Video/Audio Open Access

ASVspoof 2021 Challenge - Physical 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


JSON-LD (schema.org) Export

{
  "description": "<p>The automatic speaker verification spoofing and countermeasures (ASVspoof) challenge series is a&nbsp;community-led initiative which aims to promote the consideration of spoofing and the development of&nbsp;countermeasures. &nbsp;ASVspoof 2021 is the 4th in a series of bi-annual, competitive challenges where the&nbsp;goal is to develop countermeasures capable of discriminating between bona fide and spoofed or deepfake&nbsp;speech.&nbsp;<br>\n<br>\nASVspoof 2021 comprises three different tasks: &nbsp; &nbsp;<br>\n<em>&nbsp;Logical access (LA)</em>: bona fide and spoofed utterances generated using text-to-speech (TTS) and voice&nbsp;conversion (VC) algorithms are communicated across telephony and VoIP networks with various coding&nbsp;and transmission effects;<br>\n&nbsp; &nbsp;&nbsp;<br>\n<em>Physical access (PA)</em>: bona fide utterances are made in a real, physical space in which spoofing attacks&nbsp;are captured and then replayed within the same physical space using replay devices of varying quality;<br>\n&nbsp; &nbsp;&nbsp;<br>\n<em>Speech deepfake (DF)</em>: a fake audio detection task comprising bona fide and spoofed utterances&nbsp;generated using TTS and VC algorithms. Similar to the LA task (includes compressed data) but without&nbsp;speaker verification.<br>\n<br>\n<strong>This repository provides the evaluation set for the PA task.</strong><br>\n<br>\nFor more details, please visit our website below. https://www.asvspoof.org</p>", 
  "license": "https://opendatacommons.org/licenses/by/1.0/", 
  "creator": [
    {
      "affiliation": "Nuance Communications Inc., Spain", 
      "@type": "Person", 
      "name": "Delgado, H\u00e9ctor"
    }, 
    {
      "affiliation": "EURECOM, France", 
      "@type": "Person", 
      "name": "Evans, Nicholas"
    }, 
    {
      "affiliation": "University of Eastern Finland, Finland", 
      "@type": "Person", 
      "name": "Kinnunen, Tomi"
    }, 
    {
      "affiliation": "Institute for Infocomm Research, Singapore", 
      "@type": "Person", 
      "name": "Lee, Kong Aik"
    }, 
    {
      "affiliation": "University of Eastern Finland, Finland", 
      "@type": "Person", 
      "name": "Liu, Xuechen"
    }, 
    {
      "affiliation": "EURECOM, France", 
      "@type": "Person", 
      "name": "Nautsch, Andreas"
    }, 
    {
      "affiliation": "EURECOM, France", 
      "@type": "Person", 
      "name": "Patino, Jose"
    }, 
    {
      "affiliation": "Inria, France", 
      "@type": "Person", 
      "name": "Sahidullah, Md"
    }, 
    {
      "affiliation": "EURECOM, France", 
      "@type": "Person", 
      "name": "Todisco, Massimiliano"
    }, 
    {
      "affiliation": "National Institute of Informatics, Japan", 
      "@type": "Person", 
      "name": "Wang, Xin"
    }, 
    {
      "affiliation": "National Institute of Informatics, Japan", 
      "@type": "Person", 
      "name": "Yamagishi, Junichi"
    }
  ], 
  "url": "https://zenodo.org/record/4834716", 
  "datePublished": "2021-05-28", 
  "version": "1.0", 
  "keywords": [
    "Speaker recognition", 
    "Speaker verification", 
    "ASVspoof", 
    "Anti-spoofing", 
    "Presentation attack detection", 
    "Deepfake detection"
  ], 
  "@context": "https://schema.org/", 
  "identifier": "https://doi.org/10.5281/zenodo.4834716", 
  "@id": "https://doi.org/10.5281/zenodo.4834716", 
  "@type": "MediaObject", 
  "name": "ASVspoof 2021 Challenge - Physical Access Database"
}
968
1,515
views
downloads
All versions This version
Views 968968
Downloads 1,5151,515
Data volume 9.9 TB9.9 TB
Unique views 893893
Unique downloads 682682

Share

Cite as