Title :
An advanced channel compensation method for speaker recognition
Author :
Imamverdiyev, Yadigar ; Sukhostat, Lyudmila
Author_Institution :
Inst. of Inf. Technol., Baku, Azerbaijan
Abstract :
This paper discusses various methods for channel compensation to effectively reduce errors in speech data transmitted through different channels in order to increase the accuracy of speaker recognition system. The aim of this paper is to analyze and evaluate the channel distortions and noise effects on speech. Methods used for channel equalization and compensation in order to improve the efficiency of speaker verification and identification systems over various communication channels are described. A scalable approach for probabilistic linear discriminant analysis for speaker recognition is presented.
Keywords :
channel estimation; distortion; probability; speaker recognition; advanced channel compensation method; channel distortions; channel equalization; communication channels; identification systems; noise effects; probabilistic linear discriminant analysis; speaker recognition; speaker verification; speech data; Acoustic distortion; Acoustics; Speaker recognition; Speech; Speech processing; Speech recognition; Training; Speaker recognition; channel compensation; i-vector; probabilistic linear discriminant analysis;
Conference_Titel :
Application of Information and Communication Technologies (AICT), 2013 7th International Conference on
Conference_Location :
Baku
Print_ISBN :
978-1-4673-6419-5
DOI :
10.1109/ICAICT.2013.6722705
