Full HMM Training for Minimizing Generation Error in Synthesis

In maximum-likelihood (ML) based HMM synthesis, the generated trajectory of a sentence in the training set is in general does not reproduce the trajectory of the original one. To overcome this shortcoming, a minimum generation error (MGE) criterion has been previously proposed. In this paper, a complete MGE-based HMM training is introduced, where the MGE criterion is applied to the entire training process, including context-dependent HMM training, context-dependent HMM clustering and clustered HMM training. In this procedure, the HMMs are trained to minimize the generation error of training data, which is in line with the HMM-based synthesis. From the experiments, the quality of synthesized speech is improved after applying the MGE criterion to the whole training process.