Abstract
We address the blind separation of two autoregressive (AR) processes from a single mixture thereof, when their respective driving-noise ("innovation") sequences are known to be temporally sparse. Unlike other single-channel separation schemes, which use dictionary- learning, our method essentially estimates the sparsifying transformation of each source directly from the ob- served mixture (by estimating the respective AR parameters), and therefore does not require a training stage. We cast the problem as a constrained, non-convex ℓ 1- norm minimization and propose an iterative solution scheme, which iterates between linear-programming- based estimation of the respective driving-sequences given estimates of the AR parameters, and gradient- based refinement of the estimated AR parameters given the estimated driving sequences. Near-perfect separation is demonstrated using a simulated example.
Original language | English |
---|---|
Pages (from-to) | 1479-1483 |
Number of pages | 5 |
Journal | European Signal Processing Conference |
State | Published - 2010 |
Event | 18th European Signal Processing Conference, EUSIPCO 2010 - Aalborg, Denmark Duration: 23 Aug 2010 → 27 Aug 2010 |