Towards Multi-Scale Speaking Style Modelling with Hierarchical Context Information for Mandarin Speech Synthesis.
Shun LeiYixuan ZhouLiyang ChenJiankun HuZhiyong WuShiyin KangHelen MengPublished in: CoRR (2022)
Keyphrases
- speech synthesis
- speech recognition
- prosodic features
- multiscale
- coarse to fine
- text to speech
- vocal tract
- hidden markov models
- natural images
- pattern recognition
- edge detection
- speech signal
- automatic speech recognition
- hierarchical model
- image segmentation
- language model
- scale space
- image representation
- computer vision
- speaker independent
- speech corpus
- speaker verification
- hierarchical structure
- hierarchical structures
- website
- deep structure
- genetic algorithm
- information retrieval
- data sets