@inproceedings{jones-etal-2016-multi,
title = "Multi-language Speech Collection for {NIST} {LRE}",
author = "Jones, Karen and
Strassel, Stephanie and
Walker, Kevin and
Graff, David and
Wright, Jonathan",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1674",
pages = "4253--4258",
abstract = "The Multi-language Speech (MLS) Corpus supports NIST{'}s Language Recognition Evaluation series by providing new conversational telephone speech and broadcast narrowband data in 20 languages/dialects. The corpus was built with the intention of testing system performance in the matter of distinguishing closely related or confusable linguistic varieties, and careful manual auditing of collected data was an important aspect of this work. This paper lists the specific data requirements for the collection and provides both a commentary on the rationale for those requirements as well as an outline of the various steps taken to ensure all goals were met as specified. LDC conducted a large-scale recruitment effort involving the implementation of candidate assessment and interview techniques suitable for hiring a large contingent of telecommuting workers, and this recruitment effort is discussed in detail. We also describe the telephone and broadcast collection infrastructure and protocols, and provide details of the steps taken to pre-process collected data prior to auditing. Finally, annotation training, procedures and outcomes are presented in detail.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jones-etal-2016-multi">
<titleInfo>
<title>Multi-language Speech Collection for NIST LRE</title>
</titleInfo>
<name type="personal">
<namePart type="given">Karen</namePart>
<namePart type="family">Jones</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephanie</namePart>
<namePart type="family">Strassel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Walker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Graff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Wright</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</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">Khalid</namePart>
<namePart type="family">Choukri</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">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</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 (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The Multi-language Speech (MLS) Corpus supports NIST’s Language Recognition Evaluation series by providing new conversational telephone speech and broadcast narrowband data in 20 languages/dialects. The corpus was built with the intention of testing system performance in the matter of distinguishing closely related or confusable linguistic varieties, and careful manual auditing of collected data was an important aspect of this work. This paper lists the specific data requirements for the collection and provides both a commentary on the rationale for those requirements as well as an outline of the various steps taken to ensure all goals were met as specified. LDC conducted a large-scale recruitment effort involving the implementation of candidate assessment and interview techniques suitable for hiring a large contingent of telecommuting workers, and this recruitment effort is discussed in detail. We also describe the telephone and broadcast collection infrastructure and protocols, and provide details of the steps taken to pre-process collected data prior to auditing. Finally, annotation training, procedures and outcomes are presented in detail.</abstract>
<identifier type="citekey">jones-etal-2016-multi</identifier>
<location>
<url>https://aclanthology.org/L16-1674</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>4253</start>
<end>4258</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-language Speech Collection for NIST LRE
%A Jones, Karen
%A Strassel, Stephanie
%A Walker, Kevin
%A Graff, David
%A Wright, Jonathan
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F jones-etal-2016-multi
%X The Multi-language Speech (MLS) Corpus supports NIST’s Language Recognition Evaluation series by providing new conversational telephone speech and broadcast narrowband data in 20 languages/dialects. The corpus was built with the intention of testing system performance in the matter of distinguishing closely related or confusable linguistic varieties, and careful manual auditing of collected data was an important aspect of this work. This paper lists the specific data requirements for the collection and provides both a commentary on the rationale for those requirements as well as an outline of the various steps taken to ensure all goals were met as specified. LDC conducted a large-scale recruitment effort involving the implementation of candidate assessment and interview techniques suitable for hiring a large contingent of telecommuting workers, and this recruitment effort is discussed in detail. We also describe the telephone and broadcast collection infrastructure and protocols, and provide details of the steps taken to pre-process collected data prior to auditing. Finally, annotation training, procedures and outcomes are presented in detail.
%U https://aclanthology.org/L16-1674
%P 4253-4258
Markdown (Informal)
[Multi-language Speech Collection for NIST LRE](https://aclanthology.org/L16-1674) (Jones et al., LREC 2016)
ACL
- Karen Jones, Stephanie Strassel, Kevin Walker, David Graff, and Jonathan Wright. 2016. Multi-language Speech Collection for NIST LRE. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 4253–4258, Portorož, Slovenia. European Language Resources Association (ELRA).