Adding ASL interpreter after session complete

I work in a languages program and would like to devise a workflow for adding ASL interpretation video to a presentation after it has been recorded. Right now, our Deaf instructors rely on the CC to make sense of presentations. But I would like to improve this by adding video signing. I really like the side-by-side option in viewing MediaSpace screen recordings and would like to figure out a way add interpretations after-the-fact…in a way that doesn’t require me to re-record the existing screencast as a new blurry version of itself.

Essentially, an interpreter would watch and interpret presentations on video. I would then mix this video together with the original screencast to create a MediaSpace object. Is this even possible?

Use cases: ASL interpretation for “How to” videos; ASL interpretations of large group Zoom sessions; and generally enhancing accessibility for Deaf and Hard-of-Hearing instructors.