Comparison of scoring methods used in speaker recognition with Joint Factor Analysis

2009 ◽  
Author(s):  
Ondrej Glembek ◽  
Lukas Burget ◽  
Najim Dehak ◽  
Niko Brummer ◽  
Patrick Kenny
Keyword(s):  
Factor Analysis ◽  
Speaker Recognition ◽  
Scoring Methods ◽  
Joint Factor ◽  
Joint Factor Analysis

Joint Factor Analysis Versus Eigenchannels in Speaker Recognition

2007 ◽  
Vol 15 (4) ◽  
pp. 1435-1447 ◽  
Author(s):  
Patrick Kenny ◽  
Gilles Boulianne ◽  
Pierre Ouellet ◽  
Pierre Dumouchel
Keyword(s):  
Factor Analysis ◽  
Speaker Recognition ◽  
Joint Factor ◽  
Joint Factor Analysis

Investigation into variants of joint factor analysis for speaker recognition

2009 ◽  
Author(s):  
Lukáš Burget ◽  
Pavel Matějka ◽  
Valiantsina Hubeika ◽  
Jan Černocký
Keyword(s):  
Factor Analysis ◽  
Speaker Recognition ◽  
Joint Factor ◽  
Joint Factor Analysis

Joint Factor Analysis of Channel Mismatch in Whispering Speaker Verification

2012 ◽  
Vol 37 (4) ◽  
pp. 555-559 ◽  
Author(s):  
Gang Lv ◽  
Heming Zhao
Keyword(s):  
Factor Analysis ◽  
Speaker Recognition ◽  
Speaker Verification ◽  
Recognition Rate ◽  
Gaussian Mixture ◽  
Recognition System ◽  
Joint Factor ◽  
Channel Mismatch ◽  
Joint Factor Analysis ◽  
Correct Recognition Rate

Abstract A speaker recognition system based on joint factor analysis (JFA) is proposed to improve whispering speakers’ recognition rate under channel mismatch. The system estimated separately the eigenvoice and the eigenchannel before calculating the corresponding speaker and the channel factors. Finally, a channel-free speaker model was built to describe accurately a speaker using model compensation. The test results from the whispered speech databases obtained under eight different channels showed that the correct recognition rate of a recognition system based on JFA was higher than that of the Gaussian Mixture Model-Universal Background Model. In particular, the recognition rate in cellphone channel tests increased significantly.

Sign in / Sign up

Export Citation Format

Share Document