摘要
模式匹配是声纹识别的关键问题之一,为了提高识别正确率和识别效率,本文采用GMM模型建模,训练阶段利用EM算法求取参数集,并通过MAP准则实现模式识别。引入LBG算法求取起始参数值,并设计了基于3种方法的联合判决门限决策。实验结果表明GMM模型利用平均值向量和协方差矩阵使它具有更好的模型能力,当高斯混合数为32时识别率达到最高,联合判决门限决策有效降低了误识率与虚警率,并提高了识别效率。
Pattern matching is one of the key problems of voiceprint recognition. In order to improve the accuracy and efficiency of recognition, this paper adopts GMM modeling, applies the EM algorithm to calculate parameter set during the training stage, and achieves pattern recognition via MAP criterion. LBG algorithm is introduced to calculate the initial parameter values, and a combined threshold decision is designed based on 3 methods. Experiment results show that GMM, with mean vector and covariance matrix, enjoys better modeling capability, and reaches the highest recognition rate when the mixed number is 32. The combined threshold decision effectively reduces the false acceptation rate and false alarm rate, and mean- while, it improves the efficiency of recognition.
出处
《通信技术》
2015年第1期97-101,共5页
Communications Technology
基金
用于社区司法矫正的声纹识别系统研究项目(黔科合SY字[2013]3105号)
贵州省中药现代化科技产业研究开发专项(黔科合中药字[2013]5066号)
贵州省工程技术研究中心建设项目(黔科合G字[2014]4002号)~~
关键词
声纹识别
模式匹配
LBG
高斯混合模型
voiceprint recognition
pattern matching
LBG
Gaussian mixture model