Modeling Multi-speaker Latent Space to Improve Neural TTS: Quick Enrolling New Speaker and Enhancing Premium Voice.

Yan Deng Lei He Frank K. Soong

Published in: CoRR (2018)

Keyphrases

prosodic features
text to speech
speaker verification
latent space
neural network
gaussian process latent variable models
data sets
high dimensional
generative model
labeled data
mixture model