Software Open Access

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

Amirsina Torfi


DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.1/metadata.xsd">
  <identifier identifierType="DOI">10.5281/zenodo.840400</identifier>
  <creators>
    <creator>
      <creatorName>Amirsina Torfi</creatorName>
      <affiliation>West Virginia University</affiliation>
    </creator>
  </creators>
  <titles>
    <title>astorfi/lip-reading-deeplearning: 3D Convolutional Neural Networks for Cross Audio-Visual Matching Recognition</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2017</publicationYear>
  <subjects>
    <subject>speech recognition</subject>
    <subject>lip reading</subject>
    <subject>deep learning</subject>
  </subjects>
  <dates>
    <date dateType="Issued">2017-08-08</date>
  </dates>
  <resourceType resourceTypeGeneral="Software"/>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/840400</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsSupplementTo">https://github.com/astorfi/lip-reading-deeplearning</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="arXiv" relationType="Cites">arXiv:1706.05739</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="arXiv" relationType="Cites">arXiv:1705.09422</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="arXiv" relationType="IsSupplementTo">arXiv:1706.05739</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.836306</relatedIdentifier>
  </relatedIdentifiers>
  <rightsList>
    <rights rightsURI="https://creativecommons.org/licenses/by/4.0/legalcode">Creative Commons Attribution 4.0 International</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">&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;</description>
    <description descriptionType="Other">{"references": ["Torfi et al. (2017). Source code is associated to arXiv:1706.05739."]}</description>
  </descriptions>
</resource>
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