A linguistic-invariant spoofing detection method using teacher-student gradient reversal and VIB achieves up to 36.2% relative EER reduction across nine DF Arena datasets.
Enhancing multi-corpus training in ssl-based anti-spoofing models: Domain- invariant feature extraction,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Linguistic Bias Mitigation for Spoofing Detection via Gradient Reversal and A Variational Information Bottleneck
A linguistic-invariant spoofing detection method using teacher-student gradient reversal and VIB achieves up to 36.2% relative EER reduction across nine DF Arena datasets.