@inproceedings{stadtschnitzer-etal-2014-exploiting,
title = "Exploiting the large-scale {G}erman Broadcast Corpus to boost the Fraunhofer {IAIS} Speech Recognition System",
author = "Stadtschnitzer, Michael and
Schwenninger, Jochen and
Stein, Daniel and
Koehler, Joachim",
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/858_Paper.pdf",
pages = "3887--3890",
abstract = "In this paper we describe the large-scale German broadcast corpus (GER-TV1000h) containing more than 1,000 hours of transcribed speech data. This corpus is unique in the German language corpora domain and enables significant progress in tuning the acoustic modelling of German large vocabulary continuous speech recognition (LVCSR) systems. The exploitation of this huge broadcast corpus is demonstrated by optimizing and improving the Fraunhofer IAIS speech recognition system. Due to the availability of huge amount of acoustic training data new training strategies are investigated. The performance of the automatic speech recognition (ASR) system is evaluated on several datasets and compared to previously published results. It can be shown that the word error rate (WER) using a larger corpus can be reduced by up to 9.1 {\%} relative. By using both larger corpus and recent training paradigms the WER was reduced by up to 35.8 {\%} relative and below 40 {\%} absolute even for spontaneous dialectal speech in noisy conditions, making the ASR output a useful resource for subsequent tasks like named entity recognition also in difficult acoustic situations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="stadtschnitzer-etal-2014-exploiting">
<titleInfo>
<title>Exploiting the large-scale German Broadcast Corpus to boost the Fraunhofer IAIS Speech Recognition System</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Stadtschnitzer</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">Daniel</namePart>
<namePart type="family">Stein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joachim</namePart>
<namePart type="family">Koehler</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>In this paper we describe the large-scale German broadcast corpus (GER-TV1000h) containing more than 1,000 hours of transcribed speech data. This corpus is unique in the German language corpora domain and enables significant progress in tuning the acoustic modelling of German large vocabulary continuous speech recognition (LVCSR) systems. The exploitation of this huge broadcast corpus is demonstrated by optimizing and improving the Fraunhofer IAIS speech recognition system. Due to the availability of huge amount of acoustic training data new training strategies are investigated. The performance of the automatic speech recognition (ASR) system is evaluated on several datasets and compared to previously published results. It can be shown that the word error rate (WER) using a larger corpus can be reduced by up to 9.1 % relative. By using both larger corpus and recent training paradigms the WER was reduced by up to 35.8 % relative and below 40 % absolute even for spontaneous dialectal speech in noisy conditions, making the ASR output a useful resource for subsequent tasks like named entity recognition also in difficult acoustic situations.</abstract>
<identifier type="citekey">stadtschnitzer-etal-2014-exploiting</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/858_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>3887</start>
<end>3890</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploiting the large-scale German Broadcast Corpus to boost the Fraunhofer IAIS Speech Recognition System
%A Stadtschnitzer, Michael
%A Schwenninger, Jochen
%A Stein, Daniel
%A Koehler, Joachim
%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 stadtschnitzer-etal-2014-exploiting
%X In this paper we describe the large-scale German broadcast corpus (GER-TV1000h) containing more than 1,000 hours of transcribed speech data. This corpus is unique in the German language corpora domain and enables significant progress in tuning the acoustic modelling of German large vocabulary continuous speech recognition (LVCSR) systems. The exploitation of this huge broadcast corpus is demonstrated by optimizing and improving the Fraunhofer IAIS speech recognition system. Due to the availability of huge amount of acoustic training data new training strategies are investigated. The performance of the automatic speech recognition (ASR) system is evaluated on several datasets and compared to previously published results. It can be shown that the word error rate (WER) using a larger corpus can be reduced by up to 9.1 % relative. By using both larger corpus and recent training paradigms the WER was reduced by up to 35.8 % relative and below 40 % absolute even for spontaneous dialectal speech in noisy conditions, making the ASR output a useful resource for subsequent tasks like named entity recognition also in difficult acoustic situations.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/858_Paper.pdf
%P 3887-3890
Markdown (Informal)
[Exploiting the large-scale German Broadcast Corpus to boost the Fraunhofer IAIS Speech Recognition System](http://www.lrec-conf.org/proceedings/lrec2014/pdf/858_Paper.pdf) (Stadtschnitzer et al., LREC 2014)
ACL