Frequency domain errors-in-variables approach for two-channel SIMO system identification

This paper deals with the blind identification of the variances of the additive noises in a two-channel SIMO system. They are estimated by using a frequency domain errors-in-variables scheme, when finite impulse responses (FIR) filters are driven by a white input sequence. It should be noted that the proposed approach has the advantage of addressing the unbalanced case, i.e. when the noise variances are not the same. Moreover, the algorithm enables the solution to be directly obtained from the noisy data and no optimization algorithm is required. © 2007 EURASIP.