自适应压缩感知的语音压缩重构算法研究  

Research on algorithm of speech compression and recovery based on adaptive compressed sensing

作　　者：毛静[1,2] 尹鹏亮[1,2] 马琦[1,2] 张斌珍[1,2] 

机构地区：[1]中北大学电子测试国家重点实验室,山西太原030051 [2]中北大学仪器科学与动态测试教育部重点实验室,山西太原030051

出　　处：《电子技术应用》2015年第2期72-74,77,共4页Application of Electronic Technique

基　　金：国家自然科学基金(61335008)

摘　　要：根据传统语音信号的处理过程和语音信号的特征,提出了利用自适应冗余字典KSVD算法、自适应观测矩阵和SAMP重构算法的压缩重构方法,通过仿真分析,并与普通压缩感知对比平均帧重构信噪比、相对误差,验证了压缩感知自适应算法的优越性。According to the speech characteristics and traditional signal processing, this paper proposes that the adaptive algo- rithm is joined in compressed sensing, combined with redundant dictionary KSVD adaptive algorithm, adaptive observation matrix and SAMP reconstruction algorithm. By simulation analysis and comparison with the general compressed sensing on the average frame reconstruction SNR and relative error, it is ended to verify the superiority of adaptive compressed sensing algorithm.

关 键 词：压缩感知 语音信号 自适应算法 

分 类 号：TN912[电子电信—通信与信息系统]