ASVspoof logo 

 

ASVspoof5

We need you!

Call for spoofed/speech DeepFake data contributors

if you are interested in becoming a contributor, send an email to info@asvspoof.org

Call for spoofed/speech DeepFake
data contributorsCall for spoofed/speech DeepFake data contributors

 Database creation:          ongoing
 Challenge set-up:            first half, 2023
 ASVspoof5 challenge:    second half, 2023

  • Focus on VC and TTS, including adversarial attacks (ASV/CM feedback)
  • Tentative data for creating attacks: Librispeech, LibriTTS, others (TBD) with noise/channel effects
  • As in ASVspoof 2021, attack detection from degraded-quality data
  • Both CM-only and CM+ASV tasks

 

 Those interested to learn more about ASVspoof are referred to the ASVspoof 2021 results summary paper.

 

 
List of organisers (alphabetical)

Héctor Delgado, Nuance Communications Inc., Spain
Nicholas Evans, EURECOM, France
Jeeweon Jung, Naver Corporation, South Korea
Tomi Kinnunen, University of Eastern Finland, Finland
Ivan Kukanov, Institute for Infocomm Research, Singapore
Kong Aik Lee, Institute for Infocomm Research, Singapore
Xuechen Liu, University of Eastern Finland, Finland
Hye-jin Shim, University of Eastern Finland, Finland
Md Sahidullah, Independent Researcher & Consultant, India
Hemlata Tak, EURECOM, France
Massimiliano Todisco, EURECOM, France
Xin Wang, National Institute of Informatics, Japan
Junichi Yamagishi, National Institute of Informatics, Japan

 

Funding agencies 

Academy of Finland Agence Nationale de la Recherche Japan Science and Technology Agency Agency for Science, Technology and Research