@inproceedings{schuppler-etal-2014-grass,
title = "{GRASS}: the Graz corpus of Read And Spontaneous Speech",
author = "Schuppler, Barbara and
Hagmueller, Martin and
Morales-Cordovilla, Juan A. and
Pessentheiner, Hannes",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/394_Paper.pdf",
pages = "1465--1470",
abstract = "This paper provides a description of the preparation, the speakers, the recordings, and the creation of the orthographic transcriptions of the first large scale speech database for Austrian German. It contains approximately 1900 minutes of (read and spontaneous) speech produced by 38 speakers. The corpus consists of three components. First, the Conversation Speech (CS) component contains free conversations of one hour length between friends, colleagues, couples, or family members. Second, the Commands Component (CC) contains commands and keywords which were either read or elicited by pictures. Third, the Read Speech (RS) component contains phonetically balanced sentences and digits. The speech of all components has been recorded at super-wideband quality in a soundproof recording-studio with head-mounted microphones, large-diaphragm microphones, a laryngograph, and with a video camera. The orthographic transcriptions, which have been created and subsequently corrected manually, contain approximately 290 000 word tokens from 15 000 different word types.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="schuppler-etal-2014-grass">
<titleInfo>
<title>GRASS: the Graz corpus of Read And Spontaneous Speech</title>
</titleInfo>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Schuppler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Hagmueller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Morales-Cordovilla</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hannes</namePart>
<namePart type="family">Pessentheiner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hrafn</namePart>
<namePart type="family">Loftsson</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">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 (ELRA)</publisher>
<place>
<placeTerm type="text">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper provides a description of the preparation, the speakers, the recordings, and the creation of the orthographic transcriptions of the first large scale speech database for Austrian German. It contains approximately 1900 minutes of (read and spontaneous) speech produced by 38 speakers. The corpus consists of three components. First, the Conversation Speech (CS) component contains free conversations of one hour length between friends, colleagues, couples, or family members. Second, the Commands Component (CC) contains commands and keywords which were either read or elicited by pictures. Third, the Read Speech (RS) component contains phonetically balanced sentences and digits. The speech of all components has been recorded at super-wideband quality in a soundproof recording-studio with head-mounted microphones, large-diaphragm microphones, a laryngograph, and with a video camera. The orthographic transcriptions, which have been created and subsequently corrected manually, contain approximately 290 000 word tokens from 15 000 different word types.</abstract>
<identifier type="citekey">schuppler-etal-2014-grass</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/394_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>1465</start>
<end>1470</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GRASS: the Graz corpus of Read And Spontaneous Speech
%A Schuppler, Barbara
%A Hagmueller, Martin
%A Morales-Cordovilla, Juan A.
%A Pessentheiner, Hannes
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F schuppler-etal-2014-grass
%X This paper provides a description of the preparation, the speakers, the recordings, and the creation of the orthographic transcriptions of the first large scale speech database for Austrian German. It contains approximately 1900 minutes of (read and spontaneous) speech produced by 38 speakers. The corpus consists of three components. First, the Conversation Speech (CS) component contains free conversations of one hour length between friends, colleagues, couples, or family members. Second, the Commands Component (CC) contains commands and keywords which were either read or elicited by pictures. Third, the Read Speech (RS) component contains phonetically balanced sentences and digits. The speech of all components has been recorded at super-wideband quality in a soundproof recording-studio with head-mounted microphones, large-diaphragm microphones, a laryngograph, and with a video camera. The orthographic transcriptions, which have been created and subsequently corrected manually, contain approximately 290 000 word tokens from 15 000 different word types.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/394_Paper.pdf
%P 1465-1470
Markdown (Informal)
[GRASS: the Graz corpus of Read And Spontaneous Speech](http://www.lrec-conf.org/proceedings/lrec2014/pdf/394_Paper.pdf) (Schuppler et al., LREC 2014)
ACL
- Barbara Schuppler, Martin Hagmueller, Juan A. Morales-Cordovilla, and Hannes Pessentheiner. 2014. GRASS: the Graz corpus of Read And Spontaneous Speech. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 1465–1470, Reykjavik, Iceland. European Language Resources Association (ELRA).