Abstract: Compressed Sensing(CS),an emerging theory,provides an alternative approach for signal compression.In this study,an incoherent speech dictionary scheme is proposed via K-L Expansion to improve the matching property of previous ones,and the Segment MP(SegMP) algorithm is designed aiming at the shortages of MP and OMP.We build a speech autocorrelation model and estimate the model parameter to construct the dictionary.Afterwards,the SegMP is employed to obtain low-dimensional measurements and to reconstruct speech with the dictionary that is rebuilt by the model parameter.Finally,the compressed speech signal sensing is implemented.Extensive experiments demonstrate that the presented scheme outperforms state-of-the-art method in vocal signals' sparse description.It has three characteristics:better signal adaptability,higher reconstruction quality and lower complexity.