Speaker Identification Research Based on Parallel PNN Model
WANG Chengru1 ,WANG Jinjia1,2 (1. Department of Communication and Electronic Engineering, Yanshan University, Qinghuangdao 066004; 2. State Key Lab of Visual & Hearing Signal Process, Beijing University)
In the paper, a speaker identification system that introduces acoust ic classification information into a heteroscedastic probabilistic neural networ k model is proposed. The training of the novel model utilizes maximum likelihood criterion and develops an effective EM algorithm to adjust model parameters. Th ese experimental results indicate the model maintains identification accuracy, w hile reduces the computational load about 1/3.
【CateGory Index】： TN912.3