Unsupervised Quantized Prosody Representation for Controllable Speech Synthesis.
Yutian WangYuankun XieKun ZhaoHui WangQin ZhangPublished in: CoRR (2022)
Keyphrases
- speech synthesis
- text to speech
- speech recognition
- prosodic features
- vocal tract
- unsupervised learning
- speech corpus
- unsupervised manner
- machine learning
- data mining
- semi supervised
- hidden markov models
- language model
- image classification
- feature representation
- multiresolution
- pattern recognition
- case study
- feature selection
- feature hierarchies