You are here

Zhizheng Wu research description

In NST, Zhizheng is working on acoustic modelling for speech synthesis. Recently, deep neural network (DNN) has been successfully applied to
automatic speech recognition, and some positive results have also been reported in the speech synthesis research by replacing the decision tree
mapping. We will continue to improve the performance of DNN for speech synthesis and investigate ways to jointly optimize the front-end with the
acoustic model.