Login / Signup
DQR-TTS: Semi-supervised Text-to-speech Synthesis with Dynamic Quantized Representation.
Jianzong Wang
Pengcheng Li
Xulong Zhang
Ning Cheng
Jing Xiao
Published in:
ISPA/BDCloud/SocialCom/SustainCom (2023)
Keyphrases
</>
text to speech
text to speech synthesis
semi supervised
semi supervised learning
labeled data
prior knowledge
multi view
multiscale
data structure
unsupervised learning
image representation
unlabeled data
representation scheme
semi supervised classification
semi supervised clustering