@inproceedings{kohn-etal-2016-mining,
title = "Mining the Spoken {W}ikipedia for Speech Data and Beyond",
author = {K{\"o}hn, Arne and
Stegen, Florian and
Baumann, Timo},
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/L16-1735",
pages = "4644--4647",
abstract = "We present a corpus of time-aligned spoken data of Wikipedia articles as well as the pipeline that allows to generate such corpora for many languages. There are initiatives to create and sustain spoken Wikipedia versions in many languages and hence the data is freely available, grows over time, and can be used for automatic corpus creation. Our pipeline automatically downloads and aligns this data. The resulting German corpus currently totals 293h of audio, of which we align 71h in full sentences and another 86h of sentences with some missing words. The English corpus consists of 287h, for which we align 27h in full sentence and 157h with some missing words. Results are publically available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kohn-etal-2016-mining">
<titleInfo>
<title>Mining the Spoken Wikipedia for Speech Data and Beyond</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arne</namePart>
<namePart type="family">Köhn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Florian</namePart>
<namePart type="family">Stegen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Timo</namePart>
<namePart type="family">Baumann</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>We present a corpus of time-aligned spoken data of Wikipedia articles as well as the pipeline that allows to generate such corpora for many languages. There are initiatives to create and sustain spoken Wikipedia versions in many languages and hence the data is freely available, grows over time, and can be used for automatic corpus creation. Our pipeline automatically downloads and aligns this data. The resulting German corpus currently totals 293h of audio, of which we align 71h in full sentences and another 86h of sentences with some missing words. The English corpus consists of 287h, for which we align 27h in full sentence and 157h with some missing words. Results are publically available.</abstract>
<identifier type="citekey">kohn-etal-2016-mining</identifier>
<location>
<url>https://aclanthology.org/L16-1735</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>4644</start>
<end>4647</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mining the Spoken Wikipedia for Speech Data and Beyond
%A Köhn, Arne
%A Stegen, Florian
%A Baumann, Timo
%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 kohn-etal-2016-mining
%X We present a corpus of time-aligned spoken data of Wikipedia articles as well as the pipeline that allows to generate such corpora for many languages. There are initiatives to create and sustain spoken Wikipedia versions in many languages and hence the data is freely available, grows over time, and can be used for automatic corpus creation. Our pipeline automatically downloads and aligns this data. The resulting German corpus currently totals 293h of audio, of which we align 71h in full sentences and another 86h of sentences with some missing words. The English corpus consists of 287h, for which we align 27h in full sentence and 157h with some missing words. Results are publically available.
%U https://aclanthology.org/L16-1735
%P 4644-4647
Markdown (Informal)
[Mining the Spoken Wikipedia for Speech Data and Beyond](https://aclanthology.org/L16-1735) (Köhn et al., LREC 2016)
ACL
- Arne Köhn, Florian Stegen, and Timo Baumann. 2016. Mining the Spoken Wikipedia for Speech Data and Beyond. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 4644–4647, Portorož, Slovenia. European Language Resources Association (ELRA).