基于压缩感知观测序列倒谱距离的语音端点检测算法

被引:11
作者
叶蕾 [1 ]
孙林慧 [1 ]
杨震 [2 ]
机构
[1] 南京邮电大学通信与信息工程学院
[2] 南京邮电大学信号处理与传输研究院
关键词
端点检测; 压缩感知; 倒谱距离;
D O I
暂无
中图分类号
TN912.3 [语音信号处理];
学科分类号
0711 ;
摘要
本文基于语音信号在离散余弦基上的近似稀疏性,采用稀疏随机观测矩阵和线性规划重构算法对语音信号进行压缩感知与重构。研究了语音信号的压缩感知观测序列特性,根据语音帧和非语音帧压缩感知观测序列频谱幅度分布分散且差异较大的特性,提出基于压缩感知观测序列倒谱距离的语音端点检测算法,并对4dB-20dB下的带噪语音进行端点检测仿真实验。仿真结果显示,基于压缩感知观测序列倒谱距离的语音端点检测算法与奈奎斯特采样下语音的倒谱距离端点检测算法一样具有良好的抗噪性能,但由于采用压缩采样,减少了端点检测算法的运算数据量。
引用
收藏
页码:67 / 72
页数:6
相关论文
共 15 条
  • [1] Using sparse representations for missing data imputation in noise robust speech recognition. J.F.Gemmeke,B.Cranen. European Signal Processing Conf.(EU- SIPCO) . 2008
  • [2] Retrieving sparse patterns using a com-pressed sensing framework:applications to speech coding based on sparse linear prediction. Giacobello D,Christensen M G,Murthi M N,Jensen S H,Moonen M. Signal Processing Letters,IEEE . 2010
  • [3] A compressed sensing approach for underdetermined blind audio source separation with sparse representation. Tao Xu,Wenwu Wang. . 2009
  • [4] Extensions of compressed sensing. D. Donoho,Y. Tsaig. Signal Processing . 2006
  • [5] "Competitiveoptimization of compressed sensing". M.Andrecut,R.A.Este,S.A.Kauffman. Journal of PhysicsA:Mathematical and Theoretical . 2007
  • [6] Compressed sensing. D.L.Donoho. IEEE Transactions on Information Theory . 2006
  • [7] Compressive sampling. E.J.Cande‘s. Proc.of the International Congress of Mathematicians . 2006
  • [8] Robust uncertainty principles:exact signal reconstruction from highly incomplete frequency information. E.J.Cande‘s,J.Romberg,T.Tao. IEEE Transactions on Information Theory . 2006
  • [9] Quantitative robust uncertainty principles and optimally sparse decompositions
    Candès, Emmanuel J.
    Romberg, Justin
    [J]. FOUNDATIONS OF COMPUTATIONAL MATHEMATICS, 2006, 6 (02) : 227 - 254
  • [10] Sparse recovery using sparse random matrices. R.Berinde,P.Indyk. MIT-CSAIL Technical Report . 2008