arXiv subjects

Cemal Hanilçi

Publications and source records attributed to Cemal Hanilçi.

4 recordsLinked to original sources

arXiv2026

Cyclostationarity Analysis as a Complement to Self-Supervised Representations for Speech Deepfake Detection

Speech deepfake detection (SDD) is essential for maintaining trust in voice-driven technologies and digital media. Although recent SDD systems increasingly rely on SSL representations that capture rich contextual information, complementary signal-driven acoustic features remain important for modeling fine-grained structural properties of speech. Most existing acoustic front ends are based on time-frequency representations, which do not fully exploit higher-order spectral dependencies inherent in speech signals. We introduce a cyclostationarity-inspired acoustic feature extraction framework for SDD based on spectral correlation density (SCD). The proposed features model periodic statistical structures in speech by capturing spectral correlations between frequency components. In particular, we investigate whether cyclostationary representations provide complementary information beyond conventional time-frequency features and modern SSL embeddings. To this end, we introduce temporally structured SCD representations that preserve the evolution of spectral and cyclic-frequency correlations over time. Their effectiveness is evaluated using multiple SDD architectures, including conventional neural networks, SSL-based embedding systems, and hybrid fusion models. Experiments on ASVspoof 2019 LA, 2021 DF, and ASVspoof 5 demonstrate that higher-order spectral correlations provide complementary information to SSL embeddings in several challenging conditions. In particular, fusion of SSL and SCD embeddings reduces the equal error rate on ASVspoof 2019 LA from 8.28% to 0.98%, and from 15.81% to 14.80% on the challenging ASVspoof 5 dataset. These findings establish higher-order cyclostationary spectral correlations as a complementary source of information for modern SDD, while providing new signal-processing insight into the statistical differences between natural and synthetic speech.

eess.AS↗

arXiv2026

Joint Optimization of Speaker and Spoof Detectors for Spoofing-Robust Automatic Speaker Verification

Spoofing-robust speaker verification (SASV) combines the tasks of speaker and spoof detection to authenticate speakers under adversarial settings. Many SASV systems rely on fusion of speaker and spoof cues at embedding, score or decision levels, based on independently trained subsystems. In this study, we respect similar modularity of the two subsystems, by integrating their outputs using trainable back-end classifiers. In particular, we explore various approaches for directly optimizing the back-end for the recently-proposed SASV performance metric (a-DCF) as a training objective. Our experiments on the ASVspoof 5 dataset demonstrate two important findings: (i) nonlinear score fusion consistently improves a-DCF over linear fusion, and (ii) the combination of weighted cosine scoring for speaker detection with SSL-AASIST for spoof detection achieves state-of-the-art performance, reducing min a-DCF to 0.196 and SPF-EER to 7.6%. These contributions highlight the importance of modular design, calibrated integration, and task-aligned optimization for advancing robust and interpretable SASV systems.

eess.AS↗

arXiv2025

Optimizing a-DCF for Spoofing-Robust Speaker Verification

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 $0.0289$).

eess.AS↗

arXiv2024

Spoofing-Robust Speaker Verification Using Parallel Embedding Fusion: BTU Speech Group's Approach for ASVspoof5 Challenge

This paper introduces the parallel network-based spoofing-aware speaker verification (SASV) system developed by BTU Speech Group for the ASVspoof5 Challenge. The SASV system integrates ASV and CM systems to enhance security against spoofing attacks. Our approach employs score and embedding fusion from ASV models (ECAPA-TDNN, WavLM) and CM models (AASIST). The fused embeddings are processed using a simple DNN structure, optimizing model performance with a combination of recently proposed a-DCF and BCE losses. We introduce a novel parallel network structure where two identical DNNs, fed with different inputs, independently process embeddings and produce SASV scores. The final SASV probability is derived by averaging these scores, enhancing robustness and accuracy. Experimental results demonstrate that the proposed parallel DNN structure outperforms traditional single DNN methods, offering a more reliable and secure speaker verification system against spoofing attacks.

eess.AS↗