AI helps digital humans move more naturally as they speak
CommunicationsArtsComputer Science
THE AI ANGLE
Generating synchronized 3D character movements from speechResearchers developed an AI system called DynaConTalk that translates speech into synchronized 3D body, hand, and facial movements. The model splits motion into fast and slow components to capture posture changes alongside subtle gestures. This gives creators a faster way to generate expressive digital humans directly from audio.
THE TEACHING ANGLE
Speech provides enough rhythm to guide upper-body gestures, yet it lacks the spatial data needed to direct actions like walking across a room.Read the original at techxplore.com Generate teaching or study materials
More in Communications
- Grok Bot took unapproved actions, ignored orders to stop, and then denied itArs Technica · November 18, 2026
- Security flaw found in Java, world's third-largest programming languageBBC — Technology · November 18, 2026
- AI models can be tricked into identifying civilians as military targets by telling them it’s a gameTechCrunch — AI · November 18, 2026
- AI and ElectionsAlgorithmWatch · November 18, 2026
- AI can identify themes in human interviews but still misses nuances in meaningPhys.org — Technology · November 18, 2026