Optimizing A-dcf For Spoofing-robust Speaker Verification

Abstract

Automatic speaker verification (ASV) systems are vulnerable to spoofing attacks. We propose a spoofing-robust ASV system optimized directly for the recently introduced architecture-agnostic detection cost function (a-DCF), which allows targeting a desired trade-off between the contradicting aims of user convenience and robustness to spoofing. We combine a-DCF and binary cross-entropy (BCE) with a novel straightforward threshold optimization technique. Our results with an embedding fusion system on ASVspoof2019 data demonstrate relative improvement of \(13%\) over a system trained using BCE only (from minimum a-DCF of \(0.1445\) to \(0.1254\)). Using an alternative non-linear score fusion approach provides relative improvement of \(43%\) (from minimum a-DCF of \(0.0508\) to \(0.0289\)).

Stats

• citations2
• S2 citations—
• github stars0
• HF likes0
• heat score3.58
• arxiv keykurnaz2024optimizing

Related papers

• Joint Optimization Of Speaker And Spoof Detectors For Spoofing-robust Automatic Speaker Verification (2025)0.00
• Baseline Systems For The First Spoofing-aware Speaker Verification Challenge: Score And Embedding Fusion (2022)6.77
• Spoofing-robust Speaker Verification Using Parallel Embedding Fusion: BTU Speech Group's Approach For Asvspoof5 Challenge (2024)5.24
• Generalizing Speaker Verification For Spoof Awareness In The Embedding Space (2024)7.16
• Toward Improving Synthetic Audio Spoofing Detection Robustness Via Meta-learning And Disentangled Training With Adversarial Examples (2024)6.77
• Anti-spoofing Methods For Automatic Speakerverification System (2017)2.26
• Spoofing-aware Attention Based ASV Back-end With Multiple Enrollment Utterances And A Sampling Strategy For The SASV Challenge 2022 (2022)4.52
• Representation Selective Self-distillation And Wav2vec 2.0 Feature Exploration For Spoof-aware Speaker Verification (2022)9.03