Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron

We present an extension to the Tacotron speech synthesis architecture that learns a latent embedding space of prosody, derived from a reference acoustic representation containing the desired prosody. We show that conditioning Tacotron on this learned embedding space results in synthesized audio that matches the prosody of the reference signal with fine time detail even when the reference and synthesis speakers are different... (read more)

PDF Abstract ICML 2018 PDF ICML 2018 Abstract

Datasets


  Add Datasets introduced or used in this paper

Results from the Paper


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

Methods used in the Paper


METHOD TYPE
Griffin-Lim Algorithm
Phase Reconstruction
Sigmoid Activation
Activation Functions
Highway Layer
Miscellaneous Components
Residual Connection
Skip Connections
Convolution
Convolutions
Batch Normalization
Normalization
Max Pooling
Pooling Operations
Residual GRU
Recurrent Neural Networks
BiGRU
Bidirectional Recurrent Neural Networks
Highway Network
Feedforward Networks
CBHG
Speech Synthesis Blocks
ReLU
Activation Functions
Dropout
Regularization
Dense Connections
Feedforward Networks
Tanh Activation
Activation Functions
Additive Attention
Attention Mechanisms
GRU
Recurrent Neural Networks
Tacotron
Text-to-Speech Models