Meta builds AI models that provide realistic sounds in VR settings

New Delhi: Meta (formerly Facebook) has built three new artificial intelligence (AI) models designed to make sound more realistic in mixed and virtual reality experiences.

The three AI models — Visual-Acoustic Matching, Visually-Informed Dereverberation and VisualVoice — focus on human speech and sounds in video and are designed to push “us toward a more immersive reality at a faster rate,” the company said in a statement.