Algorithm for underdetermined blind signal separation based on constrained NMF
Junna Shang · Jisuanji yingyong yanjiu · 2011
This paper proposed a constrained nonnegative matrix factorization(NMF) method to resolve the problem of underdetermined blind signal separation.It was hard to obtain unique factorization and correctly separated source signals when NMF was directly applied to resolve problem above.On the basis of standard NMF,imposed determinant criterion on estimated mixing matrix to achieve the unique factorization of NMF.Imposed sparsity and the least correlated component constraints on estimated sources to realize the unique separation of mixed signals and improve the performance of source separation.Simulation results show the effectiveness of the proposed algorithm.