Title :
Speaker Recognition via Similar Centroids Balanced FKVQ
Author :
Li Shaomei ; Guo Yunfei ; Liu Lixiong
Author_Institution :
Nat. Digital Switching Syst. Res. Center, Zhengzhou, China
Abstract :
To solve the false acceptance problem in speaker recognition, definition of similar centroids among all reference speakers´ codebooks and similarity between each two speakers are given. A triple is introduced to mark each centroid with the description of similar centroids. And such triple is used to modify the target function in the fuzzy kernel vector quantization speaker recognition, in which the distortion between a test speech feature vector and a centroid is balanced by the centroid´s all similar centroids. The proposed algorithm can weaken similar centroids´ effect in recognition, and decrease false acceptance rate. Similar centroids balanced algorithm showed excellent effect in speaker recognition, and especially in the case of reference speakers with high similarity.
Keywords :
fuzzy set theory; speaker recognition; vector quantisation; centroids balanced FKVQ; false acceptance rate; fuzzy kernel vector quantization; speaker recognition; Clustering algorithms; Embedded computing; Fuzzy control; Kernel; Speaker recognition; Speech; Switching systems; Testing; Training data; Vector quantization;
Conference_Titel :
Computational Intelligence and Software Engineering, 2009. CiSE 2009. International Conference on
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-4507-3
Electronic_ISBN :
978-1-4244-4507-3
DOI :
10.1109/CISE.2009.5362688
