Video/Audio Open Access

ASVspoof 2021 Challenge - Logical Access Database

Delgado, Héctor; Evans, Nicholas; Kinnunen, Tomi; Lee, Kong Aik; Liu, Xuechen; Nautsch, Andreas; Patino, Jose; Sahidullah, Md; Todisco, Massimiliano; Wang, Xin; Yamagishi, Junichi


MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000ngm##2200000uu#4500</leader>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Speaker recognition</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Speaker verification</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">ASVspoof</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Anti-spoofing</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Presentation attack detection</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Deepfake detection</subfield>
  </datafield>
  <controlfield tag="005">20210528172641.0</controlfield>
  <controlfield tag="001">4837263</controlfield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">EURECOM, France</subfield>
    <subfield code="a">Evans, Nicholas</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">University of Eastern Finland, Finland</subfield>
    <subfield code="a">Kinnunen, Tomi</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Institute for Infocomm Research, Singapore</subfield>
    <subfield code="a">Lee, Kong Aik</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">University of Eastern Finland, Finland</subfield>
    <subfield code="a">Liu, Xuechen</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">EURECOM, France</subfield>
    <subfield code="a">Nautsch, Andreas</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">EURECOM, France</subfield>
    <subfield code="a">Patino, Jose</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Inria, France</subfield>
    <subfield code="a">Sahidullah, Md</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">EURECOM, France</subfield>
    <subfield code="a">Todisco, Massimiliano</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">National Institute of Informatics, Japan</subfield>
    <subfield code="a">Wang, Xin</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">National Institute of Informatics, Japan</subfield>
    <subfield code="a">Yamagishi, Junichi</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">7763666128</subfield>
    <subfield code="z">md5:2abee34d8b0b91159555fc4f016e4562</subfield>
    <subfield code="u">https://zenodo.org/record/4837263/files/ASVspoof2021_LA_eval.tar.gz</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2021-05-28</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="o">oai:zenodo.org:4837263</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">Nuance Communications Inc., Spain</subfield>
    <subfield code="a">Delgado, Héctor</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">ASVspoof 2021 Challenge - Logical Access Database</subfield>
  </datafield>
  <datafield tag="536" ind1=" " ind2=" ">
    <subfield code="c">ANR-18-CE92-0024</subfield>
    <subfield code="a">Reliable, secure and privacy preserving multi-biometric person authentication</subfield>
  </datafield>
  <datafield tag="536" ind1=" " ind2=" ">
    <subfield code="c">309629</subfield>
    <subfield code="a">NOTCH: NOn-cooperaTive speaker CHaracterization</subfield>
  </datafield>
  <datafield tag="536" ind1=" " ind2=" ">
    <subfield code="c">ANR-18-JSTS-0001</subfield>
    <subfield code="a">Speaker identity cloning and protection</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">https://opendatacommons.org/licenses/by/1.0/</subfield>
    <subfield code="a">Open Data Commons Attribution License v1.0</subfield>
  </datafield>
  <datafield tag="650" ind1="1" ind2="7">
    <subfield code="a">cc-by</subfield>
    <subfield code="2">opendefinition.org</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">&lt;p&gt;The automatic speaker verification spoofing and countermeasures (ASVspoof) challenge series is a community-led initiative which aims to promote the consideration of spoofing and the development of countermeasures. &amp;nbsp;ASVspoof 2021 is the 4th in a series of bi-annual, competitive challenges where the goal is to develop countermeasures capable of discriminating between bona fide and spoofed or deepfake speech.&amp;nbsp;&lt;/p&gt;

&lt;p&gt;ASVspoof 2021 comprises three different tasks:&amp;nbsp; &amp;nbsp;&amp;nbsp;&lt;br&gt;
&amp;nbsp;&lt;em&gt;Logical access (LA)&lt;/em&gt;: bona fide and spoofed utterances generated using text-to-speech (TTS) and voice conversion (VC) algorithms are communicated across telephony and VoIP networks with various coding and transmission effects;&lt;br&gt;
&amp;nbsp; &amp;nbsp;&amp;nbsp;&lt;br&gt;
&lt;em&gt;Physical access (PA)&lt;/em&gt;: bona fide utterances are made in a real, physical space in which spoofing attacks are captured and then replayed within the same physical space using replay devices of varying quality;&lt;br&gt;
&amp;nbsp; &amp;nbsp;&amp;nbsp;&lt;br&gt;
&lt;em&gt;Speech deepfake (DF)&lt;/em&gt;: a fake audio detection task comprising bona fide and spoofed utterances generated using TTS and VC algorithms. Similar to the LA task (includes compressed data) but without speaker verification.&lt;/p&gt;

&lt;p&gt;&lt;strong&gt;This repository provides the evaluation set for the&amp;nbsp;LA&amp;nbsp;task.&lt;/strong&gt;&lt;/p&gt;

&lt;p&gt;For more details, please visit our website below.&amp;nbsp;https://www.asvspoof.org&lt;/p&gt;</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">doi</subfield>
    <subfield code="i">isVersionOf</subfield>
    <subfield code="a">10.5281/zenodo.4817650</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.4837263</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">video</subfield>
  </datafield>
</record>
1,641
1,365
views
downloads
All versions This version
Views 1,6411,596
Downloads 1,3651,365
Data volume 10.6 TB10.6 TB
Unique views 1,4371,412
Unique downloads 769769

Share

Cite as