New framework syncs robot lip movements with speech, supporting 11+ languages and enhancing humanlike interaction.

Almost half of our attention during face-to-face conversation focuses on lip motion. Yet, robots still struggle to move their ...

To match the lip movements with speech, they designed a "learning pipeline" to collect visual data from lip movements. An AI model uses this data for training, then generates reference points for ...

VoiceRun, on the other hand, lets users code how they want their voice agents to behave, giving them more flexibility in ...