Asynchronous Signal Detection in Frequency-Selective Non-Gaussian Channels

We present a signal detection algorithm for digital amplitude-phase modulated signals in frequency-selective fading channels with non-Gaussian noise. We consider an asynchronous scenario in which the timing (symbol transition epochs) is unknown and a symbol rate offset is present due to clock drift. A Gibbs sampling-based algorithm is proposed to estimate the unknown parameters and signal detection is performed using a maximum-likelihood procedure. The additive noise is modeled by a Gaussian mixture distribution, a well-known model for man-made and natural noise. Numerical results are presented to characterize the performance of the proposed algorithm.