Abstract: Using the modern time series analysis method, a new time-domain approach to multichannel Wiener deconvolution filters design is presented. Its features are that based on the autoregressive moving average (ARMA) innovation model, asymptotically stable Wiener deconvolution filters can simply be obtained. the solution of Diophantine equations is avoided so that the computational burden may be reduced, and it can handle the deconvolution filtering, smoothing and prediction problems in a unified framework. A simulation example shows its effectiveness.