HMM-based unit selection speech synthesis using log likelihood ratios derived from perceptual data

Xian-Jun Xia, Zhen-Hua Ling, Yuan Jiang, Li-Rong Dai

Abstract: Highlights•We present a method to make use of perceptual data during the construction of a unit selection speech synthesis system.•The perceptual data is collected by judging the naturalness of each synthetic prosodic word manually.•Log likelihood ratios (LLR) are derived from the perceptual data and act as target cost functions in the HMM-based unit selection speech synthesis.•Several different ways of utilizing LLRs at synthesis time are proposed and compared in our experiments.