Login / Signup
Using generative modelling to produce varied intonation for speech synthesis.
Zack Hodari
Oliver Watts
Simon King
Published in:
CoRR (2019)
Keyphrases
</>
speech synthesis
prosodic features
text to speech
speech recognition
vocal tract
generative model
speaker verification
speech corpus
real time
data driven
case study
real world
automatic speech recognition
feature extraction
word processing
image sequences
image processing
information systems