@inproceedings{trojanova-etal-2008-design,
title = "Design and Recording of {C}zech Audio-Visual Database with Impaired Conditions for Continuous Speech Recognition",
author = "Trojanov{\'a}, Jana and
Hr{\'u}z, Marek and
Campr, Pavel and
{\v{Z}}elezn{\'y}, Milo{\v{s}}",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}`08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L08-1466/",
abstract = "In this paper we discuss the design, acquisition and preprocessing of a Czech audio-visual speech corpus. The corpus is intended for training and testing of existing audio-visual speech recognition system. The name of the database is UWB-07-ICAVR, where ICAVR stands for Impaired Condition Audio Visual speech Recognition. The corpus consists of 10,000 utterances of continuous speech obtained from 50 speakers. The total length of the database is 25 hours. Each utterance is stored as a separate sentence. The corpus extends existing databases by covering condition of variable illumination. We acquired 50 speakers, where half of them were men and half of them were women. Recording was done by two cameras and two microphones. Database introduced in this paper can be used for testing of visual parameterization in audio-visual speech recognition (AVSR). Corpus can be easily split into training and testing part. Each speaker pronounced 200 sentences: first 50 were the same for all, the rest of them were different. Six types of illumination were covered. Session for one speaker can fit on one DVD disk. All files are accompanied by visual labels. Labels specify region of interest (mouth and area around them specified by bounding box). Actual pronunciation of each sentence is transcribed into the text file."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="trojanova-etal-2008-design">
<titleInfo>
<title>Design and Recording of Czech Audio-Visual Database with Impaired Conditions for Continuous Speech Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jana</namePart>
<namePart type="family">Trojanová</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marek</namePart>
<namePart type="family">Hrúz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pavel</namePart>
<namePart type="family">Campr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miloš</namePart>
<namePart type="family">Železný</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC‘08)</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">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">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper we discuss the design, acquisition and preprocessing of a Czech audio-visual speech corpus. The corpus is intended for training and testing of existing audio-visual speech recognition system. The name of the database is UWB-07-ICAVR, where ICAVR stands for Impaired Condition Audio Visual speech Recognition. The corpus consists of 10,000 utterances of continuous speech obtained from 50 speakers. The total length of the database is 25 hours. Each utterance is stored as a separate sentence. The corpus extends existing databases by covering condition of variable illumination. We acquired 50 speakers, where half of them were men and half of them were women. Recording was done by two cameras and two microphones. Database introduced in this paper can be used for testing of visual parameterization in audio-visual speech recognition (AVSR). Corpus can be easily split into training and testing part. Each speaker pronounced 200 sentences: first 50 were the same for all, the rest of them were different. Six types of illumination were covered. Session for one speaker can fit on one DVD disk. All files are accompanied by visual labels. Labels specify region of interest (mouth and area around them specified by bounding box). Actual pronunciation of each sentence is transcribed into the text file.</abstract>
<identifier type="citekey">trojanova-etal-2008-design</identifier>
<location>
<url>https://aclanthology.org/L08-1466/</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Design and Recording of Czech Audio-Visual Database with Impaired Conditions for Continuous Speech Recognition
%A Trojanová, Jana
%A Hrúz, Marek
%A Campr, Pavel
%A Železný, Miloš
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC‘08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F trojanova-etal-2008-design
%X In this paper we discuss the design, acquisition and preprocessing of a Czech audio-visual speech corpus. The corpus is intended for training and testing of existing audio-visual speech recognition system. The name of the database is UWB-07-ICAVR, where ICAVR stands for Impaired Condition Audio Visual speech Recognition. The corpus consists of 10,000 utterances of continuous speech obtained from 50 speakers. The total length of the database is 25 hours. Each utterance is stored as a separate sentence. The corpus extends existing databases by covering condition of variable illumination. We acquired 50 speakers, where half of them were men and half of them were women. Recording was done by two cameras and two microphones. Database introduced in this paper can be used for testing of visual parameterization in audio-visual speech recognition (AVSR). Corpus can be easily split into training and testing part. Each speaker pronounced 200 sentences: first 50 were the same for all, the rest of them were different. Six types of illumination were covered. Session for one speaker can fit on one DVD disk. All files are accompanied by visual labels. Labels specify region of interest (mouth and area around them specified by bounding box). Actual pronunciation of each sentence is transcribed into the text file.
%U https://aclanthology.org/L08-1466/
Markdown (Informal)
[Design and Recording of Czech Audio-Visual Database with Impaired Conditions for Continuous Speech Recognition](https://aclanthology.org/L08-1466/) (Trojanová et al., LREC 2008)
ACL