Speech Synthesis with Self-Supervisedly Learnt Prosodic Representations.
Zhaoci LiuZhen-Hua LingYa-Jun HuJia PanJin-Wei WangYun-Di WuPublished in: INTERSPEECH (2023)
Keyphrases
- speech synthesis
- prosodic features
- speech recognition
- text to speech
- vocal tract
- text to speech synthesis
- speech corpus
- higher level
- automatic speech recognition
- hidden markov models
- language model
- symbolic representation
- multiple representations
- databases
- noisy environments
- real time
- external representations
- data sets
- real world
- computer vision
- word processing
- database systems
- information systems
- expert systems
- bayesian networks