8502

High Dimensional Spaces and Modelling in the task of Speaker Recognition

Lukas Machlica
University of West Bohemia, Faculty of Applied Sciences, Department of Cybernetics, Univerzitni 8, Pilsen, Czech Republic
University of West Bohemia, 2012

@phdthesis{LukasMachlica_2012_HighDimensional,

   author={Luk'{a}v{s} Machlica},

   title={High Dimensional Spaces and Modelling in the task of Speaker Recognition},

   year={2012},

   address={Univerzitni 8, Pilsen, Czech Republic},

   school={University of West Bohemia, Faculty of Applied Sciences, Department of Cybernetics},

   url={http://www.kky.zcu.cz/en/publications/LukasMachlica_2012_HighDimensional}

}

Download Download (PDF)   View View   Source Source   

759

views

The automatic speaker recognition made a significant progress in the last two decades. Huge speech corpora containing thousands of speakers recorded on several channels are at hand, and methods utilizing as much information as possible were developed. Nowadays state-of-the-art methods are based on Gaussian mixture models used to estimate relevant statistics from feature vectors extracted from the speech of a speaker, which are further concatenated into a high dimensional vector – supervector. Methods concerning the extraction of high dimensional supervectors along with techniques capable to build a speaker model in such a high dimensional space are described in depth and links between these methods are found. The main emphasize is laid on the analysis of these methods and an efficient implementation in order to process huge amounts of development data to train the speaker recognition system. Also the influence of development corpora on the recognition performance is experimentally tested.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2017 hgpu.org

All rights belong to the respective authors

Contact us: