Title :
Speaker Recognition Method Based on CPSO Clustering and KMP Algorithm
Author :
Dong An ; Meng Shao ; Zhe Yuan ; Huaitao Shi ; Qingchen Pan
Author_Institution :
Sch. of Traffic & Mech. Eng., Shenyang Jianzhu Univ., Shenyang, China
Abstract :
This paper proposes a chaotic particle swarm optimization and kernel matching pursuit algorithm a combination of speaker recognition methods. First through the CPSO clustering algorithm to transform the MFCC feature parameters of processing, streamlining of the MFCC feature parameters (SMFCC), then use the KMP algorithm on the reduction parameters after the SMFCC feature classification training and recognition. The results show that CPSO-KMP-based speaker recognition method compared to the GMM-UBM method, the relative increase in EER performance of 31%.
Keywords :
chaos; particle swarm optimisation; pattern classification; pattern clustering; pattern matching; speaker recognition; support vector machines; CPSO clustering algorithm; KMP algorithm; Mel frequency cepstral coefficient; SMFCC feature classification; SVM; chaotic particle swarm optimization; kernel matching pursuit algorithm; speaker recognition method; streamlining of MFCC feature parameter; support vector machine; Classification algorithms; Clustering algorithms; Kernel; Matching pursuit algorithms; Mel frequency cepstral coefficient; Speaker recognition; Support vector machines; Chaotic Particle Swarm Optimization; Clustering; Kernel Matching Pursuit; Speaker Recognition;
Conference_Titel :
Computational Intelligence and Design (ISCID), 2014 Seventh International Symposium on
Print_ISBN :
978-1-4799-7004-9
DOI :
10.1109/ISCID.2014.115
