Control of fundamental frequency contours using the generation process model in HMM-based speech synthesis

A method was proposed to increase the naturalness of prosody generated with speech synthesis based on hidden Markov models (HMMs). This method adds a constraint to the fundamental frequency contours (F₀ contours) during the HMM-based speech synthesis. The constraint adopted is the generation process model of F₀ contours (F₀ model). The method first extracts the F₀ model parameters from the original Fo contour (generated by the HMM-based speech synthesis) and then optimizes them successively by referring to the pre-trained HMMs. The experimental results show that the proposed method can improve naturalness when the F₀ control by the original method is inadequate.