@inproceedings{schabus-etal-2012-building,
title = "Building a synchronous corpus of acoustic and 3{D} facial marker data for adaptive audio-visual speech synthesis",
author = "Schabus, Dietmar and
Pucher, Michael and
Hofer, Gregor",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/302_Paper.pdf",
pages = "3313--3316",
abstract = "We have created a synchronous corpus of acoustic and 3D facial marker data from multiple speakers for adaptive audio-visual text-to-speech synthesis. The corpus contains data from one female and two male speakers and amounts to 223 Austrian German sentences each. In this paper, we first describe the recording process, using professional audio equipment and a marker-based 3D facial motion capturing system for the audio-visual recordings. We then turn to post-processing, which incorporates forced alignment, principal component analysis (PCA) on the visual data, and some manual checking and corrections. Finally, we describe the resulting corpus, which will be released under a research license at the end of our project. We show that the standard PCA based feature extraction approach also works on a multi-speaker database in the adaptation scenario, where there is no data from the target speaker available in the PCA step.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="schabus-etal-2012-building">
<titleInfo>
<title>Building a synchronous corpus of acoustic and 3D facial marker data for adaptive audio-visual speech synthesis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dietmar</namePart>
<namePart type="family">Schabus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Pucher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gregor</namePart>
<namePart type="family">Hofer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We have created a synchronous corpus of acoustic and 3D facial marker data from multiple speakers for adaptive audio-visual text-to-speech synthesis. The corpus contains data from one female and two male speakers and amounts to 223 Austrian German sentences each. In this paper, we first describe the recording process, using professional audio equipment and a marker-based 3D facial motion capturing system for the audio-visual recordings. We then turn to post-processing, which incorporates forced alignment, principal component analysis (PCA) on the visual data, and some manual checking and corrections. Finally, we describe the resulting corpus, which will be released under a research license at the end of our project. We show that the standard PCA based feature extraction approach also works on a multi-speaker database in the adaptation scenario, where there is no data from the target speaker available in the PCA step.</abstract>
<identifier type="citekey">schabus-etal-2012-building</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/302_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>3313</start>
<end>3316</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Building a synchronous corpus of acoustic and 3D facial marker data for adaptive audio-visual speech synthesis
%A Schabus, Dietmar
%A Pucher, Michael
%A Hofer, Gregor
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F schabus-etal-2012-building
%X We have created a synchronous corpus of acoustic and 3D facial marker data from multiple speakers for adaptive audio-visual text-to-speech synthesis. The corpus contains data from one female and two male speakers and amounts to 223 Austrian German sentences each. In this paper, we first describe the recording process, using professional audio equipment and a marker-based 3D facial motion capturing system for the audio-visual recordings. We then turn to post-processing, which incorporates forced alignment, principal component analysis (PCA) on the visual data, and some manual checking and corrections. Finally, we describe the resulting corpus, which will be released under a research license at the end of our project. We show that the standard PCA based feature extraction approach also works on a multi-speaker database in the adaptation scenario, where there is no data from the target speaker available in the PCA step.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/302_Paper.pdf
%P 3313-3316
Markdown (Informal)
[Building a synchronous corpus of acoustic and 3D facial marker data for adaptive audio-visual speech synthesis](http://www.lrec-conf.org/proceedings/lrec2012/pdf/302_Paper.pdf) (Schabus et al., LREC 2012)
ACL