In this paper, we provide theoretical results on the problem of optimal stream weight selection for the multi-stream classi- fication problem. It is shown, that in the presence of estimation or modeling errors using stream weights can decrease the total classification error. Stream weight estimates are computed for various conditions. Then we turn our attention to the problem of unsupervised stream weights computation. Based on the theoretical results we propose to use models and “anti-models” (class- specific background models) to estimate stream weights. A non-linear function of the ratio of the inter- to intra-class distance is used for stream weight estimation. The proposed unsupervised stream weight estimation algorithm is evaluated on both artificial data and on the problem of audio-visual speech classification. Finally the proposed algorithm is extended to the problem of audio- visual speech recognition. It is shown that the proposed algorithms achieve results comparable to the supervised minimum-error training approach under most testing conditions.