@inproceedings{brierley-atwell-2010-proposec,
title = "{P}ro{POSEC}: A Prosody and {P}o{S} Annotated Spoken {E}nglish Corpus",
author = "Brierley, Claire and
Atwell, Eric",
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/749_Paper.pdf",
abstract = "We have previously reported on ProPOSEL, a purpose-built Prosody and PoS English Lexicon compatible with the Python Natural Language ToolKit. ProPOSEC is a new corpus research resource built using this lexicon, intended for distribution with the Aix-MARSEC dataset. ProPOSEC comprises multi-level parallel annotations, juxtaposing prosodic and syntactic information from different versions of the Spoken English Corpus, with canonical dictionary forms, in a query format optimized for Perl, Python, and text processing programs. The order and content of fields in the text file is as follows: (1) Aix-MARSEC file number; (2) word; (3) LOB PoS-tag; (4) C5 PoS-tag; (5) Aix SAM-PA phonetic transcription; (6) SAM-PA phonetic transcription from ProPOSEL; (7) syllable count; (8) lexical stress pattern; (9) default content or function word tag; (10) DISC stressed and syllabified phonetic transcription; (11) alternative DISC representation, incorporating lexical stress pattern; (12) nested arrays of phonemes and tonic stress marks from Aix. As an experimental dataset, ProPOSEC can be used to study correlations between these annotation tiers, where significant findings are then expressed as additional features for phrasing models integral to Text-to-Speech and Speech Recognition. As a training set, ProPOSEC can be used for machine learning tasks in Information Retrieval and Speech Understanding systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="brierley-atwell-2010-proposec">
<titleInfo>
<title>ProPOSEC: A Prosody and PoS Annotated Spoken English Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Claire</namePart>
<namePart type="family">Brierley</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Atwell</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>We have previously reported on ProPOSEL, a purpose-built Prosody and PoS English Lexicon compatible with the Python Natural Language ToolKit. ProPOSEC is a new corpus research resource built using this lexicon, intended for distribution with the Aix-MARSEC dataset. ProPOSEC comprises multi-level parallel annotations, juxtaposing prosodic and syntactic information from different versions of the Spoken English Corpus, with canonical dictionary forms, in a query format optimized for Perl, Python, and text processing programs. The order and content of fields in the text file is as follows: (1) Aix-MARSEC file number; (2) word; (3) LOB PoS-tag; (4) C5 PoS-tag; (5) Aix SAM-PA phonetic transcription; (6) SAM-PA phonetic transcription from ProPOSEL; (7) syllable count; (8) lexical stress pattern; (9) default content or function word tag; (10) DISC stressed and syllabified phonetic transcription; (11) alternative DISC representation, incorporating lexical stress pattern; (12) nested arrays of phonemes and tonic stress marks from Aix. As an experimental dataset, ProPOSEC can be used to study correlations between these annotation tiers, where significant findings are then expressed as additional features for phrasing models integral to Text-to-Speech and Speech Recognition. As a training set, ProPOSEC can be used for machine learning tasks in Information Retrieval and Speech Understanding systems.</abstract>
<identifier type="citekey">brierley-atwell-2010-proposec</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/749_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ProPOSEC: A Prosody and PoS Annotated Spoken English Corpus
%A Brierley, Claire
%A Atwell, Eric
%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 brierley-atwell-2010-proposec
%X We have previously reported on ProPOSEL, a purpose-built Prosody and PoS English Lexicon compatible with the Python Natural Language ToolKit. ProPOSEC is a new corpus research resource built using this lexicon, intended for distribution with the Aix-MARSEC dataset. ProPOSEC comprises multi-level parallel annotations, juxtaposing prosodic and syntactic information from different versions of the Spoken English Corpus, with canonical dictionary forms, in a query format optimized for Perl, Python, and text processing programs. The order and content of fields in the text file is as follows: (1) Aix-MARSEC file number; (2) word; (3) LOB PoS-tag; (4) C5 PoS-tag; (5) Aix SAM-PA phonetic transcription; (6) SAM-PA phonetic transcription from ProPOSEL; (7) syllable count; (8) lexical stress pattern; (9) default content or function word tag; (10) DISC stressed and syllabified phonetic transcription; (11) alternative DISC representation, incorporating lexical stress pattern; (12) nested arrays of phonemes and tonic stress marks from Aix. As an experimental dataset, ProPOSEC can be used to study correlations between these annotation tiers, where significant findings are then expressed as additional features for phrasing models integral to Text-to-Speech and Speech Recognition. As a training set, ProPOSEC can be used for machine learning tasks in Information Retrieval and Speech Understanding systems.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/749_Paper.pdf
Markdown (Informal)
[ProPOSEC: A Prosody and PoS Annotated Spoken English Corpus](http://www.lrec-conf.org/proceedings/lrec2010/pdf/749_Paper.pdf) (Brierley & Atwell, LREC 2010)
ACL