ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection

By Junichi Yamagishi, Xin Eric Wang, Massimiliano Todisco, Md. Sahidullah, Jose Patino, Andreas Nautsch, Xuechen Liu, Kong Aik LEE, Tomi H. Kinnunen, N. Evans and 1 more. 2021 Edition of the Automatic Speaker Verification and Spoofing Countermeasures Challenge, 2021

541 citations recorded by the source corpus.

ASVspoof 2021 is the forth edition in the series of bi-annual challenges which aim to promote the study of spoofing and the design of countermeasures to protect automatic speaker verification systems from manipulation. In addition to a continued focus upon logical and physical access tasks in which there are a number of advances compared to previous editions, ASVspoof 2021 introduces a new task involving deepfake speech detection. This paper describes all three tasks, the new databases for each of them, the evaluation metrics, four challenge baselines, the evaluation platform and a summary of challenge results. Despite the introduction of channel and compression variability which compound the difficulty, results for the logical access and deepfake tasks are close to those from previous ASVspoof editions. Results for the physical access task show the difficulty in detecting attacks in real, variable physical spaces. With ASVspoof 2021 being the first edition for which participants were not provided with any matched training or development data and with this reflecting real conditions in which the nature of spoofed and deepfake speech can never be predicated with confidence, the results are extremely encouraging and demonstrate the substantial progress made in the field in recent years.

Subfields: Artificial Intelligence, Signal Processing

View Paper: https://www.semanticscholar.org/paper/3e419a95be55c9e52a549cd727d5660d9ecc38d1

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Signal Processing

Citations in the corpus

Creating, Using, Misusing, and Detecting Deep Fakes (2022, background): “In the most recent 2021 challenge (Yamagishi et al. 2021), the top-performing deep-fake audio classifier achieved an equal error rate of 15.”
ASVspoof 2021: Towards Spoofed and Deepfake Speech Detection in the Wild (2022, methodology): “TABLE V EMPIRICAL DESCRIPTION OF TOP-5 SUBMISSIONS FOR EACH TASK, AND THE BASELINE SYSTEMS (BOTTOM) [14]”
LM-VC: Zero-Shot Voice Conversion via Speech Generation Based on Language Models (2023, background): “But it may cause potential risks in misuse, such as generating fake audio impersonating a specific speaker [41].”
AASIST: Audio Anti-Spoofing Using Integrated Spectro-Temporal Graph Attention Networks (2021, background): “The ASVspoof community has led research in the ﬁeld with a series of challenges accompanied by public datasets [1–4].”
NANSY++: Unified Voice Synthesis with Neural Analysis and Synthesis (2022, background): “Recently, anti-spoofing challenges have drawn attentions from many fields because of its importance, and showed promising results on anti-spoofing for speech (Yamagishi et al., 2021).”