A prosodic model of Mandarin speech and its application to pitch level generation for text-to-speech

A prosodic model of Mandarin speech is proposed to simulate human´s pronunciation mechanism for exploring the hidden pronunciation states embedded in the input text. Parameters representing these pronunciation states are then used to assist prosody information generation. A multirate recurrent neural network (MRNN) is employed to realize the prosodic model. Two learning methods were proposed to train the MRNN. One is an indirect method which firstly uses an additional SRNN to track the dynamics of the prosody information of the utterance; and then takes the outputs of its hidden layer as desired targets to train the MRNN. The other is a direct training method which integrates the MRNN and the following MLP prosody synthesizers to directly learn the relation between the input linguistic features and the output prosody information. Simulation results confirmed the effectiveness of the approach. Most synthesized prosodic parameter sequences match quite well with their original counterparts