Login / Signup
Dynamic Prosody Generation for Speech Synthesis using Linguistics-Driven Acoustic Embedding Selection.
Shubhi Tyagi
Marco Nicolis
Jonas Rohnke
Thomas Drugman
Jaime Lorenzo-Trueba
Published in:
CoRR (2019)
Keyphrases
</>
speech synthesis
prosodic features
speech recognition
text to speech
vocal tract
dynamically select
dynamic environments
hidden markov models
pattern recognition
data driven
language learning
feature extraction
high dimensional
probabilistic model
selection strategy
speaker verification