FCTalker: Fine and Coarse Grained Context Modeling for Expressive Conversational Speech Synthesis.
Yifan HuRui LiuGuanglai GaoHaizhou LiPublished in: CoRR (2022)
Keyphrases
- coarse grained
- context modeling
- speech synthesis
- fine grained
- context awareness
- speech recognition
- cross modal
- multi modal
- text to speech
- image coder
- lossless compression
- protein sequences
- arithmetic coding
- high level
- multimedia retrieval
- ubiquitous computing
- access control
- shared memory
- ambient intelligence
- context aware
- high order
- bag of features
- rate distortion
- natural language
- data compression
- smart home
- image coding
- hidden markov models
- multiscale