Software Open Access

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

Amirsina Torfi


JSON-LD (schema.org) Export

{
  "description": "<p>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.</p>", 
  "license": "https://creativecommons.org/licenses/by/4.0/legalcode", 
  "creator": [
    {
      "affiliation": "West Virginia University", 
      "@type": "Person", 
      "name": "Amirsina Torfi"
    }
  ], 
  "url": "https://zenodo.org/record/840400", 
  "codeRepository": "https://github.com/astorfi/lip-reading-deeplearning", 
  "citation": [
    {
      "@id": "https://arxiv.org/abs/arXiv:1706.05739", 
      "@type": "CreativeWork"
    }, 
    {
      "@id": "https://arxiv.org/abs/arXiv:1705.09422", 
      "@type": "CreativeWork"
    }
  ], 
  "datePublished": "2017-08-08", 
  "keywords": [
    "speech recognition", 
    "lip reading", 
    "deep learning"
  ], 
  "contributor": [
    {
      "affiliation": "West Virginia University", 
      "@type": "Person", 
      "name": "Amirsina Torfi"
    }, 
    {
      "affiliation": "West Virginia University", 
      "@type": "Person", 
      "name": "Seyed Mehdi Iranmanesh"
    }, 
    {
      "affiliation": "West Virginia University", 
      "@type": "Person", 
      "name": "Nasser Nasrabadi"
    }, 
    {
      "affiliation": "West Virginia University", 
      "@type": "Person", 
      "name": "Jeremy Dawson"
    }
  ], 
  "@context": "https://schema.org/", 
  "identifier": "https://doi.org/10.5281/zenodo.840400", 
  "@id": "https://doi.org/10.5281/zenodo.840400", 
  "@type": "SoftwareSourceCode", 
  "name": "astorfi/lip-reading-deeplearning: 3D Convolutional Neural Networks for Cross Audio-Visual Matching Recognition"
}
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