Multilevel parametric-base F0 model for speech synthesis

Abstract This paper proposes a new F0 model for speech synthesis basedon the parameterization of the logF0 contour of the syllables.This parameterization consists of the N -order discrete cosinetransform (DCT) plus some additional parameters such as thegradient of the syllable average pitch. A statistical model of thesyllable pitch contour is then created by clustering the param-eterized vectors with a decision tree. Similar statistical modelsare also created for other linguistic levels other than the syllable.For synthesis, the statistical model of each level is used to definea log-likelihood function for the input text. These functions arethen weighted and added into a global log-likelihood functionwhich is then maximized with respect to the DCT coefficients ofthe syllable model. The final logF0 contour is obtained from theinverse transformation of the syllable DCT coefficients. A sub-jective test showed a clear preference for the proposed modelagainst our previous HMM-based baseline.Index Terms: speech synthesis, HMM-based synthesis,prosody, discrete cosine transform