We propose an approach to modeling Chinese tonal patterns, focusing on the basic fundamental frequency (F 0 ) patterns characterized by the contextual linguistic features that can be directly extracted from text. We analyze tonal patterns as sparse target points (tonal F 0 peaks and valleys) and represent them in parametric form within the framework of a functional F 0 model. The relationships between the target points and underlying linguistic features are trained using classification and

more »

... ssion tree analysis (CARTs), and this functional model is used to trace the F 0 trajectories when training the CARTs and to synthesize a tonal pattern from the target points predicted by the CARTs. Our experiments indicate that the proposed method has low F 0 prediction errors. Utilization of the F 0 ranges measured from training samples could significantly reduce the influences of differences in voice ranges on training a speaker-independent model. Furthermore, the most important roles in characterizing tonal patterns were played by a few linguistic features such as lexical tone context and the distinction between voiced from unvoiced initials.