Robuta

https://ieeetv.ieee.org/ondemand/ieee-icassp-2020-virtual-conference-may-2020/6610 Aligntts: Efficient Feed-Forward Text-To-Speech System Without Explicit Alignment | IEEETV Targeting at both high efficiency and performance, we propose AlignTTS to predict the mel-spectrum in parallel. AlignTTS is based on a Feed-Forward Transformer... text to speech