My two cents…

I have a pal who’s a professional movie audio guy, and the studio he works at — which does sound mostly at the documentary/indie films level (not huge Hollywood) — has lots of high-end sound software to (try to) accomplish all kinds of weird clean up of audio that low-to-no-budget indie and docu filmmakers throw their way. For some of my movie restoration work I’ve thrown him small clips — less than a minute long — for cleaning out dialogue or music from something already mixed to stereo or mono, and while this is totally in his wheelhouse and while his results were decent-to-good (but not perfect) some of these bits took him an hour to do; an hour of his time using all the resources at his studio/work to clean out music or dialogue from a .wav file under a minute long.

So my two cents is that it seems things aren’t there yet as far as your initial request and that you look well into the alternative mentioned by ThatPixarGuy as your solution…although it would be cool if someone chimed in here with a cleaning method that works really well and is not nearly as time intensive.