IBM Model 1
IBM Model 1 defines the probability of a sentence $s_1^J$, with length $J$, being translated to a sentence $t_1^I$, with length $I$, with the alignment $a_1^J$ as:
$Pr(t,a|s) = \frac{\epsilon}{(J+1)^{I}}\prod_{j=1}^{J}{tr(t_j|s_{a(j)})}$
ASM/AAM
LeungMalikFilterBank