: Crowd-sourcing large amounts of data. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 2311–2316, Marseille, France. European Language Resources Association.