Urgent.News

What's breaking now, across thousands of outlets.

AI

Bearings: Self-Supervised Soundfield Embeddings from First-Order Ambisonics

Recently proposed self-supervised audio encoders learn powerful general-purpose representations of sound scenes, yet they are spatially blind. To supply the missing spatial representation of sound scenes, we introduce Bearings. Bearings is a self-supervised framework that learns soundfield embeddings from unlabeled first-order Ambisonics. We pre-train a masked auto-encoder paired with a decoder…

We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.

Read the original at arxiv.org →

More in AI

Trump announces new 'AI force' amid mounting pressure

Several voices, including from within the AI industry, have been calling for policing the fast-growing technology. Trump has once again called AI warnings "hoaxes" and vowed to "cherish, help" the…

  • US President Donald Trump announces AI force creation.
  • Appoints AI czar to lead new force soon.
  • Trump compares AI force formation to Space Force.

More from Saturday 19 September →