@inproceedings{henrichsen-uneson-2012-smallworlds,
title = "{SMALLW}orlds {--} Multilingual Content-Controlled Monologues",
author = "Henrichsen, Peter Juel and
Uneson, Marcus",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/357_Paper.pdf",
pages = "3362--3368",
abstract = "We present the speech corpus SMALLWorlds (Spoken Multi-lingual Accounts of Logically Limited Worlds), newly established and still growing. SMALLWorlds contains monologic descriptions of scenes or worlds which are simple enough to be formally describable. The descriptions are instances of content-controlled monologue: semantically ''''''``pre-specified'''''''' but still bearing most hallmarks of spontaneous speech (hesitations and filled pauses, relaxed syntax, repetitions, self-corrections, incomplete constituents, irrelevant or redundant information, etc.) as well as idiosyncratic speaker traits. In the paper, we discuss the pros and cons of data so elicited. Following that, we present a typical SMALLWorlds task: the description of a simple drawing with differently coloured circles, squares, and triangles, with no hints given as to which description strategy or language style to use. We conclude with an example on how SMALLWorlds may be used: unsupervised lexical learning from phonetic transcription. At the time of writing, SMALLWorlds consists of more than 250 recordings in a wide range of typologically diverse languages from many parts of the world, some unwritten and endangered.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="henrichsen-uneson-2012-smallworlds">
<titleInfo>
<title>SMALLWorlds – Multilingual Content-Controlled Monologues</title>
</titleInfo>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="given">Juel</namePart>
<namePart type="family">Henrichsen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcus</namePart>
<namePart type="family">Uneson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present the speech corpus SMALLWorlds (Spoken Multi-lingual Accounts of Logically Limited Worlds), newly established and still growing. SMALLWorlds contains monologic descriptions of scenes or worlds which are simple enough to be formally describable. The descriptions are instances of content-controlled monologue: semantically ”””“pre-specified”””” but still bearing most hallmarks of spontaneous speech (hesitations and filled pauses, relaxed syntax, repetitions, self-corrections, incomplete constituents, irrelevant or redundant information, etc.) as well as idiosyncratic speaker traits. In the paper, we discuss the pros and cons of data so elicited. Following that, we present a typical SMALLWorlds task: the description of a simple drawing with differently coloured circles, squares, and triangles, with no hints given as to which description strategy or language style to use. We conclude with an example on how SMALLWorlds may be used: unsupervised lexical learning from phonetic transcription. At the time of writing, SMALLWorlds consists of more than 250 recordings in a wide range of typologically diverse languages from many parts of the world, some unwritten and endangered.</abstract>
<identifier type="citekey">henrichsen-uneson-2012-smallworlds</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/357_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>3362</start>
<end>3368</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SMALLWorlds – Multilingual Content-Controlled Monologues
%A Henrichsen, Peter Juel
%A Uneson, Marcus
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F henrichsen-uneson-2012-smallworlds
%X We present the speech corpus SMALLWorlds (Spoken Multi-lingual Accounts of Logically Limited Worlds), newly established and still growing. SMALLWorlds contains monologic descriptions of scenes or worlds which are simple enough to be formally describable. The descriptions are instances of content-controlled monologue: semantically ”””“pre-specified”””” but still bearing most hallmarks of spontaneous speech (hesitations and filled pauses, relaxed syntax, repetitions, self-corrections, incomplete constituents, irrelevant or redundant information, etc.) as well as idiosyncratic speaker traits. In the paper, we discuss the pros and cons of data so elicited. Following that, we present a typical SMALLWorlds task: the description of a simple drawing with differently coloured circles, squares, and triangles, with no hints given as to which description strategy or language style to use. We conclude with an example on how SMALLWorlds may be used: unsupervised lexical learning from phonetic transcription. At the time of writing, SMALLWorlds consists of more than 250 recordings in a wide range of typologically diverse languages from many parts of the world, some unwritten and endangered.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/357_Paper.pdf
%P 3362-3368
Markdown (Informal)
[SMALLWorlds – Multilingual Content-Controlled Monologues](http://www.lrec-conf.org/proceedings/lrec2012/pdf/357_Paper.pdf) (Henrichsen & Uneson, LREC 2012)
ACL
- Peter Juel Henrichsen and Marcus Uneson. 2012. SMALLWorlds – Multilingual Content-Controlled Monologues. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 3362–3368, Istanbul, Turkey. European Language Resources Association (ELRA).