Joint Optimization of ASV and CM tasks: BTUEF Team's Submission for WildSpoof Challenge

TL;DR

This paper presents a modular framework for spoofing-aware speaker verification that effectively combines ASV and CM systems, optimizing their interaction to improve robustness against spoofing attacks.

Contribution

It introduces a novel non-linear fusion framework with trainable loss functions that explicitly models the interaction between ASV and CM components.

Findings

Best results achieved with ReDimNet-based ASV and fine-tuned SSL-AASIST.

Significant reduction in a-DCF scores on evaluation datasets.

Framework enables effective reuse and optimization of existing systems.

Abstract

Spoofing-aware speaker verification (SASV) jointly addresses automatic speaker verification and spoofing countermeasures to improve robustness against adversarial attacks. In this paper, we investigate our recently proposed modular SASV framework that enables effective reuse of publicly available ASV and CM systems through non-linear fusion, explicitly modeling their interaction, and optimization with an operating-condition-dependent trainable a-DCF loss. The framework is evaluated using ECAPA-TDNN and ReDimNet as ASV embedding extractors and SSL-AASIST as the CM model, with experiments conducted both with and without fine-tuning on the WildSpoof SASV training data. Results show that the best performance is achieved by combining ReDimNet-based ASV embeddings with fine-tuned SSL-AASIST representations, yielding an a-DCF of 0.0515 on the progress evaluation set and 0.2163 on the final evaluation set.