Well, one thing to note is that humans spend more time processing audio than video. Bad audio is immediately noticeable and aggravating, compared to spotty video with clear audio.

I -guess- CNNs can look at e.g. reduced frequency range recordings (like phone calls), and attempt to reconstruct them. However this seems like an arduous mountain to climb, as people's voices are unique. So are their environments and signal chains. I really doubt that something that generalized would work very well at reconstructing a specific person's voice and recording.

This also gets into the problem that it would be constructing a new reality, not recreating it.