Dans de nombreuses situations, le statisticien observe un échantillon fini issu d’un phénomène temporel X1, . . . , Xn. Une modélisation usuelle est de considérer cet échantillon comme issu d’un processus stationnaire X := (Xt)t∈Z au second ordre (voir [2], [10]). Cela signifie que la variable aléatoire Xt est, pour tout t ∈ Z, de carré sommable, et que la moyenne (que l’on suppose égale à 0) e...

Convolutive source separation is often done in two stages: 1) estimation of the mixing filters and 2) estimation of the sources. Traditional approaches suffer from the ambiguities of arbitrary permutations and scaling in each frequency bin of the estimated filters and/or the sources, and they are usually corrected by taking into account some special properties of the filters/sources. This paper...

We propose an iterative rake receiver structure using an optimum semi-blind channel estimation algorithm for DS-CDMA mobile communication systems. This receiver performs an iterative estimation of the channel according to the maximum a posteriori criterion, using the expectation-maximization algorithm. This estimation process requires a convenient representation of the discrete multipath fading...