Generative Model-Based Text-to-Speech Synthesis

Generative Model-Based Text-to-Speech Synthesis

Date Posted: 

February 10, 2017

Date Recorded: 

February 3, 2017

Speaker(s): 

Heiga Zen
  • Speech Representation, Perception and Recognition

Associated CBMM Pages: 

Description: 

Heiga Zen, Google

Abstract: Recent progress in generative modeling has improved the naturalness of synthesized speech significantly.  In this talk I will summarize these generative model-based approaches for speech synthesis and describe possible future directions.

Associated Research Thrust: