TDASS: Target Domain Adaptation Speech Synthesis Framework for Multi-speaker Low-Resource TTS.

Xulong Zhang Jianzong Wang Ning Cheng Jing Xiao

Published in: IJCNN (2022)

Keyphrases

speech synthesis
domain adaptation
text to speech
speech recognition
prosodic features
labeled data
target domain
cross domain
sentiment classification
speaker verification
vocal tract
feature extraction
pattern recognition
unsupervised learning
unlabeled data
feature representation