基于稀疏对角矩阵的语音信号压缩感知.pdfVIP

计算机王也程与设计 2012 年9 月 Sept. 2012 第 33 卷第9 期 COMPUTER ENGINEERING AND DESIGN Vo l. 33 No.9 基于稀疏对角炬阵的语音信号压缩感知 马春1.2 ，孙南1，川，程涛军1.2 ，李新华1，2 O. 安徽大学电子信息工程学院，安徽合肥 230039; 2. 安徽大学计算智能与信号处理 教育部重点实验室，安徽合肥 230039; 3. 安徽省现代成像与显示技术重点实验室，安徽合肥 230039) 摘 要:探索压缩感知理论在语音信号重构中的应用，研究测量矩阵选取对语音信号重构效果的影响。改进传统随机，托 普利兹，循环等测量矩阵，尝试将稀疏对角矩阵应用于测量矩阵完成对语音信号的非相干测量。在语音信号上进行实验， 分别采用稀疏对角结构测量矩阵和传统测量矩阵，对比它们使用 StOMP 算法重构语音信号的效果。实验结采表明，采用 改进的稀疏对角循环矩阵重构语音信号，较传统矩阵重构的精确度有明显提高，运行时间也有明显缩短。 关键词:稀疏对角矩阵;测量矩阵;语音信号;信号重构;压缩感知 中图法分类号: TP391 文献标识号:A 文章编号: 1000-7024 (2012) 09-3526-05 Compressed sensing of speech signal using sparse diagonal matrix 1 2 1 2 3 1 2 1 2 MA Chun • , SUN Nan • • , CHENG Tao-jun • , LI Xin-hua • (l. School of Electronics and Information Engineering , Anhui University , Hefei 230039 , China; 2. Key Laboratory of IC . SP of Ministry of Education , Anhui University , Hefei 230039 , China; 3. Key Laboratory of Modern Imaging and Displaying Technology of Anhui Province , Hefei 230039 , China) Abstract: The application of compressed sensing in speech signal reconstruction is explored , and the effect of the selection of measurement matrix for speech signal reconstruction is studied. Then the traditional measurement matrix , such as Radom , Toeplitz , Circulate , are improved , and the sparse diagonal matrix is tried to be use in measurement matrix to finish the inco- herent measurement of speech signal. The experiments are made on speech signal , by using sparse diagonal structure measure ment matrix and traditional measuremen