@inproceedings{cieri-etal-2008-bridging,
title = "Bridging the Gap between Linguists and Technology Developers: Large-Scale, Sociolinguistic Annotation for Dialect and Speaker Recognition",
author = "Cieri, Christopher and
Strassel, Stephanie and
Glenn, Meghan and
Schwartz, Reva and
Shen, Wade and
Campbell, Joseph",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/793_paper.pdf",
abstract = "Recent years have seen increased interest within the speaker recognition community in high-level features including, for example, lexical choice, idiomatic expressions or syntactic structures. The promise of speaker recognition in forensic applications drives development toward systems robust to channel differences by selecting features inherently robust to channel difference. Within the language recognition community, there is growing interest in differentiating not only languages but also mutually intelligible dialects of a single language. Decades of research in dialectology suggest that high-level features can enable systems to cluster speakers according to the dialects they speak. The Phanotics (Phonetic Annotation of Typicality in Conversational Speech) project seeks to identify high-level features characteristic of American dialects, annotate a corpus for these features, use the data to dialect recognition systems and also use the categorization to create better models for speaker recognition. The data, once published, should be useful to other developers of speaker and dialect recognition systems and to dialectologists and sociolinguists. We expect the methods will generalize well beyond the speakers, dialects, and languages discussed here and should, if successful, provide a model for how linguists and technology developers can collaborate in the future for the benefit of both groups and toward a deeper understanding of how languages vary and change.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cieri-etal-2008-bridging">
<titleInfo>
<title>Bridging the Gap between Linguists and Technology Developers: Large-Scale, Sociolinguistic Annotation for Dialect and Speaker Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephanie</namePart>
<namePart type="family">Strassel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meghan</namePart>
<namePart type="family">Glenn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reva</namePart>
<namePart type="family">Schwartz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wade</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Campbell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-may</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</title>
</titleInfo>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent years have seen increased interest within the speaker recognition community in high-level features including, for example, lexical choice, idiomatic expressions or syntactic structures. The promise of speaker recognition in forensic applications drives development toward systems robust to channel differences by selecting features inherently robust to channel difference. Within the language recognition community, there is growing interest in differentiating not only languages but also mutually intelligible dialects of a single language. Decades of research in dialectology suggest that high-level features can enable systems to cluster speakers according to the dialects they speak. The Phanotics (Phonetic Annotation of Typicality in Conversational Speech) project seeks to identify high-level features characteristic of American dialects, annotate a corpus for these features, use the data to dialect recognition systems and also use the categorization to create better models for speaker recognition. The data, once published, should be useful to other developers of speaker and dialect recognition systems and to dialectologists and sociolinguists. We expect the methods will generalize well beyond the speakers, dialects, and languages discussed here and should, if successful, provide a model for how linguists and technology developers can collaborate in the future for the benefit of both groups and toward a deeper understanding of how languages vary and change.</abstract>
<identifier type="citekey">cieri-etal-2008-bridging</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/793_paper.pdf</url>
</location>
<part>
<date>2008-may</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bridging the Gap between Linguists and Technology Developers: Large-Scale, Sociolinguistic Annotation for Dialect and Speaker Recognition
%A Cieri, Christopher
%A Strassel, Stephanie
%A Glenn, Meghan
%A Schwartz, Reva
%A Shen, Wade
%A Campbell, Joseph
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 may
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F cieri-etal-2008-bridging
%X Recent years have seen increased interest within the speaker recognition community in high-level features including, for example, lexical choice, idiomatic expressions or syntactic structures. The promise of speaker recognition in forensic applications drives development toward systems robust to channel differences by selecting features inherently robust to channel difference. Within the language recognition community, there is growing interest in differentiating not only languages but also mutually intelligible dialects of a single language. Decades of research in dialectology suggest that high-level features can enable systems to cluster speakers according to the dialects they speak. The Phanotics (Phonetic Annotation of Typicality in Conversational Speech) project seeks to identify high-level features characteristic of American dialects, annotate a corpus for these features, use the data to dialect recognition systems and also use the categorization to create better models for speaker recognition. The data, once published, should be useful to other developers of speaker and dialect recognition systems and to dialectologists and sociolinguists. We expect the methods will generalize well beyond the speakers, dialects, and languages discussed here and should, if successful, provide a model for how linguists and technology developers can collaborate in the future for the benefit of both groups and toward a deeper understanding of how languages vary and change.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/793_paper.pdf
Markdown (Informal)
[Bridging the Gap between Linguists and Technology Developers: Large-Scale, Sociolinguistic Annotation for Dialect and Speaker Recognition](http://www.lrec-conf.org/proceedings/lrec2008/pdf/793_paper.pdf) (Cieri et al., LREC 2008)
ACL