@inproceedings{altosaar-etal-2010-speech,
title = "A Speech Corpus for Modeling Language Acquisition: {CAREGIVER}",
author = "Altosaar, Toomas and
ten Bosch, Louis and
Aimetti, Guillaume and
Koniaris, Christos and
Demuynck, Kris and
van den Heuvel, Henk",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/597_Paper.pdf",
abstract = "A multi-lingual speech corpus used for modeling language acquisition called CAREGIVER has been designed and recorded within the framework of the EU funded Acquisition of Communication and Recognition Skills (ACORNS) project. The paper describes the motivation behind the corpus and its design by relying on current knowledge regarding infant language acquisition. Instead of recording infants and children, the voices of their primary and secondary caregivers were captured in both infant-directed and adult-directed speech modes over four languages in a read speech manner. The challenges and methods applied to obtain similar prompts in terms of complexity and semantics across different languages, as well as the normalized recording procedures employed at different locations, is covered. The corpus contains nearly 66000 utterance based audio files spoken over a two-year period by 17 male and 17 female native speakers of Dutch, English, Finnish, and Swedish. An orthographical transcription is available for every utterance. Also, time-aligned word and phone annotations for many of the sub-corpora also exist. The CAREGIVER corpus will be published via ELRA.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="altosaar-etal-2010-speech">
<titleInfo>
<title>A Speech Corpus for Modeling Language Acquisition: CAREGIVER</title>
</titleInfo>
<name type="personal">
<namePart type="given">Toomas</namePart>
<namePart type="family">Altosaar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Louis</namePart>
<namePart type="family">ten Bosch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guillaume</namePart>
<namePart type="family">Aimetti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Koniaris</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kris</namePart>
<namePart type="family">Demuynck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">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">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>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Rosner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>A multi-lingual speech corpus used for modeling language acquisition called CAREGIVER has been designed and recorded within the framework of the EU funded Acquisition of Communication and Recognition Skills (ACORNS) project. The paper describes the motivation behind the corpus and its design by relying on current knowledge regarding infant language acquisition. Instead of recording infants and children, the voices of their primary and secondary caregivers were captured in both infant-directed and adult-directed speech modes over four languages in a read speech manner. The challenges and methods applied to obtain similar prompts in terms of complexity and semantics across different languages, as well as the normalized recording procedures employed at different locations, is covered. The corpus contains nearly 66000 utterance based audio files spoken over a two-year period by 17 male and 17 female native speakers of Dutch, English, Finnish, and Swedish. An orthographical transcription is available for every utterance. Also, time-aligned word and phone annotations for many of the sub-corpora also exist. The CAREGIVER corpus will be published via ELRA.</abstract>
<identifier type="citekey">altosaar-etal-2010-speech</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/597_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Speech Corpus for Modeling Language Acquisition: CAREGIVER
%A Altosaar, Toomas
%A ten Bosch, Louis
%A Aimetti, Guillaume
%A Koniaris, Christos
%A Demuynck, Kris
%A van den Heuvel, Henk
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F altosaar-etal-2010-speech
%X A multi-lingual speech corpus used for modeling language acquisition called CAREGIVER has been designed and recorded within the framework of the EU funded Acquisition of Communication and Recognition Skills (ACORNS) project. The paper describes the motivation behind the corpus and its design by relying on current knowledge regarding infant language acquisition. Instead of recording infants and children, the voices of their primary and secondary caregivers were captured in both infant-directed and adult-directed speech modes over four languages in a read speech manner. The challenges and methods applied to obtain similar prompts in terms of complexity and semantics across different languages, as well as the normalized recording procedures employed at different locations, is covered. The corpus contains nearly 66000 utterance based audio files spoken over a two-year period by 17 male and 17 female native speakers of Dutch, English, Finnish, and Swedish. An orthographical transcription is available for every utterance. Also, time-aligned word and phone annotations for many of the sub-corpora also exist. The CAREGIVER corpus will be published via ELRA.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/597_Paper.pdf
Markdown (Informal)
[A Speech Corpus for Modeling Language Acquisition: CAREGIVER](http://www.lrec-conf.org/proceedings/lrec2010/pdf/597_Paper.pdf) (Altosaar et al., LREC 2010)
ACL
- Toomas Altosaar, Louis ten Bosch, Guillaume Aimetti, Christos Koniaris, Kris Demuynck, and Henk van den Heuvel. 2010. A Speech Corpus for Modeling Language Acquisition: CAREGIVER. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).