Listen, Denoise, Action! Audio-Driven Motion Synthesis with Diffusion
ModelsACM Transactions on Graphics (TOG), 2022 |
OverFlow: Putting flows on top of neural transducers for better TTSInterspeech (Interspeech), 2022 |
Neural HMMs are all you need (for high-quality attention-free TTS)IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2021 |