Conference paper Open Access

The IWSLT 2019 KIT Speech Translation System

Pham, Ngoc-Quan; Nguyen, Thai-Son; Ha, Thanh-Le; Hussain, Juan; Schneider, Felix; Niehues, Jan; Stüker, Sebastian; Waibel, Alexander


JSON-LD (schema.org) Export

{
  "inLanguage": {
    "alternateName": "eng", 
    "@type": "Language", 
    "name": "English"
  }, 
  "description": "<p>This paper describes KIT&rsquo;s submission to the IWSLT 2019 Speech Translation task on two sub-tasks corresponding to two different datasets. We investigate different end-to-end architectures for the speech recognition module, including our new transformer-based architectures. Overall, our modules in the pipe-line are based on the transformer architecture which has recently achieved great results in various fields. In our systems, using transformer is also advantageous compared to traditional hybrid systems in term of simplicity while still having competent results.</p>", 
  "license": "https://creativecommons.org/licenses/by/4.0/legalcode", 
  "creator": [
    {
      "affiliation": "Institute for Anthropomatics and Robotics, KIT - Karlsruhe Institute of Technology, Germany", 
      "@type": "Person", 
      "name": "Pham, Ngoc-Quan"
    }, 
    {
      "affiliation": "Institute for Anthropomatics and Robotics, KIT - Karlsruhe Institute of Technology, Germany", 
      "@type": "Person", 
      "name": "Nguyen, Thai-Son"
    }, 
    {
      "affiliation": "Institute for Anthropomatics and Robotics, KIT - Karlsruhe Institute of Technology, Germany", 
      "@type": "Person", 
      "name": "Ha, Thanh-Le"
    }, 
    {
      "affiliation": "Institute for Anthropomatics and Robotics, KIT - Karlsruhe Institute of Technology, Germany", 
      "@type": "Person", 
      "name": "Hussain, Juan"
    }, 
    {
      "affiliation": "IInstitute for Anthropomatics and Robotics, KIT - Karlsruhe Institute of Technology, Germany", 
      "@type": "Person", 
      "name": "Schneider, Felix"
    }, 
    {
      "affiliation": "Department of Data Science, University of Maastricht, Netherlands", 
      "@type": "Person", 
      "name": "Niehues, Jan"
    }, 
    {
      "affiliation": "Institute for Anthropomatics and Robotics KIT - Karlsruhe Institute of Technology, Germany", 
      "@type": "Person", 
      "name": "St\u00fcker, Sebastian"
    }, 
    {
      "affiliation": "Language Technologies Institute, Carnegie Mellon University & Institute for Anthropomatics and Robotics KIT - Karlsruhe Institute of Technology, Germany", 
      "@type": "Person", 
      "name": "Waibel, Alexander"
    }
  ], 
  "headline": "The IWSLT 2019 KIT Speech Translation System", 
  "image": "https://zenodo.org/static/img/logos/zenodo-gradient-round.svg", 
  "datePublished": "2019-11-02", 
  "url": "https://zenodo.org/record/3525564", 
  "@context": "https://schema.org/", 
  "identifier": "https://doi.org/10.5281/zenodo.3525564", 
  "@id": "https://doi.org/10.5281/zenodo.3525564", 
  "@type": "ScholarlyArticle", 
  "name": "The IWSLT 2019 KIT Speech Translation System"
}
405
436
views
downloads
All versions This version
Views 405405
Downloads 436436
Data volume 101.9 MB101.9 MB
Unique views 359359
Unique downloads 392392

Share

Cite as