Optimization of a neural network for speaker and task dependent F 0-generation

The generation of a pleasant pitch contour is an important issue for the naturalness of each TTS system. Till now the results are far from being satisfactory. In this paper we present a speakerand task specific approach realized by a neural network. Personal and task specific characteristics are maintained and the demand of gcneralization decreases. So the results in application can signilicantly be improved. I!sing an optimized network structure global and well localized paltems can be covered and trained simultaneously within one network. Correlation analysis of the data base versus the sensitivity of the trained network validates the importance of distinctive paramctcrs in training. Based on this comparison we give a discussion of the generalization properties of the nn trained speaker and task dependency. Finally a variation of the context range helps to find an optimized tuning of the input parameter set.