Corpus-based synthesis of fundamental frequency contours based on a generation process model

A mode-constrained corpus-based synthesis strategy was developed for fundamental frequency (F0) contours of Japanese sentences. In the training phase, the relationship between linguistic factors and the command values (amplitudes and locations) of F0 contour generation process model was learned for a prediction module; a neural network in the current paper. Input parameters consist of linguistic information related to accentual phrases that can be automatically driven from text, such as the position of the accentual phrase in the utterance, number of morae, accent type, and morphological information. In the synthesis phase, the prediction module is used to generate command values of the model. The synthesis method was also realized based on multiple linear regression analysis to examine how each input parameter contributes to the F0 contour generation. The use of the parametric model restricts the degrees of freedom of the mapping between linguistic and prosodic features, and thus enables to generate appropriate values even with limited training data. Experimental results showed that the method could generate F0 contours quite close to those by the rulebased method.