基于稀疏对角矩阵的语音信号压缩感知

Compressed sensing of speech signal using sparse diagonal matrix

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。实验结果表明,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。

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 measurement matrix and traditional measurement matrix for comparison of the effect of speech signal reconstruction by StOMP algorithm.The experimental results show that the reconstruction accuracy and the operation time of using the improved sparse diagonal circulate matrix for speech signal reconstruction are superior to that of using traditional matrix.