Software Open Access

astorfi/lip-reading-deeplearning: 3D Convolutional Neural Networks for Cross Audio-Visual Matching Recognition

Amirsina Torfi


MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nmm##2200000uu#4500</leader>
  <datafield tag="999" ind1="C" ind2="5">
    <subfield code="x">Torfi et al. (2017). Source code is associated to arXiv:1706.05739.</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">speech recognition</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">lip reading</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">deep learning</subfield>
  </datafield>
  <controlfield tag="005">20200125192220.0</controlfield>
  <controlfield tag="001">840400</controlfield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">West Virginia University</subfield>
    <subfield code="4">res</subfield>
    <subfield code="a">Amirsina Torfi</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">West Virginia University</subfield>
    <subfield code="4">res</subfield>
    <subfield code="a">Seyed Mehdi Iranmanesh</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">West Virginia University</subfield>
    <subfield code="4">res</subfield>
    <subfield code="a">Nasser Nasrabadi</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">West Virginia University</subfield>
    <subfield code="4">res</subfield>
    <subfield code="a">Jeremy Dawson</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">73869863</subfield>
    <subfield code="z">md5:b95de7b614ea22099bc4623d148d56f7</subfield>
    <subfield code="u">https://zenodo.org/record/840400/files/astorfi/lip-reading-deeplearning-1.2.zip</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2017-08-08</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">software</subfield>
    <subfield code="o">oai:zenodo.org:840400</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">West Virginia University</subfield>
    <subfield code="a">Amirsina Torfi</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">astorfi/lip-reading-deeplearning: 3D Convolutional Neural Networks for Cross Audio-Visual Matching Recognition</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">https://creativecommons.org/licenses/by/4.0/legalcode</subfield>
    <subfield code="a">Creative Commons Attribution 4.0 International</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;This project is aimed to provide the implementation for Coupled 3D Convolutional Neural Networks for audio-visual matching. Lip-reading can be a specific application for this work.&lt;/p&gt;</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">url</subfield>
    <subfield code="i">isSupplementTo</subfield>
    <subfield code="a">https://github.com/astorfi/lip-reading-deeplearning</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">arxiv</subfield>
    <subfield code="i">cites</subfield>
    <subfield code="a">arXiv:1706.05739</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">arxiv</subfield>
    <subfield code="i">cites</subfield>
    <subfield code="a">arXiv:1705.09422</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">arxiv</subfield>
    <subfield code="i">isSupplementTo</subfield>
    <subfield code="a">arXiv:1706.05739</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">doi</subfield>
    <subfield code="i">isVersionOf</subfield>
    <subfield code="a">10.5281/zenodo.836306</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.840400</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">software</subfield>
  </datafield>
</record>
1,199
74
views
downloads
All versions This version
Views 1,1991,154
Downloads 7474
Data volume 5.5 GB5.5 GB
Unique views 1,1131,074
Unique downloads 6363

Share

Cite as