Two-stage F0 control model using syllable based F0 units

This paper proposes syllable-based F0 units(SBUs) for F0 contour generation and a two-stage strategy. The two-stage strategy provides a flexible F0 generation framework by introducing a global model and local model. The local model consists of the SBUs which make it possible to precisely estimate F0 contour using segmental information. Experimental results show that the proposed approach can generate a good global model(the measured multiple correlation coefficient is 0.843), and can precisely estimate average F0(the measured multiple correlation coefficient is 0.875). It is also confirmed that generating SBUs according to syllable positions is important in precisely estimating F0 contour. Listening tests show that speech synthesized with the proposed model is preferred to the output of the conventional model. We expect that the approach will prove to be useful and powerful for synthesizing various types of speech.