@inproceedings{pollak-rajnoha-2010-multi,
title = "Multi-Channel Database of Spontaneous {C}zech with Synchronization of Channels Recorded by Independent Devices",
author = "Poll{\'a}k, Petr and
Rajnoha, Josef",
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/516_Paper.pdf",
abstract = "This paper describes Czech spontaneous speech database of lectures on digital signal processing topic collected at Czech Technical University in Prague, commonly with the procedure of its recording and annotation. The database contains 21.7 hours of speech material from 22 speakers recorded in 4 channels with 3 principally different microphones. The annotation of the database is composed from basic time segmentation, orthographic transcription including marks for speaker and environmental non-speech events, pronunciation lexicon in SAMPA alphabet, session and speaker information describing recording conditions, and the documentation. The orthographic transcription with time segmentation is saved in XML format supported by frequently used annotation tool Transcriber. In this article, special attention is also paid to the description of time synchronization of signals recorded by two independent devices: computer based recording platform using two external sound cards and commercial audio recorder Edirol R09. This synchronization is based on cross-correlation analysis with simple automated selection of suitable short signal subparts. The collection and annotation of this database is now complete and its availability via ELRA is currently under preparation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pollak-rajnoha-2010-multi">
<titleInfo>
<title>Multi-Channel Database of Spontaneous Czech with Synchronization of Channels Recorded by Independent Devices</title>
</titleInfo>
<name type="personal">
<namePart type="given">Petr</namePart>
<namePart type="family">Pollák</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josef</namePart>
<namePart type="family">Rajnoha</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>This paper describes Czech spontaneous speech database of lectures on digital signal processing topic collected at Czech Technical University in Prague, commonly with the procedure of its recording and annotation. The database contains 21.7 hours of speech material from 22 speakers recorded in 4 channels with 3 principally different microphones. The annotation of the database is composed from basic time segmentation, orthographic transcription including marks for speaker and environmental non-speech events, pronunciation lexicon in SAMPA alphabet, session and speaker information describing recording conditions, and the documentation. The orthographic transcription with time segmentation is saved in XML format supported by frequently used annotation tool Transcriber. In this article, special attention is also paid to the description of time synchronization of signals recorded by two independent devices: computer based recording platform using two external sound cards and commercial audio recorder Edirol R09. This synchronization is based on cross-correlation analysis with simple automated selection of suitable short signal subparts. The collection and annotation of this database is now complete and its availability via ELRA is currently under preparation.</abstract>
<identifier type="citekey">pollak-rajnoha-2010-multi</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/516_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-Channel Database of Spontaneous Czech with Synchronization of Channels Recorded by Independent Devices
%A Pollák, Petr
%A Rajnoha, Josef
%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 pollak-rajnoha-2010-multi
%X This paper describes Czech spontaneous speech database of lectures on digital signal processing topic collected at Czech Technical University in Prague, commonly with the procedure of its recording and annotation. The database contains 21.7 hours of speech material from 22 speakers recorded in 4 channels with 3 principally different microphones. The annotation of the database is composed from basic time segmentation, orthographic transcription including marks for speaker and environmental non-speech events, pronunciation lexicon in SAMPA alphabet, session and speaker information describing recording conditions, and the documentation. The orthographic transcription with time segmentation is saved in XML format supported by frequently used annotation tool Transcriber. In this article, special attention is also paid to the description of time synchronization of signals recorded by two independent devices: computer based recording platform using two external sound cards and commercial audio recorder Edirol R09. This synchronization is based on cross-correlation analysis with simple automated selection of suitable short signal subparts. The collection and annotation of this database is now complete and its availability via ELRA is currently under preparation.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/516_Paper.pdf
Markdown (Informal)
[Multi-Channel Database of Spontaneous Czech with Synchronization of Channels Recorded by Independent Devices](http://www.lrec-conf.org/proceedings/lrec2010/pdf/516_Paper.pdf) (Pollák & Rajnoha, LREC 2010)
ACL