Generative Model-Based Text-to-Speech Synthesis
Date Posted: February 10, 2017
Date Recorded: February 3, 2017Speaker(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.