@inproceedings{schiel-2010-bastat,
title = "{BAS}tat : New Statistical Resources at the {B}avarian Archive for Speech Signals",
author = "Schiel, Florian",
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/277_Paper.pdf",
abstract = "A new type of language resource called 'BAStat' has been released by the Bavarian Archive for Speech Signals at Ludwig Maximilians Universitaet, Munich. In contrast to primary resources like speech and text corpora BAStat comprises statistical estimates based on a number of primary spoken language resources: first and second order occurrence probability of phones, syllables and words, duration statistics, probabilities of pronunciation variants of words and probabilities of context information. Unlike other statistical speech resources BAStat is based solely on recordings of conversational German and therefore models spoken language not text. The resource consists of a bundle of 7-bit ASCII tables and matrices to maximize inter-operability between different operation systems and can be downloaded for free from the BAS web-site. This contribution gives a detailed description about the empirical basis, the contained data types, the format of the resulting statistical data, some interesting interpretations of grand figures and a brief comparison to the text-based statistical resource CELEX.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="schiel-2010-bastat">
<titleInfo>
<title>BAStat : New Statistical Resources at the Bavarian Archive for Speech Signals</title>
</titleInfo>
<name type="personal">
<namePart type="given">Florian</namePart>
<namePart type="family">Schiel</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 new type of language resource called ’BAStat’ has been released by the Bavarian Archive for Speech Signals at Ludwig Maximilians Universitaet, Munich. In contrast to primary resources like speech and text corpora BAStat comprises statistical estimates based on a number of primary spoken language resources: first and second order occurrence probability of phones, syllables and words, duration statistics, probabilities of pronunciation variants of words and probabilities of context information. Unlike other statistical speech resources BAStat is based solely on recordings of conversational German and therefore models spoken language not text. The resource consists of a bundle of 7-bit ASCII tables and matrices to maximize inter-operability between different operation systems and can be downloaded for free from the BAS web-site. This contribution gives a detailed description about the empirical basis, the contained data types, the format of the resulting statistical data, some interesting interpretations of grand figures and a brief comparison to the text-based statistical resource CELEX.</abstract>
<identifier type="citekey">schiel-2010-bastat</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/277_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BAStat : New Statistical Resources at the Bavarian Archive for Speech Signals
%A Schiel, Florian
%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 schiel-2010-bastat
%X A new type of language resource called ’BAStat’ has been released by the Bavarian Archive for Speech Signals at Ludwig Maximilians Universitaet, Munich. In contrast to primary resources like speech and text corpora BAStat comprises statistical estimates based on a number of primary spoken language resources: first and second order occurrence probability of phones, syllables and words, duration statistics, probabilities of pronunciation variants of words and probabilities of context information. Unlike other statistical speech resources BAStat is based solely on recordings of conversational German and therefore models spoken language not text. The resource consists of a bundle of 7-bit ASCII tables and matrices to maximize inter-operability between different operation systems and can be downloaded for free from the BAS web-site. This contribution gives a detailed description about the empirical basis, the contained data types, the format of the resulting statistical data, some interesting interpretations of grand figures and a brief comparison to the text-based statistical resource CELEX.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/277_Paper.pdf
Markdown (Informal)
[BAStat : New Statistical Resources at the Bavarian Archive for Speech Signals](http://www.lrec-conf.org/proceedings/lrec2010/pdf/277_Paper.pdf) (Schiel, LREC 2010)
ACL