Browsing by Author "Yeşil, Fatih"

Now showing 1 - 4 of 4

Restricted
Comparison of text-independent speaker verification systems in a multi-class, semi-automatic detection scenario
(2013-06) Yeşil, Fatih; Demiroğlu, Cenk; Demiroğlu, Cenk; Aktemur, Tankut Barış; Uğurdağ, H. Fatih; Department of Electrical and Electronics Engineering; Yeşil, Fatih
Performance of the speaker veri cation systems is typically measured based on their binary decision accuracy. Soft outputs of the systems are used mostly for calibration or multiple system combination purposes. However, in speaker veri cation applications where close to 100% accuracy is required, such as the systems that are used in the call centers of nance companies, it is not possible to rely on the binary decisions of the existing veri cation systems. Still, in such cases, multi-class veri cation outputs (for example, high, medium and low veri cation score) returned by the speaker veri cation systems can be used by a human agent to either reduce the veri cation time and/or increase the veri cation accuracy compared to a human-only scenario. In this thesis, an overview of a speaker veri cation system is given explaining in detail the algorithms that are implemented. Particularly the details about a classi- er, GDA, which was rstly used by us for a veri cation purpose are given. It does relatively better job than state of the art algorithms for non-linear data like in our case. In the experiments section, some of the most popular speaker veri cation systems are compared in terms of the classical performance metric used in the literature. Then, multi-class output performance of them is compared when a human agent is assumed to be in the veri cation loop. Performance is measured by the reduction in the number of questions used by the human agent for verifying the identity of the caller without compromising the security. Experiments are performed using the NIST 2006 and 2008 databases. Eight and one conversation sides (5 minutes each) enrollment data and 1 side and 10 seconds veri cation data conditions are used.
Metadata only
Gauss karışım modeli tabanlı konuşmacı doğrulama sistemlerinde kişiye ve kanala uyarlanmada klasik MAP tabanlı yöntemlerin performans analizi
(IEEE, 2011) Koşunda, Serol; Yeşil, Fatih; Ayazoğlu, Yaprak; Demiroğlu, Cenk; Electrical & Electronics Engineering; DEMİROĞLU, Cenk; Koşunda, Serol; Yeşil, Fatih; Ayazoğlu, Yaprak
In this paper, performance of Gaussian mixture models (GMM) based algorithms implemented in Speech Processing Laboratory at Ozyegin University, within NIST SRE2004 and 2006 database was reported. Gaussian mixture models (GMM) is one of the most commonly used methods in text-independent speaker verification systems. In this paper, performance of the GMM approach has been measured with different parameters and settings. It has also been observed that eigenchannel-MAP and JFA methods both have increased the performance of the system against session variability which is one of the most challenging problem in text-independent speaker verification systems.
Metadata only
ÖZÜ konuşmacı doğrulama sisteminin çok sınıflı senaryoda NIST 2010 veritabanı ile başarımı
(IEEE, 2011) Yeşil, Fatih; Demiroğlu, Cenk; Electrical & Electronics Engineering; DEMİROĞLU, Cenk; Yeşil, Fatih
Performance of the speaker verification systems is typically measured based on their binary decision accuracy. However, in speaker verification applications where close to %100 accuracy is required, such as the systems that are used in the call centers of finance companies, it is not possible to rely on the binary decisions of the existing verification systems. Still, in such cases, multi-class verification outputs (for example, high, medium and low verification score) returned by the speaker verification systems can be used by a human agent to either reduce the verification time and/or increase the verification accuracy compared to a human-only scenario. In this work, we compare such multiclass output performance of some of the most popular speaker verification systems when a human agent is assumed to be in the verification loop. Performance is measured by the reduction in the number of questions used by the human agent for verifying the identity of the caller without compromising from the security. Experiments are performed using the NIST 2010 database for the 8 conversation sides (5 minutes each) enrollment data and 10 seconds verification data condition.
Metadata only
Performance of the OZU speaker verification systems with the NIST SRE 2010 data in a multi-class scenario
(IEEE, 2012) Yeşil, Fatih; Demiroğlu, Cenk; Electrical & Electronics Engineering; DEMİROĞLU, Cenk; Yeşil, Fatih
Konuşmacı doğrulama sistemlerinin başarımı tipik olarak ikili karar mekanizmasına dayanır. Yine de finans şirketlerinin çağrı merkezi gibi 100%’ e yakın kesinlik gerektiren uygulamalarda var olan sistemlerin ikili kararlarına güvenmek mümkün değildir. Bu tür durumlarda doğrulama sisteminin döndürdüğü düşük, orta, yüksek gibi skorlar, sadece insan olan bir çağrı merkezi senaryosuyla kıyaslandığında doğrulamanın kesinligini arttırabilir ve/veya doğrulama süresini kısaltabilir. Bu çalışmada bir temsilcinin doğrulama döngüsü içinde var olduğu düşünülerek bazı popüler konuşmacı doğrulama sistemlerinin çoklu sınıf başarımları karşılaştırılmıştır. Başarım güvenlikten ödün vermeden temsilcinin sorduğu soru sayısındaki azalmayla ölçülmüştür. Deneyler NIST 2010 veritabanı kullanarak 5er dakikalık çoklu eğitim, 5er dakikalık ve 10ar saniyelik test kayıtlarının olduğu durumlar için yapılmıştır.