Superpositional HMM-based intonation synthesis using a functional F0 model

• Published in: The 9th International Symposium on Chinese Spoken Language Processing pp. 270 - 274
• Main Authors: Jinfu Ni, Shiga, Yoshinori, Hori, Chiori
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01-09-2014
• Subjects: Correlation; Frequency synthesizers; functional F0 model; Hidden Markov models; HMM-based speech synthesis; Intonation synthesis; making focal prominence; prosody; Registers; Speech; Speech synthesis; Training
• DOI: 10.1109/ISCSLP.2014.6936614

This paper addresses intonation synthesis combining statistical and functional approach with manipulation of fundamental frequency (F 0 ) contours in HMM-based speech synthesis. An F 0 contour 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 F 0 model. At the phase of synthesis, CDHMM-generated micro, accent, and register components are superimposed to form F 0 contours 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 F 0 behaviors but also shows its flexibility for intonation manipulation through modifying the functional model parameters.