Msdtron: a high-capability multi-speaker speech synthesis system for diverse data using characteristic information

In multi-speaker speech synthesis, data from a number of speakers usually tends to have great diversity due to the fact that the speakers may differ largely in ages, speaking styles, emotions, and so on. It is important but challenging to improve the modelling capabilities for multi-speaker speech synthesis. To address the issue, this paper proposes a high-capability speech synthesis system (called Msdtron) in which 1) a representation of harmonic structure of speech, called excitation spectrogram, is designed to directly guide the learning of harmonics in mel-spectrogram. 2) conditional gated LSTM (CGLSTM) is proposed to control the flow of text-content information through network by re-weighting the LSTM gates using speaker information. The experiments show significant reduction in reconstruction errors of mel-spectrogram in the training of multi-speaker model, and a great improvement is observed in the subjective evaluation of speaker adapted model.