Speech Bert Embedding for Improving Prosody in Neural TTS.

Liping Chen Yan Deng Xi Wang Frank K. Soong Lei He

Published in: ICASSP (2021)

Keyphrases

text to speech
speech synthesis
prosodic features
neural network
network architecture
vocal tract
neural model
vector space
multi modal
data hiding
graph embedding
word processing
watermarking algorithm
multi stream
audio visual
speech recognition
bit rate
nonlinear predictive control