Browsing by Author "Hanilçi, Cemal"
Now showing items 1-20 of 20
-
ASVspoof: The Automatic Speaker Verification Spoofing and Countermeasures Challenge
Wu, Zhizheng; Yamagishi, Junichi; Kinnunen, Tomi; Hanilçi, Cemal; Sahidullah, Mohammed; Sizov, Aleksandr (Ieee-Inst Electrical Electronics Engineers Inc, 2017)Concerns regarding the vulnerability of automatic speaker verification (ASV) technology against spoofing can undermine confidence in its reliability and form a barrier to exploitation. The absence of competitive evaluations ... -
Classifiers for Synthetic Speech Detection: A Comparison
Hanilçi, Cemal; Kinnunen, Tomi; Sahidullah, Md; Sizov, Aleksandr (Isca-Int Speech Communication Assoc, 2015)Automatic speaker verification (ASV) systems are highly vulnerable against spoofing attacks, also known as imposture. With recent developments in speech synthesis and voice conversion technology, it has become important ... -
Double Compressed AMR Audio Detection Using Long-Term Features and Deep Neural Networks
Büker, Aykut; Hanilçi, Cemal (Ieee, 2019)Detecting double compressed audio files is an important problem for audio forensics applications such as audio forgery detection and determining the authenticity of an audio file appearing as an evidence. In this paper, ... -
EFFECT OF LANGUAGE MISMATCH ON TURKISH SPEAKER VERIFICATION
Hanilçi, Cemal (2017)Bu çalışmada, arkaplan verisi ile gerçekleştirme verisi arasında konuşulan dil anlamında bir uyumsuzluk olması durumunda Türkçe konuşmalar için konuşmacı tanıma performansı incelenmiştir. Gauss karışım modeli - genel ... -
AN EXPERIMENTAL STUDY ON AUDIO REPLAY ATTACK DETECTION USING DEEP NEURAL NETWORKS
Bakar, Bekir; Hanilçi, Cemal (Ieee, 2018)Automatic speaker verification (ASV) systems can be easily spoofed by previously recorded speech, synthesized speech and speech signal that artificially generated by voice conversion techniques. In order to increase the ... -
Features and Classifiers for Replay Spoofing Attack Detection
Hanilçi, Cemal (Ieee, 2017)Automatic speaker verification (ASV) systems are known to be highly vulnerable against spoofing attacks. Various successful countermeasures have recently been proposed to detect spoofing attacks originating from speech ... -
Features and Regression Techniques for Crowd Density Estimation: A Comparison
Kurnaz, Oğuzhan; Hanilçi, Cemal (Ieee, 2019)Crowd density estimation is an important problem for the security applications and it is a regression task consisting of feature extraction and regression steps. In this paper, we compare different features and regression ... -
Gauss Karışım Modeli ve Genlik Spektrumu Öznitelikleri ile Sesteki Gizli Bilginin Sezimlenmesi
Hanilçi, Cemal (2017)Son yıllarda, dijital verilerin kullanımının önemli ölçüde artması ile dijital ortam verilerinin gizli haberleşme için kullanılması oldukça yaygınlaşmıştır. Bununla birlikte, dijital verilerdeki gizli mesajın tespiti ... -
Linear prediction residual features for automatic speaker verification anti-spoofing
Hanilçi, Cemal (Springer, 2018)Automatic speaker verification (ASV) systems are highly vulnerable against spoofing attacks. Anti-spoofing, determining whether a speech signal is natural/genuine or spoofed, is very important for improving the reliability ... -
Mixture Linear Prediction in Speaker Verification Under Vocal Effort Mismatch
Pohjalainen, Jouni; Hanilçi, Cemal; Kinnunen, Tomi; Alku, Paavo (Ieee-Inst Electrical Electronics Engineers Inc, 2014)This paper describes an approach to robust signal analysis using iterative parameter re-estimation of a mixture autoregressive (AR) model. The model's focus can be adjusted by initialization of the target and non-target ... -
Replay Spoofing Attack Detection Using Deep Neural Networks
Bakar, Bekir; Hanilçi, Cemal (Ieee, 2018)In recent years, there has been increased interest in speaker verification(SV) systems and their usage has become widespread. This situation made the detecting of spoofing attacks, the discrimination of genuine speech from ... -
Source cell-phone recognition from recorded speech using non-speech segments
Hanilçi, Cemal; Kinnunen, Tomi (Academic Press Inc Elsevier Science, 2014)In a recent study, we have introduced the problem of identifying cell-phones using recorded speech and shown that speech signals convey information about the source device, making it possible to identify the source with ... -
Speaker Recognition Anti-spoofing Using Linear Prediction Residual
Hanilçi, Cemal (Ieee, 2017)Speaker recognition systems have recently proven to be highly vulnerable against spoofing attacks. Therefore, it is important to detect spoofing attacks performed by speech synthesis and voice conversion in order to improve ... -
Speaker Verification Anti-Spoofing Using Linear Prediction Residual Phase Features
Hanilçi, Cemal (Ieee, 2017)The vulnerability of automatic speaker verification (ASV) systems against spoofing attacks is an important security concern about the reliability of ASV technology. Recently, various countermeasures have been developed for ... -
Spoofing detection goes noisy: An analysis of synthetic speech detection in the presence of additive noise
Hanilçi, Cemal; Kinnunen, Tomi; Sahidullah, Md; Sizov, Aleksandr (Elsevier, 2016)Automatic speaker verification (ASV) technology is recently finding its way to end-user applications for secure access to personal data, smart services or physical facilities. Similar to other bioinatric technologies, ... -
A Study on Turkish Text - Dependent Speaker Recognition
Çeliktaş, Havva; Hanilçi, Cemal (Ieee, 2017)Speaker recognition is a pattern recognition task which has long been studied, but the accuracies are still far from the desired levels. The majority of the studies on speaker recognition demonstrates the results obtained ... -
Tomografide temel beyin tanılarının otomatik tespiti
Küplü, Serdar (Bursa Teknik Üniversitesi, 2017)Bilgisayarlı tomografi (BT) sağlık kuruluşlarının görüntüleme bölümlerinde manyetik rezonans (MR) ile beraber en sık kullanılan kesitsel tanı ünitesidir. Tomografi ve MR cihazlarının şüphe edilen hastalık türüne göre tanı ... -
Turkish Text-Dependent Speaker Verification using i-vector/PLDA Approach
Hanilçi, Cemal; Celiktas, Havva (Ieee, 2018)i-vector feature extraction is the state-of-the-art technique for text-independent speaker recognition. There exist studies in literature utilizing i-vector approach for text-dependent speaker verification. However, its ... -
Türkçe sesler ile konuşmacı kimliğinin doğrulanması/belirlenmesi
Çeliktaş, Havva (Bursa Teknik Üniversitesi, 2019)Konuşmacı tanıma sistemleri son yıllarda oldukça popüler hale gelen ancak üzerinde uzun süredir çalışılmasına rağmen hala istenilen performans başarısı elde edilmemiş bir örüntü tanıma problemidir. Konuşmacı tanıma sistemleri, ... -
Yapay sinir ağları ile konuşmacı doğrulama sistemleri için saldırı tespiti
Bakar, Bekir (Bursa Teknik Üniversitesi, 2018)Kimlik kartları, manyetik kartlar gibi geleneksel ve eski şifreleme yöntemlerinin doğurduğu bazı olumsuz sonuçlar kişi veya kurumları alternatif şifreleme yöntemleri arayışına yöneltmiştir. Bir bireyin yüz, parmak izi, ...
