ASVspoof 5
PulseAugur coverage of ASVspoof 5 — every cluster mentioning ASVspoof 5 across labs, papers, and developer communities, ranked by signal.
-
New method explains deepfake speech detector decisions
Researchers have developed a new method to understand how deepfake speech detectors make their decisions. By using Integrated Gradients on self-supervised representations, the technique can pinpoint specific moments in …
-
New RAT training method improves deepfake audio detection
Researchers have developed a new training strategy called Reference-Augmented Training (RAT) to improve the detection of audio deepfakes. While initially designed to use speaker reference recordings, the method surprisi…
-
Voice spoofing detection models need language-specific adaptation
Researchers have benchmarked self-supervised learning feature extractors and classifiers for voice spoofing detection, finding that simple data scaling can degrade performance on the ASVspoof 5 dataset due to domain bia…