@inproceedings{ivanko-etal-2022-rusavic,
title = "{RUSAVIC} Corpus: {R}ussian Audio-Visual Speech in Cars",
author = "Ivanko, Denis and
Axyonov, Alexandr and
Ryumin, Dmitry and
Kashevnik, Alexey and
Karpov, Alexey",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.166",
pages = "1555--1559",
abstract = "We present a new audio-visual speech corpus (RUSAVIC) recorded in a car environment and designed for noise-robust speech recognition. Our goal was to produce a speech corpus which is natural (recorded in real driving conditions), controlled (providing different SNR levels by windows open/closed, moving/parked vehicle, etc.), and adequate size (the amount of data is enough to train state-of-the-art NN approaches). We focus on the problem of audio-visual speech recognition: with the use of automated lip-reading to improve the performance of audio-based speech recognition in the presence of severe acoustic noise caused by road traffic. We also describe the equipment and procedures used to create RUSAVIC corpus. Data are collected in a synchronous way through several smartphones located at different angles and equipped with FullHD video camera and microphone. The corpus includes the recordings of 20 drivers with minimum of 10 recording sessions for each. Besides providing a detailed description of the dataset and its collection pipeline, we evaluate several popular audio and visual speech recognition methods and present a set of baseline recognition results. At the moment RUSAVIC is a unique audio-visual corpus for the Russian language that is recorded in-the-wild condition and we make it publicly available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ivanko-etal-2022-rusavic">
<titleInfo>
<title>RUSAVIC Corpus: Russian Audio-Visual Speech in Cars</title>
</titleInfo>
<name type="personal">
<namePart type="given">Denis</namePart>
<namePart type="family">Ivanko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandr</namePart>
<namePart type="family">Axyonov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dmitry</namePart>
<namePart type="family">Ryumin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexey</namePart>
<namePart type="family">Kashevnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexey</namePart>
<namePart type="family">Karpov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</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">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</namePart>
<namePart type="family">Mazo</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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a new audio-visual speech corpus (RUSAVIC) recorded in a car environment and designed for noise-robust speech recognition. Our goal was to produce a speech corpus which is natural (recorded in real driving conditions), controlled (providing different SNR levels by windows open/closed, moving/parked vehicle, etc.), and adequate size (the amount of data is enough to train state-of-the-art NN approaches). We focus on the problem of audio-visual speech recognition: with the use of automated lip-reading to improve the performance of audio-based speech recognition in the presence of severe acoustic noise caused by road traffic. We also describe the equipment and procedures used to create RUSAVIC corpus. Data are collected in a synchronous way through several smartphones located at different angles and equipped with FullHD video camera and microphone. The corpus includes the recordings of 20 drivers with minimum of 10 recording sessions for each. Besides providing a detailed description of the dataset and its collection pipeline, we evaluate several popular audio and visual speech recognition methods and present a set of baseline recognition results. At the moment RUSAVIC is a unique audio-visual corpus for the Russian language that is recorded in-the-wild condition and we make it publicly available.</abstract>
<identifier type="citekey">ivanko-etal-2022-rusavic</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.166</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>1555</start>
<end>1559</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RUSAVIC Corpus: Russian Audio-Visual Speech in Cars
%A Ivanko, Denis
%A Axyonov, Alexandr
%A Ryumin, Dmitry
%A Kashevnik, Alexey
%A Karpov, Alexey
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F ivanko-etal-2022-rusavic
%X We present a new audio-visual speech corpus (RUSAVIC) recorded in a car environment and designed for noise-robust speech recognition. Our goal was to produce a speech corpus which is natural (recorded in real driving conditions), controlled (providing different SNR levels by windows open/closed, moving/parked vehicle, etc.), and adequate size (the amount of data is enough to train state-of-the-art NN approaches). We focus on the problem of audio-visual speech recognition: with the use of automated lip-reading to improve the performance of audio-based speech recognition in the presence of severe acoustic noise caused by road traffic. We also describe the equipment and procedures used to create RUSAVIC corpus. Data are collected in a synchronous way through several smartphones located at different angles and equipped with FullHD video camera and microphone. The corpus includes the recordings of 20 drivers with minimum of 10 recording sessions for each. Besides providing a detailed description of the dataset and its collection pipeline, we evaluate several popular audio and visual speech recognition methods and present a set of baseline recognition results. At the moment RUSAVIC is a unique audio-visual corpus for the Russian language that is recorded in-the-wild condition and we make it publicly available.
%U https://aclanthology.org/2022.lrec-1.166
%P 1555-1559
Markdown (Informal)
[RUSAVIC Corpus: Russian Audio-Visual Speech in Cars](https://aclanthology.org/2022.lrec-1.166) (Ivanko et al., LREC 2022)
ACL
- Denis Ivanko, Alexandr Axyonov, Dmitry Ryumin, Alexey Kashevnik, and Alexey Karpov. 2022. RUSAVIC Corpus: Russian Audio-Visual Speech in Cars. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 1555–1559, Marseille, France. European Language Resources Association.