Login / Signup
Prosody Modelling With Pre-Trained Cross-Utterance Representations for Improved Speech Synthesis.
Ya-Jie Zhang
Chao Zhang
Wei Song
Zhengchen Zhang
Youzheng Wu
Xiaodong He
Published in:
IEEE ACM Trans. Audio Speech Lang. Process. (2023)
Keyphrases
</>
speech synthesis
speech recognition
pre trained
text to speech
vocal tract
hidden markov models
prosodic features
pattern recognition
automatic speech recognition
machine learning
speech signal
training examples
control signals
language model
neural network
mean shift
training data