A variational Bayesian version of weighted relaxed instance frequency-wise normalization (BWRFN) improves reported speaker verification and anti-spoofing performance under domain mismatch.
Evaluation Tasks The experiments were conducted on cross-dataset ASV tasks, anti-spoofing tasks, and spoofing-robust automatic speaker ver- ification (SASV) tasks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Bayesian Learning for Domain-Invariant Speaker Verification and Anti-Spoofing
A variational Bayesian version of weighted relaxed instance frequency-wise normalization (BWRFN) improves reported speaker verification and anti-spoofing performance under domain mismatch.