ASVspoof 2021: Towards Spoofed and Deepfake Speech Detection in the Wild

ASVspoof 2021: Towards Spoofed and Deepfake Speech Detection in the Wild

IEEE/ACM Transactions on Audio, Speech, and Language Processing

10.1109/TASLP.2023.3285283

http://dx.doi.org/10.1109/taslp.2023.3285283

Xuechen Liu, Xin Wang, Md Sahidullah, Jose Patino, Hector Delgado, Tomi Kinnunen, Massimiliano Todisco, Junichi Yamagishi, Nicholas Evans, Andreas Nautsch, Kong Aik Lee

19 June 2023

Liu, X., Wang, X., Sahidullah, M., Patino, J., Delgado, H., Kinnunen, T., Todisco, M., Yamagishi, J., Evans, N., Nautsch, A., & Lee, K. A. (2023). ASVspoof 2021: Towards Spoofed and Deepfake Speech Detection in the Wild. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 31, 2507–2522. https://doi.org/10.1109/taslp.2023.3285283

Benchmarking initiatives support the meaningful comparison of competing solutions to prominent problems in speech and language processing. Successive benchmarking evaluations typically reflect a progressive evolution from ideal lab conditions towards to those encountered in the wild. ASVspoof, the spoofing and deepfake detection initiative and challenge series, has followed the same trend. This article provides a summary of the ASVspoof 2021 challenge and the results of 54 participating teams that submitted to the evaluation phase. For the logical access (LA) task, results indicate that countermeasures are robust to newly introduced encoding and transmission effects. Results for the physical access (PA) task indicate the potential to detect replay attacks in real, as opposed to simulated physical spaces, but a lack of robustness to variations between simulated and real acoustic environments. The Deepfake (DF) task, new to the 2021 edition, targets solutions to the detection of manipulated, compressed speech data posted online. While detection solutions offer some resilience to compression effects, they lack generalization across different source datasets. In addition to a summary of the top-performing systems for each task, new analyses of influential data factors and results for hidden data subsets, the article includes a review of post-challenge results, an outline of the principal challenge limitations and a road-map for the future of ASVspoof.

Publisher Copyright

This research / project is supported by the Agency for Science, Technology and Research - Council Research Fund
Grant Reference no. : CR-2021-005

This research / project is supported by the French National Research Agency & Japan Science and Technology Agency - Project VoicePersonae
Grant Reference no. : ANR-18-JSTS-0001, JPMJCR18A6

This research / project is supported by the Academy of Finland - SPEECHFAKES
Grant Reference no. : 349605

This research / project is supported by the MEXT KAKENHI - N/A
Grant Reference no. : 21K17775, 21H04906

© 2023 IEEE.  Personal use of this material is permitted.  Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

https://oar.a-star.edu.sg/communities-collections/articles/20870

2329-9290
2329-9304

Institute for Infocomm Research