ASVspoof 2021: Towards Spoofed and Deepfake Speech Detection in the Wild
Centre National de la Recherche Scientifique · University of Eastern Finland · +6 more institutions
Abstract
Benchmarkinginitiatives 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…
Citation impact
- FWCI
- 40.50
- Percentile
- 100%
- References
- 60
Authors
11- XLXuechen LiuCorresponding
Centre National de la Recherche Scientifique, University of Eastern Finland, National Institute of Informatics, Laboratoire Lorrain de Recherche en Informatique et ses Applications, Université de Lorraine
- XWXin Wang
National Institute of Informatics
- MSMd Sahidullah
Centre National de la Recherche Scientifique, Laboratoire Lorrain de Recherche en Informatique et ses Applications, Université de Lorraine
- JPJosé Patino
EURECOM
- HDHéctor Delgado
Topics & keywords
- Spoofing attack
- Computer science
- Speech recognition
- Computer security
- Peace, Justice and strong institutions