Browsing by Author "Demiroğlu, Cenk"
Now showing items 61-79 of 79
-
SAS : A speaker verification spoofing database containing diverse attacks
Wu, Z.; Khodabakhsh, Ali; Demiroğlu, Cenk; Yamagishi, J.; Saito, D.; Toda, T.; King, S. (IEEE, 2015)This paper presents the first version of a speaker verification spoofing and anti-spoofing database, named SAS corpus. The corpus includes nine spoofing techniques, two of which are speech synthesis, and seven are voice ... -
Sesli̇ yanıt si̇stemi̇ çaǧrı akışında di̇lbi̇lgi̇si̇ tabanlı Türkçe konuşma tanıma si̇stemi̇ tanıtımı
Karagöz, Gün; Demiroğlu, Cenk (IEEE, 2012)Bu bildiride, çağrı merkezleri için kullanılan sesli yanıt sisteminde dilbilgisi-tabanlı Türkçe konuşma tanıma sistemi anlatılmaktadır. Yapılan çalışmada bir telekomünikasyon kurumunun çağrı merkezi sisteminin örneklemesi ... -
A small footprint hybrid statistical and unit selection text-to-speech synthesis system for Turkish
Güner, Ekrem; Demiroğlu, Cenk (Springer Science+Business Media, 2012)Unit selection based text-to-speech synthesis (TTS) can generate high quality speech. However, The HMM-based text-to-speech (HTS) has also advantages such as the lack of spurious errors that are observed in the unit selection ... -
A small footprint hybrid statistical/unit selection text-to-speech synthesis system for agglutinative languages
Güner, Ekrem; Demiroğlu, Cenk (IEEE, 2012)Despite its success, unit selection based text-to-speech synthesis (TTS) has has some disadvantages such as sudden discontinuities in speech that distract the listeners. The HMM-based TTS (HTS) approach has been increasingly ... -
Speaker adaptation with deep learning for text-to-speech synthesis systems
End-to-end (e2e) speech synthesis systems have become popular with the recent introduction of letter-to-spectrogram conversion systems, such as Tacotron, that use encoder-decoder-based neural architectures. Even though ... -
Speaker adaptation with minimal data in statistical speech synthesis systems
Mohammadi, Amir (2014-09)Statistical speech synthesis (SSS) systems have the ability to adapt to a target speaker with a couple of minutes of adaptation data. Developing adaptation algorithms to further reduce the number of adaptation utterances ... -
Spoofing and anti-spoofing techniques for text-independent speaker verification systems
Khodabakhsh, Ali (2015-10)There has been substantial progress in the speaker verification field in recent years. I-vector based approach in particular received significant attention due to its high performance. Improvements in the verification ... -
Spoofing attacks to i-vector based voice verification systems using statistical speech synthesis with additive noise and countermeasure
Özbay, Mustafa Caner; Khodabakhsh, Ali; Mohammadi, Amir; Demiroğlu, Cenk (IEEE, 2016)Even though improvements in the speaker verification (SV) technology with i-vectors increased their real-life deployment, their vulnerability to spoofing attacks is a major concern. Here, we investigated the effectiveness ... -
Spoofing voice verification systems with statistical speech synthesis using limited adaptation data
Khodabakhsh, Ali; Mohammadi, Amir; Demiroğlu, Cenk (Elsevier, 2017-03)State-of-the-art speaker verification systems are vulnerable to spoofing attacks using speech synthesis. To solve the issue, high-performance synthetic speech detectors (SSDs) for attack methods have been proposed recently. ... -
Standard-compliant and software defined VLC system: implementation and performance evaluation
Hussain, Waqas (2015-08)LED lighting is now a cost-effective and energy-efficient technology for general-purpose illumination. Recent advances in LED lighting allow us to use LEDs not only for illumination but at the same time for wireless ... -
State of charge estimation for lithium-based batteries
Çelik, Mert (2020-01)This thesis proposes a new State of Charge (SOC) estimation method for lithiumbased batteries, which o ers a good trade-o between convergence and computation times. Lithium-based battery packages are quite common in the ... -
Thermal and optical interaction of tightly packaged LEDs in automotive lighting applications
Uras, Umut Zeynep (2018-11-20)This study aims to enhance the thermal management of an LED light engine for automotive exterior lighting with an advanced heat spreader. Although LEDs have many advantages, their applications require an accurate thermal ... -
Uncertainty assessment for detection of spoofing attacks to speaker verification systems using a Bayesian approach
Süslü, Çağıl; Eren, Eray; Demiroğlu, Cenk (Elsevier, 2022-02)There has been tremendous progress in automatic speaker verification systems over the last decade. Still, spoofing attacks pose a significant challenge to their deployment. Even though there are various attack techniques ... -
Uncertainty assessment for speaker verification systems using a bayesian approach
Süslü, Çağıl (2021-01-18)The Automatic Speaker Verification (ASV) systems are developed to discriminate the genuine speakers from the spoofing attacks and they are also used as a security application in various industries (e.g., Banking and ... -
Using eigenvoices and nearest-neighbors in HMM-based cross-lingual speaker adaptation with limited data
Sarfjoo, Seyyed Saeed; Demiroğlu, Cenk; King, S. (IEEE, 2017-04)Cross-lingual speaker adaptation for speech synthesis has many applications, such as use in speech-to-speech translation systems. Here, we focus on cross-lingual adaptation for statistical speech synthesis systems using ... -
Using eigenvoices and nearest-neighbours in HMM-based cross-lingual speaker adaptation with limited data
Sarfjoo, Seyyed Saeed (2017-08)Thesis abstract: Cross-lingual speaker adaptation for speech synthesis has many applications, such as use in speech-to-speech translation systems. Here, we focus on cross-lingual adaptation for statistical speech synthesis ... -
Visible light communications with advanced physical layer features and integration with existing wireless communication technologies
Optical wireless communication systems that operate in the visible light frequency band (390-700 nm) are called as visible light communication (VLC). VLC systems are based on the principle of modulating light emitting ... -
Vulnerability of speaker verification system under replay spoofing attack and investigation of synthetic speech detection
Özbay, Mustafa Caner (2016-05)Security issues have become major subject along with developments in the speaker verification system. Previous studies have shown that performance is still not fully proven for vulnerability. Simple and easy methods may ... -
Vurgu ve söyleyiş modelleme hatalarının SMM tabanlı Türkçe MKS sistemindeki etkileri
Güner, Ekrem; Demiroğlu, Cenk (IEEE, 2011)SMM tabanlı metinden konuşma sentezleme (SMM-MKS) yöntemi, gün geçtikçe daha 1 fazla araştırmacısının ilgisini çekmektedir. Bu yöntemin en önemli avantajlarından biri, birim seçmeli sistemlerde görülen bozulma etkilerinin ...
Share this page