Nana-HDR: A Non-attentive Non-autoregressive Hybrid Model for TTS.
Shilun LinWen-Chao SuLi MengFenglong XieXinhui LiLi LuPublished in: CoRR (2021)
Keyphrases
- autoregressive
- hybrid model
- text to speech
- high dynamic range
- moving average
- artificial neural networks
- non stationary
- visual attention
- support vector regression
- tone mapping
- gaussian markov random field
- random fields
- hybrid models
- support vector machine svm
- dynamic range
- multiscale
- sar images
- model selection
- markov random field
- arima model
- autoregressive moving average