|
|||||
|
|
| 基于压缩感知重构信号的说话人识别系统抗噪方法研究 | |
| 引用本文： | 叶蕾,郭海燕,杨震. 基于压缩感知重构信号的说话人识别系统抗噪方法研究[J]. 信号处理, 2010, 26(3): 321-326 |
| 作者姓名： | 叶蕾 郭海燕 杨震 |
| 作者单位： | 南京邮电大学通信与信息工程学院 |
| 基金项目： | 国家自然科学基金项目，南京邮电大学青蓝计划项目 |
| 摘 要： | 基于语音信号在离散余弦基下的近似稀疏性，本文对语音信号采用压缩感知(Compressed Sensing)技术进行压缩和重构，即将语音信号投影到随机高斯观测矩阵，并采用线性规划(Linear Program)方法进行重构，研究了重构误差与观测矢量点数的关系，分析了噪声环境下重构信号的频谱变化情况。针对噪声环境下压缩感知重构信号比原始信号频谱变化小的特性，提出了一种基于压缩感知重构信号的说话人识别系统抗噪方法，给出了不同信噪比下获得最高识别率时压缩感知观测矢量的最佳点数。 |
| 关 键 词： | 压缩感知 离散余弦变换 线性规划 单纯形法 说话人识别 高斯混合模型 |
| 收稿时间： | 2009-04-14 |
Research on Antinoise Method of Speaker Recognition System Based on Compressed Sensing Reconstruction Signal |
|
| YE Lei,GUO Hai-yan,YANG Zhen. Research on Antinoise Method of Speaker Recognition System Based on Compressed Sensing Reconstruction Signal[J]. Signal Processing(China), 2010, 26(3): 321-326 | |
| Authors: | YE Lei GUO Hai-yan YANG Zhen |
| Affiliation: | Department of Communication and Information Engineering, Institute of Signal Processing and? Transmission, Nanjing University of Posts and Telecommunications |
| Abstract: | Based on the approximate sparsity of Speech Signal in Discrete Cosine basis,Compressed Sensing theory is applied to compress and decompress speech signal in this paper,that is,Speech Signal is projected to a random Gauss measurement matrix and reconstructed by Linear Program,the relationship between reconstruction error and numbers of measurement vector is studied,also,the vary of spectrum of reconstruction signal is analysed.According to the less vary of spectrum of Compressed Sensing reconstruction signal... |
| Keywords: | Compressed Sensing Discrete Cosine Transform Linear Program Simplex Method Speaker Recognition Ganssi-an Mixture Model |
| 本文献已被 CNKI 万方数据 等数据库收录！ | |
| 点击此处可从《信号处理》浏览原始摘要信息 | |
| 点击此处可从《信号处理》下载全文 | |