Showing 2025Show all
2 papers · 1 filter
cs.CV2025
Shushing! Let's Imagine an Authentic Speech from the Silent Video
Jiaxin Ye, Hongming Shan
Vision-guided speech generation aims to produce authentic speech from facial appearance or lip motions without relying on auditory signals, offering significant potential for appli…
cs.SD2025
Emotional Face-to-Speech
Jiaxin Ye, Boyuan Cao, Hongming Shan
How much can we infer about an emotional voice solely from an expressive face? This intriguing question holds great potential for applications such as virtual character dubbing and…