Speaker recognition is the process of automatically recognizing who is speaking on the basis of speaker specific characteristics included in the speech signal. These speaker specific characteristics are called features. Over the past decades, extensive research has been carried out on various possible speech signal features obtained from signal in time or frequency domain. The objective of this paper is to introduce two-dimensional information entropy as a new text-independent speaker recognition feature. Computations are performed in time domain with real numbers exclusively. Experimental results show that the two-dimensional information entropy is a speaker specific characteristic, useful for speaker recognition.
Sadržaj -Virtualne privatne mreže (VPN) su stekle veliku popularnost u proteklih nekoliko godina zbog toga što omogu avaju sigurno povezivanje po niskoj ceni. Remote-Access IPsec VPN topologija omogu ava uspostavu sigurnog tunela od ra unara sa VPN klijentskim softverom do VPN gateway ure aja. Ovo rešenje naj eš e koriste zaposleni koji se nalaze van prostorija kompanije za bezbedan pristup kompanijskoj mreži. Od komercijalnih rešenja za VPN klijentski softver uglavnom su u ponudi rešenja za Microsoft Windows operativne sisteme, što znatno limitira upotrebu ove tehnologije za korisnike Linux platforme. U okviru ovog rada realizovana je integracija strongSwan klijenta (IPsec rešenje za Linux u slobodnom vlasništvu) sa jednom od najzastupljenijih IPsec implementacija za mrežne ure aje na tržištu, Cisco IOS IPsec platformom. Nakon toga, izvršena je eksperimentalna analiza najbitnijih performansi VPN konekcije, kako bi se odredio uticaj IPsec tunela na kvalitet konekcije. Performanse koje su analizirane su protok TCP i UDP paketa, Round-trip time (RTT), jitter i procenat izgubljenih paketa.Klju ne re i -IPsec, jitter, procenat izgubljenih paketa, protok, Remote-Access VPN, RTT.Ana An eli (autor za kontakte), Vlatacom, d.o.o.,
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.