中文摘要：

根据语音信号的特点,提出了一种基于线性预测分析的合成矩阵作为语音信号的稀疏变换域,并验证了语音信号在该域上的稀疏特性。由语音信号和随机高斯矩阵构造相应的观测,采用正交匹配追踪算法重构原始语音信号。实验表明,语音信号在新的变换域上的重构性能要优于DCT域,且具有较高的分段信噪比和平均意见得分。

英文摘要：

This paper presented a new speech signal sparse domain—synthesis matrix based on linear prediction technology based on the features of speech signal,and verified the sparsity of speech signal in the new sparse domain.By speech signal and the Gaussian random matrix,used OMP to reconstruct the original speech signal.Experimental results demonstrate that the performance of the speech recovered using compressed sensing for speech signal based on linear prediction analysis is better and reconstructed signal has good segment signal to noise ratio and mean opinion score,compared with DCT domain.