A gated fusion of speaker embeddings and spoofing scores, trained with alternating weight freezing, achieves 2.18% SASV-EER on ASVspoof2019 LA evaluation.
Title resolution pending
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
-
ATMM-SAGA: Alternating Training for Multi-Module with Score-Aware Gated Attention SASV system
A gated fusion of speaker embeddings and spoofing scores, trained with alternating weight freezing, achieves 2.18% SASV-EER on ASVspoof2019 LA evaluation.