BLSTM-CRF Based End-to-End Prosodic Boundary Prediction with Context Sensitive Embeddings in a Text-to-Speech Front-End.
Yibin ZhengJianhua TaoZhengqi WenYa LiPublished in: INTERSPEECH (2018)
Keyphrases
- end to end
- context sensitive
- text to speech
- text to speech synthesis
- prosodic features
- speech synthesis
- conditional random fields
- congestion control
- language model
- admission control
- pairwise
- english text
- information extraction
- graphical models
- natural language
- graph grammars
- internet protocol
- multiple task learning
- machine learning
- word processing
- vector space
- generative model
- markov random field
- writing skills
- real world