Improving Prosody for Cross-Speaker Style Transfer by Semi-Supervised Style Extractor and Hierarchical Modeling in Speech Synthesis.
Chunyu QiangPeng YangHao CheYing ZhangXiaorui WangZhongyuan WangPublished in: ICASSP (2023)
Keyphrases
- speech synthesis
- speech recognition
- prosodic features
- semi supervised
- vocal tract
- text to speech
- speech corpus
- hidden markov models
- language model
- automatic speech recognition
- multi view
- noisy environments
- pattern recognition
- data mining
- labeled data
- data sets
- supervised learning
- computer vision
- information retrieval