Superpositional HMM-based intonation synthesis using a functional F0 model
Jinfu Ni, Yoshinori Shiga, Chiori Hori · 2014
This paper addresses intonation synthesis combining statistical and functional approach with manipulation of fundamental frequency (F0) contours in HMM-based speech synthesis. An F0contour is represented as a sum of micro, accent, and register components at the logarithmic scale, which is rooted in the Fujisaki model. Separated context-dependent (CD) HMMs are trained for each type of components extracted from a speech corpus based on a functional F0model. At the phase of synthesis, CDHMM-generated micro, accent, and register components are superimposed to form F0contours for input text. Objective and subjective evaluations are carried out on a Japanese speech corpus. Compared with the conventional approach, this method not only demonstrates the improved performance in naturalness of synthetic speech by achieving better global F0behaviors but also shows its flexibility for intonation manipulation through modifying the functional model parameters.