CART-based modeling of Chinese tonal patterns with a functional model tracing the fundamental frequency trajectories

We propose an approach to modeling Chinese tonal patterns, focusing on the basic fundamental frequency (F₀) patterns characterized by the contextual linguistic features that can be directly extracted from text. We analyze tonal patterns as sparse target points (tonal F₀ peaks and valleys) and represent them in parametric form within the framework of a functional F₀ model. The relationships between the target points and underlying linguistic features are trained using classification and regression tree analysis (CARTs), and this functional model is used to trace the F₀ 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 F₀ prediction errors. Utilization of the F₀ 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.