We investigate speaker adaptation in the context of deep neural network (DNN) based speech synthesis. More specifically, our current work focuses on the exploitation of auxiliary information such as gender, speaker identity or age during the DNN training process. The proposed technique is compared to standard acoustic feature transformations such as the feature based maximum likelihood linear regression (FMLLR) based speaker adaptation. Objective error measurements as well as perceptual experiments, performed on the WSJCAM0 database, suggest that the proposed method is superior to standard feature transformations.