Showing cs.SDShow all
2 papers · 1 filter
cs.SD2022
MHTTS: Fast multi-head text-to-speech for spontaneous speech with imperfect transcription
Dabiao Ma, Yitong Zhang, Meng Li +1
Neural network based end-to-end Text-to-Speech (TTS) has greatly improved the quality of synthesized speech. While how to use massive spontaneous speech without transcription effic…
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…