【摘要】 压缩感知理论框架可以同时实现信号的采样和压缩,将压缩感知应用于语音信号处理是近年来的研究热点之一.本文根据语音信号的特点,采用K-SVD算法获得稀疏线性预测字典,作为语音信号的稀疏变换矩阵.高斯随机矩阵用于原语音信号的采样从而实现信号的压缩,最后通过正交匹配追踪算法(OMP)和采样压缩匹配追踪算法(Co Sa MP)将已采样压缩的语音信号进行信号重构.实验考察了待处理语音信号帧的长度、压缩比,稀疏变换字典以及压缩感知重构算法等因素对语音压缩感知重构性能的影响,结果表明,基于数据集训练的稀疏线性预测字典相比传统解析构造的离散余弦变换字典,对语音的重构性能具有0.6 d B左右的提升.更多还原

【Abstract】 Appling compressive sensing( CS),which theoretically guarantees that signal sampling and signal compression can be achieved simultaneously,into audio and speech signal processing is one of the most popular research topics in recent years. In this paper,K-SVD algorithm was employed to learn a sparse linear prediction dictionary regarding as the sparse basis of underlying speech signals. Compressed signals was obtained by applying random Gaussian matrix to sample original speech frames. Orthogonal matching pursuit( OMP) and compressive sampling matching pursuit( Co Sa MP) were adopted to recovery original signals from compressed one. Numbers of experiments were carried out to investigate the impact of speech frames length,compression ratios,sparse basis and reconstruction algorithms on CS performance. Results show that sparse linear prediction dictionary can advance the performance of speech signals reconstruction compared with discrete cosine transform( DCT) matrix.更多还原