This paper proposes a parameter generation algorithm using local variance (LV) constraint of spectral parameter trajectory for HMM-based speech synthesis. In the parameter generation process, we take account of both the HMM likelihood of speech feature vectors and a likelihood for LVs. To model LV precisely, we use dynamic features of LV with context-dependent HMMs. The objective experimental results show that the proposed technique can generate a better spectral trajectory in terms of the spectral and LV distortions than a conventional technique with global variance (GV) constraint. The subjective experimental results also show that the proposed technique significantly improve the reproducibility of the synthetic speech than the conventional one.
Bibliographic reference. Chunwijitra, Vataya / Nose, Takashi / Kobayashi, Takao (2012): "A speech parameter generation algorithm using local bariance for HMM-based speech synthesis", In INTERSPEECH-2012, 1151-1154.