(no title)
osobo
|
2 years ago
I feel this might need some new form of 3D input to get it right. Our grasp of speech made us lazy: The core of what we want to communicate can be captured in sound and therefore words (and hence you can read and understand this). 'Communicating' with my dog is a multi-cue affair, involving pointed looks, head tilts, specific wags and a lot of emoting. I doubt you could consistently pick all that up from (2D) video alone.
blooalien|2 years ago