Improving Trajectory Modelling for DNN-Based Speech Synthesis by Using Stacked Bottleneck Features and Minimum Generation Error Training

Zhizheng Wu, Simon King. Improving Trajectory Modelling for DNN-Based Speech Synthesis by Using Stacked Bottleneck Features and Minimum Generation Error Training. IEEE Transactions on Audio, Speech & Language Processing, 24(7):1255-1265, 2016. [doi]

Abstract

Abstract is missing.