In this paper an efficient segment selection method for corpus-based speech synthesis is presented. Traditional unit-selectors use dynamic programming (DP) to find in a fully connected segment network the most appropriate segment sequence based on target- and concatenation costs. Instead of performing a full DP search, the presented unit-selector applies fast transformations on binary valued segment connection matrices. It is further also shown that this technique can be expanded to supra-segmental unit-selection without altering the segment size in the database.