@inproceedings{vorwerk-etal-2010-wapusk20,
title = "{WAPUSK}20 - A Database for Robust Audiovisual Speech Recognition",
author = "Vorwerk, Alexander and
Wang, Xiaohui and
Kolossa, Dorothea and
Zeiler, Steffen and
Orglmeister, Reinhold",
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/533_Paper.pdf",
abstract = "Audiovisual speech recognition (AVSR) systems have been proven superior over audio-only speech recognizers in noisy environments by incorporating features of the visual modality. In order to develop reliable AVSR systems, appropriate simultaneously recorded speech and video data is needed. In this paper, we will introduce a corpus (WAPUSK20) that consists of audiovisual data of 20 speakers uttering 100 sentences each with four channels of audio and a stereoscopic video. The latter is intended to support more accurate lip tracking and the development of stereo data based normalization techniques for greater robustness of the recognition results. The sentence design has been adopted from the GRID corpus that has been widely used for AVSR experiments. Recordings have been made under acoustically realistic conditions in a usual office room. Affordable hardware equipment has been used, such as a pre-calibrated stereo camera and standard PC components. The software written to create this corpus was designed in MATLAB with help of hardware specific software provided by the hardware manufacturers and freely available open source software.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vorwerk-etal-2010-wapusk20">
<titleInfo>
<title>WAPUSK20 - A Database for Robust Audiovisual Speech Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Vorwerk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaohui</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dorothea</namePart>
<namePart type="family">Kolossa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steffen</namePart>
<namePart type="family">Zeiler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reinhold</namePart>
<namePart type="family">Orglmeister</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>Audiovisual speech recognition (AVSR) systems have been proven superior over audio-only speech recognizers in noisy environments by incorporating features of the visual modality. In order to develop reliable AVSR systems, appropriate simultaneously recorded speech and video data is needed. In this paper, we will introduce a corpus (WAPUSK20) that consists of audiovisual data of 20 speakers uttering 100 sentences each with four channels of audio and a stereoscopic video. The latter is intended to support more accurate lip tracking and the development of stereo data based normalization techniques for greater robustness of the recognition results. The sentence design has been adopted from the GRID corpus that has been widely used for AVSR experiments. Recordings have been made under acoustically realistic conditions in a usual office room. Affordable hardware equipment has been used, such as a pre-calibrated stereo camera and standard PC components. The software written to create this corpus was designed in MATLAB with help of hardware specific software provided by the hardware manufacturers and freely available open source software.</abstract>
<identifier type="citekey">vorwerk-etal-2010-wapusk20</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/533_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T WAPUSK20 - A Database for Robust Audiovisual Speech Recognition
%A Vorwerk, Alexander
%A Wang, Xiaohui
%A Kolossa, Dorothea
%A Zeiler, Steffen
%A Orglmeister, Reinhold
%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 vorwerk-etal-2010-wapusk20
%X Audiovisual speech recognition (AVSR) systems have been proven superior over audio-only speech recognizers in noisy environments by incorporating features of the visual modality. In order to develop reliable AVSR systems, appropriate simultaneously recorded speech and video data is needed. In this paper, we will introduce a corpus (WAPUSK20) that consists of audiovisual data of 20 speakers uttering 100 sentences each with four channels of audio and a stereoscopic video. The latter is intended to support more accurate lip tracking and the development of stereo data based normalization techniques for greater robustness of the recognition results. The sentence design has been adopted from the GRID corpus that has been widely used for AVSR experiments. Recordings have been made under acoustically realistic conditions in a usual office room. Affordable hardware equipment has been used, such as a pre-calibrated stereo camera and standard PC components. The software written to create this corpus was designed in MATLAB with help of hardware specific software provided by the hardware manufacturers and freely available open source software.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/533_Paper.pdf
Markdown (Informal)
[WAPUSK20 - A Database for Robust Audiovisual Speech Recognition](http://www.lrec-conf.org/proceedings/lrec2010/pdf/533_Paper.pdf) (Vorwerk et al., LREC 2010)
ACL
- Alexander Vorwerk, Xiaohui Wang, Dorothea Kolossa, Steffen Zeiler, and Reinhold Orglmeister. 2010. WAPUSK20 - A Database for Robust Audiovisual Speech Recognition. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).