In this paper we describe the voices we submitted to the 2009 Blizzard Challenge, a yearly challenge to evaluate auditory speech synthesis on common data. Since it is the second time we participate in this challenge, in this paper we focus on the changes we made to our unit selection-based system. The weighted sum of symbolic target costs has been replaced by a single statistical target cost; the weighted sum of acoustic join cost has been replaced by a single statistical join cost. Both these costs are based on context-clustering decision tree modeling, and trained on the speech database. Furthermore, the voice building process has been enhanced by improving the segmentation quality and by automatically removing potentially {"}bad{"} units.