Yazar "Kurnaz, Oguzhan" seçeneğine göre listele

Listeleniyor 1 - 4 / 4
  • Küçük Resim Yok
    Öğe
    Driver Drowsiness Detection using MobileNets and Long Short-term Memory
    (Institute of Electrical and Electronics Engineers Inc., 2021) Aydemir, Gürkan; Kurnaz, Oguzhan; Bekiryazıcı, Tahir; Avcı, Adem; Kocakulak, Mustafa
    Deep learning has been studied extensively for driver drowsiness detection using video data. However, since the proposed deep learning methods are computationally cumbersome, the commercial driver drowsiness detection methods are still using hand-crafted features such as lane deviation and percentage of eye closure. This study investigates a deep learning model that provides a fair drowsiness detection performance with a lightweight architecture. In the proposed method, Dlib library was used to detect the driver's face in individual frames of video data. The detected faces are fed into a pre-defined convolutional neural network architecture. Then, a long short-term memory network was used to capture the temporal information between the frame sequences to assess the state of drowsiness. The proposed model achieves a detection accuracy of 80% in a popular benchmark dataset. It was also verified that the model could be implemented on a commercial and inexpensive development board with a frame rate of 5 frames per second.
  • Küçük Resim Yok
    Öğe
    Evaluating Parameter Sharing for Spoofing-Aware Speaker Verification: A Case Study on the ASVspoof 5 Dataset
    (Isca-Int Speech Communication Assoc, 2025) Buker, Aykut; Kurnaz, Oguzhan; Bekiryazici, Yule; Demirtac, Selim Can; Hanilci, Cemal
    Spoofing-aware speaker verification (SASV) is an important but challenging task and has been a primary focus of the recently organized ASVspoof 5 challenge. As SASV integrates automatic speaker verification (ASV) and countermeasure (CM) systems, its performance depends on the effectiveness of each system. This study systematically examines the impact of different parameter-sharing (PS) strategies, which facilitate joint optimization, on SASV performance using the ASVspoof 5 dataset. Experimental results indicate that PS enhances performance for specific attack types and codec conditions. For example, the baseline system achieves a min a-DCF of 0.329 on the A26 attack, which improves to 0.233 with PS. Similarly, for AMR-compressed signals, PS yields a 14.09% performance gain. These observations show that PS techniques are effective in mitigating certain spoofing attacks and improving robustness to degraded audio conditions in SASV systems.
  • Küçük Resim Yok
    Öğe
    Investigating the Potential of Multi-Stage Score Fusion in Spoofing-Aware Speaker Verification
    (Ieee, 2025) Kurnaz, Oguzhan; Kinnunen, Tomi H.; Hanilci, Cemal
    Despite improvements in automatic speaker verification (ASV), vulnerability against spoofing attacks remains a major concern. In this study, we investigate the integration of ASV and countermeasure (CM) subsystems into a modular spoof-aware speaker verification (SASV) framework. Unlike conventional single-stage score-level fusion methods, we explore the potential of a multi-stage approach that utilizes the ASV and CM systems in multiple stages. By leveraging ECAPA-TDNN (ASV) and AASIST (CM) subsystems, we consider support vector machine and logistic regression classifiers to achieve SASV. In the second stage, we integrate their outputs with the original score to revise fusion back-end classifiers. Additionally, we incorporate another auxiliary score from RawGAT (CM) to further enhance our SASV framework. Our approach yields an equal error rate (EER) of 1.30% on the evaluation dataset of the SASV2022 challenge, representing a 24% relative improvement over the baseline system.
  • Küçük Resim Yok
    Öğe
    Optimizing a-DCF for Spoofing-Robust Speaker Verification
    (Ieee-Inst Electrical Electronics Engineers Inc, 2025) Kurnaz, Oguzhan; Mishra, Jagabandhu; Kinnunen, Tomi H.; Hanilci, Cemal
    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).