Title :
Text-independent speaker identification based on explicit exploitation of stochastic characteristics of test utterance
Author :
Tsai, W.H. ; Chang, W.W. ; Huang, D.G.
Author_Institution :
Philips Res. East Asia, Taipei, Taiwan
fDate :
12/6/2001 12:00:00 AM
Abstract :
The benefit of exploiting the stochastic characteristics of test utterance for speaker identification (speaker ID) via cross likelihood ratio and Bayesian information criterion is explored. Simulation results demonstrate the superiority of the proposed approaches over the conventional speaker ID based on maximum likelihood decision rule
Keywords :
Bayes methods; speaker recognition; stochastic processes; Bayesian information criterion; cross likelihood ratio; stochastic characteristics; test utterance; text-independent speaker identification;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:20011044