2 papers
eess.AS2018
FPETS : Fully Parallel End-to-End Text-to-Speech System
Dabiao Ma, Zhiba Su, Wenxuan Wang +1
End-to-end Text-to-speech (TTS) system can greatly improve the quality of synthesised speech. But it usually suffers form high time latency due to its auto-regressive structure. An…
cs.SD2018
UFANS: U-shaped Fully-Parallel Acoustic Neural Structure For Statistical Parametric Speech Synthesis With 20X Faster
Dabiao Ma, Zhiba Su, Yuhao Lu +2
Neural networks with Auto-regressive structures, such as Recurrent Neural Networks (RNNs), have become the most appealing structures for acoustic modeling of parametric text to spe…