State Duration Modeling for HMM-Based Speech Synthesis
Heiga Zen, Takashi Masuko, Keiichi Tokuda, T. YOSHIMURA, Takao Kobayasih, Takashi Kitamura · IEICE Transactions on Information and Systems · 2007
This paper describes the explicit modeling of a state duration's probability density function in HMM-based speech synthesis. We redefine, in a statistically correct manner, the probability of staying in a state for a time interval used to obtain the state duration PDF and demonstrate improvements in the duration of synthesized speech.