@inproceedings{baum-etal-2010-disco,
title = "{D}i{SC}o - A {G}erman Evaluation Corpus for Challenging Problems in the Broadcast Domain",
author = {Baum, Doris and
Schneider, Daniel and
Bardeli, Rolf and
Schwenninger, Jochen and
Samlowski, Barbara and
Winkler, Thomas and
K{\"o}hler, Joachim},
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/355_Paper.pdf",
abstract = "Typical broadcast material contains not only studio-recorded texts read by trained speakers, but also spontaneous and dialect speech, debates with cross-talk, voice-overs, and on-site reports with difficult acoustic environments. Standard approaches to speech and speaker recognition usually deteriorate under such conditions. This paper reports on the design, construction, and experimental analysis of DiSCo, a German corpus for the evaluation of speech and speaker recognition on challenging material from the broadcast domain. One of the key requirements for the design of this corpus was a good coverage of different types of serious programmes beyond clean speech and planned speech broadcast news. Corpus annotation encompasses manual segmentation, an orthographic transcription, and labelling with speech mode, dialect, and noise type. We indicate typical use cases for the corpus by reporting results from ASR, speech search, and speaker recognition on the new corpus, thereby obtaining insights into the difficulty of audio recognition on the various classes.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="baum-etal-2010-disco">
<titleInfo>
<title>DiSCo - A German Evaluation Corpus for Challenging Problems in the Broadcast Domain</title>
</titleInfo>
<name type="personal">
<namePart type="given">Doris</namePart>
<namePart type="family">Baum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Schneider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rolf</namePart>
<namePart type="family">Bardeli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jochen</namePart>
<namePart type="family">Schwenninger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Samlowski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Winkler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joachim</namePart>
<namePart type="family">Köhler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-may</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>
<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>Typical broadcast material contains not only studio-recorded texts read by trained speakers, but also spontaneous and dialect speech, debates with cross-talk, voice-overs, and on-site reports with difficult acoustic environments. Standard approaches to speech and speaker recognition usually deteriorate under such conditions. This paper reports on the design, construction, and experimental analysis of DiSCo, a German corpus for the evaluation of speech and speaker recognition on challenging material from the broadcast domain. One of the key requirements for the design of this corpus was a good coverage of different types of serious programmes beyond clean speech and planned speech broadcast news. Corpus annotation encompasses manual segmentation, an orthographic transcription, and labelling with speech mode, dialect, and noise type. We indicate typical use cases for the corpus by reporting results from ASR, speech search, and speaker recognition on the new corpus, thereby obtaining insights into the difficulty of audio recognition on the various classes.</abstract>
<identifier type="citekey">baum-etal-2010-disco</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/355_Paper.pdf</url>
</location>
<part>
<date>2010-may</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DiSCo - A German Evaluation Corpus for Challenging Problems in the Broadcast Domain
%A Baum, Doris
%A Schneider, Daniel
%A Bardeli, Rolf
%A Schwenninger, Jochen
%A Samlowski, Barbara
%A Winkler, Thomas
%A Köhler, Joachim
%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 baum-etal-2010-disco
%X Typical broadcast material contains not only studio-recorded texts read by trained speakers, but also spontaneous and dialect speech, debates with cross-talk, voice-overs, and on-site reports with difficult acoustic environments. Standard approaches to speech and speaker recognition usually deteriorate under such conditions. This paper reports on the design, construction, and experimental analysis of DiSCo, a German corpus for the evaluation of speech and speaker recognition on challenging material from the broadcast domain. One of the key requirements for the design of this corpus was a good coverage of different types of serious programmes beyond clean speech and planned speech broadcast news. Corpus annotation encompasses manual segmentation, an orthographic transcription, and labelling with speech mode, dialect, and noise type. We indicate typical use cases for the corpus by reporting results from ASR, speech search, and speaker recognition on the new corpus, thereby obtaining insights into the difficulty of audio recognition on the various classes.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/355_Paper.pdf
Markdown (Informal)
[DiSCo - A German Evaluation Corpus for Challenging Problems in the Broadcast Domain](http://www.lrec-conf.org/proceedings/lrec2010/pdf/355_Paper.pdf) (Baum et al., LREC 2010)
ACL