@inproceedings{johnson-etal-2020-spice,
title = "{S}pi{CE}: A New Open-Access Corpus of Conversational Bilingual Speech in {C}antonese and {E}nglish",
author = "Johnson, Khia A. and
Babel, Molly and
Fong, Ivan and
Yiu, Nancy",
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
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.503",
pages = "4089--4095",
abstract = "This paper describes the design, collection, orthographic transcription, and phonetic annotation of SpiCE, a new corpus of conversational Cantonese-English bilingual speech recorded in Vancouver, Canada. The corpus includes high-quality recordings of 34 early bilinguals in both English and Cantonese{---}to date, 27 have been recorded for a total of 19 hours of participant speech. Participants completed a sentence reading task, storyboard narration, and conversational interview in each language. Transcription and annotation for the corpus are currently underway. Transcripts produced with Google Cloud Speech-to-Text are available for all participants, and will be included in the initial SpiCE corpus release. Hand-corrected orthographic transcripts and force-aligned phonetic transcripts will be released periodically, and upon completion for all recordings, comprise the second release of the corpus. As an open-access language resource, SpiCE will promote bilingualism research for a typologically distinct pair of languages, of which Cantonese remains understudied despite there being millions of speakers around the world. The SpiCE corpus is especially well-suited for phonetic research on conversational speech, and enables researchers to study cross-language within-speaker phenomena for a diverse group of early Cantonese-English bilinguals. These are areas with few existing high-quality resources.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="johnson-etal-2020-spice">
<titleInfo>
<title>SpiCE: A New Open-Access Corpus of Conversational Bilingual Speech in Cantonese and English</title>
</titleInfo>
<name type="personal">
<namePart type="given">Khia</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Johnson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Molly</namePart>
<namePart type="family">Babel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Fong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Yiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth 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">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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>This paper describes the design, collection, orthographic transcription, and phonetic annotation of SpiCE, a new corpus of conversational Cantonese-English bilingual speech recorded in Vancouver, Canada. The corpus includes high-quality recordings of 34 early bilinguals in both English and Cantonese—to date, 27 have been recorded for a total of 19 hours of participant speech. Participants completed a sentence reading task, storyboard narration, and conversational interview in each language. Transcription and annotation for the corpus are currently underway. Transcripts produced with Google Cloud Speech-to-Text are available for all participants, and will be included in the initial SpiCE corpus release. Hand-corrected orthographic transcripts and force-aligned phonetic transcripts will be released periodically, and upon completion for all recordings, comprise the second release of the corpus. As an open-access language resource, SpiCE will promote bilingualism research for a typologically distinct pair of languages, of which Cantonese remains understudied despite there being millions of speakers around the world. The SpiCE corpus is especially well-suited for phonetic research on conversational speech, and enables researchers to study cross-language within-speaker phenomena for a diverse group of early Cantonese-English bilinguals. These are areas with few existing high-quality resources.</abstract>
<identifier type="citekey">johnson-etal-2020-spice</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.503</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>4089</start>
<end>4095</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SpiCE: A New Open-Access Corpus of Conversational Bilingual Speech in Cantonese and English
%A Johnson, Khia A.
%A Babel, Molly
%A Fong, Ivan
%A Yiu, Nancy
%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 Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F johnson-etal-2020-spice
%X This paper describes the design, collection, orthographic transcription, and phonetic annotation of SpiCE, a new corpus of conversational Cantonese-English bilingual speech recorded in Vancouver, Canada. The corpus includes high-quality recordings of 34 early bilinguals in both English and Cantonese—to date, 27 have been recorded for a total of 19 hours of participant speech. Participants completed a sentence reading task, storyboard narration, and conversational interview in each language. Transcription and annotation for the corpus are currently underway. Transcripts produced with Google Cloud Speech-to-Text are available for all participants, and will be included in the initial SpiCE corpus release. Hand-corrected orthographic transcripts and force-aligned phonetic transcripts will be released periodically, and upon completion for all recordings, comprise the second release of the corpus. As an open-access language resource, SpiCE will promote bilingualism research for a typologically distinct pair of languages, of which Cantonese remains understudied despite there being millions of speakers around the world. The SpiCE corpus is especially well-suited for phonetic research on conversational speech, and enables researchers to study cross-language within-speaker phenomena for a diverse group of early Cantonese-English bilinguals. These are areas with few existing high-quality resources.
%U https://aclanthology.org/2020.lrec-1.503
%P 4089-4095
Markdown (Informal)
[SpiCE: A New Open-Access Corpus of Conversational Bilingual Speech in Cantonese and English](https://aclanthology.org/2020.lrec-1.503) (Johnson et al., LREC 2020)
ACL