Neural HMMs are all you need (for high-quality attention-free TTS)
Neural sequence-to-sequence TTS has achieved significantly better output quality than
statistical speech synthesis using HMMs. However, neural TTS is generally not probabilistic …
statistical speech synthesis using HMMs. However, neural TTS is generally not probabilistic …
OverFlow: Putting flows on top of neural transducers for better TTS
Neural HMMs are a type of neural transducer recently proposed for sequence-to-sequence
modelling in text-to-speech. They combine the best features of classic statistical speech …
modelling in text-to-speech. They combine the best features of classic statistical speech …
Time-varying Normalizing Flow for Generative Modeling of Dynamical Signals
A Ghosh, AE Fontcuberta… - 2022 30th European …, 2022 - ieeexplore.ieee.org
We develop a time-varying normalizing flow (TVNF) for explicit generative modeling of
dynamical signals. Being explicit, it can generate samples of dynamical signals, and …
dynamical signals. Being explicit, it can generate samples of dynamical signals, and …