Koşunda, SerolYeşil, FatihAyazoğlu, YaprakDemiroğlu, Cenk2016-02-152016-02-152011978-1-4577-0462-8http://hdl.handle.net/10679/2371https://doi.org/10.1109/SIU.2011.5929804Due to copyright restrictions, the access to the full text of this article is only available via subscription.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.turrestrictedAccessGauss karışım modeli tabanlı konuşmacı doğrulama sistemlerinde kişiye ve kanala uyarlanmada klasik MAP tabanlı yöntemlerin performans analiziPerformance analysis of classical MAP adaptation based methods in speaker and channel adaptation in GMM-based speaker verification systemsconferenceObject92893110.1109/SIU.2011.5929804Gaussian processesEigenvalues and eigenfunctionsMaximum likelihood estimationSpeaker recognition2-s2.0-79960384010