Control (management)

Linguistics

Philosophy

Literature

Archaeology

Speech synthesis

Computer science

Natural language processing

Divergence (linguistics)

Politics

Political science

Style (visual arts)

Autoencoder

Artificial intelligence

Representation (politics)

End-to-end principle

Artificial neural network

Speech recognition

History

In this paper, we introduce the Variational Autoencoder (VAE) to an end-to-end speech synthesis model, to learn the latent representation of speaking styles in an unsupervised manner. The style representation learned through VAE shows good properties such as disentangling, scaling, and combination, which makes it easy for style control. Style transfer can be achieved in this framework by first inferring style representation through the recognition network of VAE, then feeding it into TTS network to guide the style in synthesizing speech. To avoid Kullback-Leibler (KL) divergence collapse in training, several techniques are adopted. Finally, the proposed model shows good performance of style control and outperforms Global Style Token (GST) model in ABX preference tests on style transfer.

Learning Latent Representations for Style Control and Transfer in End-to-end Speech Synthesis