Multi-reference Tacotron by Intercross Training for Style Disentangling,Transfer and Control in Speech Synthesis

4 Apr 2019 · Yanyao Bian, Changbin Chen, Yongguo Kang, Zhenglin Pan ·

Speech style control and transfer techniques aim to enrich the diversity and expressiveness of synthesized speech. Existing approaches model all speech styles into one representation, lacking the ability to control a specific speech feature independently. To address this issue, we introduce a novel multi-reference structure to Tacotron and propose intercross training approach, which together ensure that each sub-encoder of the multi-reference encoder independently disentangles and controls a specific style. Experimental results show that our model is able to control and transfer desired speech styles individually.

PDF Abstract

Code

Add Remove Mark official

No code implementations yet. Submit your code now

Tasks

Add Remove

Speech Synthesis

Datasets

Add Datasets introduced or used in this paper

Results from the Paper

Edit

Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods

Add Remove

Additive Attention • Batch Normalization • BiGRU • CBHG • Convolution • Dense Connections • Dropout • Griffin-Lim Algorithm • GRU • Highway Layer • Highway Network • Max Pooling • ReLU • Residual Connection • Residual GRU • Sigmoid Activation • Tacotron • Tanh Activation

Edit Social Preview

Multi-reference Tacotron by Intercross Training for Style Disentangling,Transfer and Control in Speech Synthesis

Code Edit Add Remove Mark official

Tasks Edit Add Remove

Datasets Edit

Results from the Paper Edit

Methods Edit Add Remove

Code

Add Remove Mark official

Tasks

Add Remove

Datasets

Results from the Paper

Edit

Methods

Add Remove