ASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detection

ASVspoof, now in its third edition, is a series of community-led challenges\nwhich promote the development of countermeasures to protect automatic speaker\nverification (ASV) from the threat of spoofing. Advances in the 2019 edition\ninclude: (i) a consideration of both logical access (LA) and physical access\n(PA) scenarios and the three major forms of spoofing attack, namely synthetic,\nconverted and replayed speech; (ii) spoofing attacks generated with\nstate-of-the-art neural acoustic and waveform models; (iii) an improved,\ncontrolled simulation of replay attacks; (iv) use of the tandem detection cost\nfunction (t-DCF) that reflects the impact of both spoofing and countermeasures\nupon ASV reliability.…

• N
  Nvidia
• IY
  Itä-Suomen Yliopisto
• AN
  Agence Nationale de la Recherche
• MO
  Ministry of Education, Culture, Sports, Science and Technology

  Awards: 18H04112, 17H04687, 16H06302, 18H04120, 18KT0051, CREST, 16K16096
• CS
  China Scholarship Council
• JS
  Japan Society for the Promotion of Science

  Awards: 16K16096, JPMJCR18A6, 18H04120, 18H04112, CREST, 16H06302, 17H04687, 18KT0051
• CR
  Core Research for Evolutional Science and Technology

  Award: JPMJCR18A6