Hierarchical Generative Modeling for Controllable Speech Synthesis
international conference on learning representations, 2019.
This paper proposes a neural end-to-end text-to-speech (TTS) model which can control latent attributes in the generated speech that are rarely annotated in the training data, such as speaking style, accent, background noise, and recording conditions. The model is formulated as a conditional generative model with two levels of hierarchical...More
PPT (Upload PPT)