In our previous work, we proposed factored maximum likelihood linear regression (FMLLR) adaptation where each MLLR parameter is defined as a function of a control vector. In this paper, we introduce a novel technique called factored maximum likelihood kernelized regression (FMLKR) for HMM-based style adaptive speech synthesis. In FMLKR, nonlinear regression between the mean vector of the base model and the corresponding mean vectors of the adaptation data is performed with the use of kernel method based on the FMLLR framework. In a series of experiments on artificial generation of singing voice, the proposed technique shows better performance than the other conventional methods.
Bibliographic reference. Sung, June Sig / Hong, Doo Hwa / Koo, Hyun Woo / Kim, Nam Soo (2013): "Factored maximum likelihood kernelized regression for HMM-based singing voice synthesis", In INTERSPEECH-2013, 359-363.