行阶梯观测矩阵下语音压缩感知观测序列的Volterra+Wiener模型研究

针对压缩感知理论下，语音信号经随机高斯矩阵投影后得到的观测序列随机性太强，难以建模的问题，提出了一种基于行阶梯观测矩阵的语音压缩感知观测序列的Volterra模型，利用该模型实现对语音压缩感知观测序列的预测，研究了Volterra滤波器输入维数与阶数对预测效果的影响，并利用维纳滤波器进一步降低预测误差。在相同的已知数据量下，基于部分压缩感知观测序列、Volterra模型、Wiener滤波器的重构，获得了优于高斯随机观测序列的重构性能。模型的研究为压缩感知与语音技术的结合提供一定的参考价值。 

Research on Volterra and Wiener Model of Compressed Sensing Measurement of Speech Signal Based on Row Echelon Matrix

Aiming at the difficulty of modeling the gauss measurement of speech signal for its strong randomicity under compressed sensing theory, this paper proposed Volterra model of compressed sensing measurement of speech signal based on special row echelon measurement matrix, and realized the prediction of compressed sensing measurement of speech signal based on this kind of Volterra model .The prediction effects of input dimensions and order of Volterra model were studied. Wiener filter was used in order to ruduce the prediction error of Volterra model. Under the same known data quantity, reconstruction based on part of compressed sensing measurement, Volterra model and wiener filter, achieves better reconstruction performance than that of gauss measurement. Research on this model offered certain reference value on the combination of compressed sensing and speech signal processing techniques.