From the paper's abstract:

>In this paper, we study the task of reconstructing a facial image of a person from a short audio recording of that person speaking.

I can imagine a potentially interesting application of this that has nothing to do with privacy violation or surveillance (that I can see):

What if we could take an audio recording of an ancestor or someone else of interest, for whom we have no pictures, and output a probable face for that person? Sounds interesting and potentially "killer" to me. Maybe I'm wrong.

Generally the killer app for a technology (as I understand the use of the term) is something that is going to earn the creator of the technology lots of money, that basically everyone - either consumers or the members of some specific industry is all going to want that technology and will be willing to pay enough money that the owner of the technology becomes rich.

I can see every police department and government agency paying plenty of money for being able to identify the speaker of a particular sentence in a meeting.

I can see the company with this technology providing services for academic research of the interesting kind you mention for the tax write-offs and also a sort of moral cover, but there is really only one thing I see as their main revenue stream.

That's an interesting take.

I guess the question is, who decides what the killer app for a technology is?