%0 Journal Article
%T 一种基于压缩感知的说话人识别参数分析<br>Parameter of Speaker Recognition Based on Compressed Sensing
%A 潘海琦
%A 杨震
%A 徐珑婷
%A 朱俊华
%J 数据采集与处理
%D 2015
%R 10.16337/j.1004-9037.2015.02.019
%X 本文为在传统的说话人识别理论研究中“较少的特征参数量不能与较高的识别率共存”的难题找到了一种解决方案。本文基于压缩感知的理论，利用行阶梯观测矩阵进行信号的投影，改变了传统的梅尔频率倒谱系数(Mel-frequency cepstral coefficient, MFCC)参数，从而提出了一种新的识别参数CS-MFCC（Compressed sensing-MFCC）。该参数不仅使得参数存储量降低到少于原存储量的1/n（n为行阶梯观测矩阵的压缩比），而且明显提高了系统的鲁棒性。通过仿真 实验证明了当压缩比n为4时,平均识别率能够提高到96%以上。<br>A solution is proposed to deal with the problem that ″less number of features cannot coexist with higher recognition rate″ in the traditional theory of speaker recognition. Ladder observation matrix projection is used to change the traditional Mel-frequency cepstral coefficient (MFCC) parameters based on compressed sensing theory, presenting a new recognition parameters named compressed sensing MFCC (CS-MFCC) parameters. These parameters make storage capacity decrease to less than 1/n of the original, here n is the compression ratio of the line ladder matrix, and also greatly increase the robustness of the system. Furthermore simulation results prove that when n is 4, the recognition rate increases to 96% above.
%K 说话人识别
%K 压缩感知
%K 识别率
%K CS-MFCC
%K 鲁棒性&lt
%K br&gt
%K speaker recognition
%K compressed sensing
%K recognition rate
%K CS-MFCC
%K robustness
%U http://sjcj.nuaa.edu.cn/ch/reader/view_abstract.aspx?file_no=20150219&flag=1