Login / Signup
Improving Multi-Speaker TTS Prosody Variance with a Residual Encoder and Normalizing Flows.
Iván Vallés-Pérez
Julian Roth
Grzegorz Beringer
Roberto Barra-Chicote
Jasha Droppo
Published in:
Interspeech (2021)
Keyphrases
</>
text to speech
prosodic features
speech synthesis
speaker verification
standard deviation
speech recognition
audio visual
synthesized speech
video compression
residual error
multi modal
covariance matrix
speaker recognition
noisy environments
automatic speech recognition
rate distortion
motion estimation