Published December 18, 2024 | Version v0.1
Dataset Open

ASVspoof 5: Design, Collection and Validation of Resources for Spoofing, Deepfake, and Adversarial Attack Detection Using Crowdsourced Speech

  • 1. ROR icon National Institute of Informatics
  • 2. Nuance Communications Inc
  • 3. Pindrop
  • 4. Apple
  • 5. ROR icon Carnegie Mellon University
  • 6. ROR icon EURECOM
  • 7. KLASS
  • 8. ROR icon TCG Crest
  • 9. ROR icon University of Eastern Finland
  • 10. The Hong Kong Polytechnic University
  • 11. ROR icon Seoul National University
  • 12. ROR icon University of Rochester
  • 13. ROR icon University of Stuttgart
  • 14. ROR icon Fraunhofer Institute for Applied and Integrated Security
  • 15. ROR icon Shanghai Jiao Tong University
  • 16. EDMO icon University at Buffalo
  • 17. ROR icon University of Helsinki
  • 18. ROR icon Tianjin University
  • 19. ROR icon University of Science and Technology of China

Description

 

This is the Zenodo repository for the ASVspoof 5 database. ASVspoof 5 is the fifth edition in a series of challenges which promote the study of speech spoofing and deepfake attacks, and the design of detection solutions. Compared to previous challenges, the ASVspoof~5 database is built from crowdsourced data collected from around 2,000 speakers in diverse acoustic conditions.  More than 20 attacks, also crowdsourced, are generated and optionally tested using surrogate detection models, while seven adversarial attacks are incorporated for the first time.

  • Please check README.txt and LICENSE.txt before downloading the database.
  • It is highly recommended to follow the rules and instructions in the ASVspoof 5 challenge evaluation plan (phase 2, https://www.asvspoof.org/), if you want to produce results comparable with the literature. 
  • Please consider citing the reference listed at the bottom of this page.
  • Latest work using the ASVspoof 5 database can be found in the Automatic Speaker Verification Spoofing Countermeasures Workshop proceeding: https://www.isca-archive.org/asvspoof_2024/index.html
  • If you are interested in creating spoofed data for research purpose using the ASVspoof 5 protocol, please send request to info@asvspoof.org

Files

LICENSE.txt

Files (142.3 GB)

Name Size Download all
md5:865d0e894ea9f686f0f37e5ae3ae3616
20.7 MB Download
md5:df0be44957623991028cce59792beb17
6.6 GB Download
md5:1e8cd685d89b64502692f1bcf1a13db3
6.6 GB Download
md5:5e0031f08c30e4bdbf0c59f91b2d662b
6.8 GB Download
md5:a8c800766f3d4ef87971e2b4f29663e2
8.4 GB Download
md5:c35064188f54f07c87aba58de22534a0
8.5 GB Download
md5:ed7cbcd1b2847998b72472ddf6b445e3
8.5 GB Download
md5:626a080e994b05df49c577d7b3dede8d
8.5 GB Download
md5:05f19a5e64fa556714ae1b38eb2ea70b
8.5 GB Download
md5:2ca2f52a3bbf827f7ec155ecb47e85d6
8.5 GB Download
md5:671200b5de2fc1e74a563b07b057af8f
8.5 GB Download
md5:eaf885b1299a61eb07f71e82e96dba37
8.5 GB Download
md5:b2625683bf440abae2af901a45542ad9
8.5 GB Download
md5:c50281c8233af6f3b0899604d21ade44
8.6 GB Download
md5:b0cc86b14826a7701b52aad4f53daf9c
7.5 GB Download
md5:d05be3f4be7a343fdbdd0ed29fdff2e1
7.5 GB Download
md5:70d1ba4ad75a20aef3dae541fbd321e3
7.5 GB Download
md5:c9bb56af2cc410d98338d74babcb95c9
7.5 GB Download
md5:a3969816982f3e52300d6147ad796df7
7.5 GB Download
md5:9cbefc63251e8cbc8eb22e62cd6fe584
19.9 kB Preview Download
md5:784002b8449ba1eeecc042bfad285de7
12.1 kB Preview Download

Additional details

Funding

Japan Science and Technology Agency
PRESTO JPMJPR23P9
Research Council of Finland
SPEECHFAKES 349605
Agence Nationale de la Recherche
BRUEL ANR-22-CE39-0009
Agence Nationale de la Recherche
COMPROMIS ANR22-PECY-0011

Dates

Available
2024-12

References

  • Xin Wang, Héctor Delgado, Hemlata Tak, Jee-weon Jung, Hye-jin Shim, Massimiliano Todisco, Ivan Kukanov, Xuechen Liu, Md Sahidullah, Tomi Kinnunen, Nicholas Evans, Kong Aik Lee, Junichi Yamagishi, Myeonghun Jeong, Ge Zhu, Yongyi Zang, You Zhang, Soumi Maiti, Florian Lux, Nicolas Müller, Wangyou Zhang, Chengzhe Sun, Shuwei Hou, Siwei Lyu, Sébastien Le Maguer, Cheng Gong, Hanjie Guo, Liping Chen, and Vishwanath Singh. 2024. ASVspoof 5: Design, Collection and Validation of Resources for Spoofing, Deepfake, and Adversarial Attack Detection Using Crowdsourced Speech. To be submmited (2024).
  • Xin Wang, Héctor Delgado, Hemlata Tak, Jee-weon Jung, Hye-jin Shim, Massimiliano Todisco, Ivan Kukanov, Xuechen Liu, Md Sahidullah, Tomi Kinnunen, Nicholas Evans, Kong Aik Lee, and Junichi Yamagishi. 2024. ASVspoof 5: Crowdsourced speech data, deepfakes, and adversarial attacks at scale. In ASVspoof Workshop 2024, 2024. 1--8. https://doi.org/10.21437/ASVspoof.2024-1